Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk Article Swipe
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2401.05033
Large language models (LLMs) are powerful dialogue agents, but specializing them towards fulfilling a specific function can be challenging. Instructing tuning, i.e. tuning models on instruction and sample responses generated by humans (Ouyang et al., 2022), has proven as an effective method to do so, yet requires a number of data samples that a) might not be available or b) costly to generate. Furthermore, this cost increases when the goal is to make the LLM follow a specific workflow within a dialogue instead of single instructions. Inspired by the self-play technique in reinforcement learning and the use of LLMs to simulate human agents, we propose a more effective method for data collection through LLMs engaging in a conversation in various roles. This approach generates a training data via "self-talk" of LLMs that can be refined and utilized for supervised fine-tuning. We introduce an automated way to measure the (partial) success of a dialogue. This metric is used to filter the generated conversational data that is fed back in LLM for training. Based on our automated and human evaluations of conversation quality, we demonstrate that such self-talk data improves results. In addition, we examine the various characteristics that showcase the quality of generated dialogues and how they can be connected to their potential utility as training data.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2401.05033
- https://arxiv.org/pdf/2401.05033
- OA Status
- green
- Cited By
- 3
- References
- 44
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4390832445
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4390832445Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2401.05033Digital Object Identifier
- Title
-
Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-TalkWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-01-10Full publication date if available
- Authors
-
Dennis Ulmer, Elman Mansimov, Kaixiang Lin, Justin Sun, Xibin Gao, Yi ZhangList of authors in order
- Landing page
-
https://arxiv.org/abs/2401.05033Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2401.05033Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2401.05033Direct OA link when available
- Concepts
-
Conversation, Computer science, Bootstrapping (finance), Workflow, Reinforcement learning, Quality (philosophy), Artificial intelligence, Sample (material), Metric (unit), Task (project management), Human–computer interaction, Psychology, Communication, Operations management, Philosophy, Database, Epistemology, Management, Chromatography, Economics, Chemistry, Financial economicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
3Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 3Per-year citation counts (last 5 years)
- References (count)
-
44Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4390832445 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2401.05033 |
| ids.doi | https://doi.org/10.48550/arxiv.2401.05033 |
| ids.openalex | https://openalex.org/W4390832445 |
| fwci | |
| type | preprint |
| title | Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10028 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9998999834060669 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Topic Modeling |
| topics[1].id | https://openalex.org/T10181 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9983000159263611 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Natural Language Processing Techniques |
| topics[2].id | https://openalex.org/T12031 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.998199999332428 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Speech and dialogue systems |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2777200299 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8081463575363159 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q52943 |
| concepts[0].display_name | Conversation |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7118921279907227 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C207609745 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5975234508514404 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q4944086 |
| concepts[2].display_name | Bootstrapping (finance) |
| concepts[3].id | https://openalex.org/C177212765 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5766139030456543 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q627335 |
| concepts[3].display_name | Workflow |
| concepts[4].id | https://openalex.org/C97541855 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5505990982055664 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q830687 |
| concepts[4].display_name | Reinforcement learning |
| concepts[5].id | https://openalex.org/C2779530757 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5438211560249329 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1207505 |
| concepts[5].display_name | Quality (philosophy) |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.5050414204597473 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C198531522 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4818357229232788 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q485146 |
| concepts[7].display_name | Sample (material) |
| concepts[8].id | https://openalex.org/C176217482 |
| concepts[8].level | 2 |
| concepts[8].score | 0.4478797912597656 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q860554 |
| concepts[8].display_name | Metric (unit) |
| concepts[9].id | https://openalex.org/C2780451532 |
| concepts[9].level | 2 |
| concepts[9].score | 0.4163625240325928 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[9].display_name | Task (project management) |
| concepts[10].id | https://openalex.org/C107457646 |
| concepts[10].level | 1 |
| concepts[10].score | 0.35027986764907837 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q207434 |
| concepts[10].display_name | Human–computer interaction |
| concepts[11].id | https://openalex.org/C15744967 |
| concepts[11].level | 0 |
| concepts[11].score | 0.19561269879341125 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[11].display_name | Psychology |
| concepts[12].id | https://openalex.org/C46312422 |
| concepts[12].level | 1 |
| concepts[12].score | 0.09520962834358215 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q11024 |
| concepts[12].display_name | Communication |
| concepts[13].id | https://openalex.org/C21547014 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q1423657 |
| concepts[13].display_name | Operations management |
| concepts[14].id | https://openalex.org/C138885662 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[14].display_name | Philosophy |
| concepts[15].id | https://openalex.org/C77088390 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q8513 |
| concepts[15].display_name | Database |
| concepts[16].id | https://openalex.org/C111472728 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q9471 |
| concepts[16].display_name | Epistemology |
| concepts[17].id | https://openalex.org/C187736073 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q2920921 |
| concepts[17].display_name | Management |
| concepts[18].id | https://openalex.org/C43617362 |
| concepts[18].level | 1 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q170050 |
| concepts[18].display_name | Chromatography |
| concepts[19].id | https://openalex.org/C162324750 |
| concepts[19].level | 0 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[19].display_name | Economics |
| concepts[20].id | https://openalex.org/C185592680 |
| concepts[20].level | 0 |
| concepts[20].score | 0.0 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[20].display_name | Chemistry |
| concepts[21].id | https://openalex.org/C106159729 |
| concepts[21].level | 1 |
| concepts[21].score | 0.0 |
| concepts[21].wikidata | https://www.wikidata.org/wiki/Q2294553 |
| concepts[21].display_name | Financial economics |
| keywords[0].id | https://openalex.org/keywords/conversation |
| keywords[0].score | 0.8081463575363159 |
| keywords[0].display_name | Conversation |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7118921279907227 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/bootstrapping |
| keywords[2].score | 0.5975234508514404 |
| keywords[2].display_name | Bootstrapping (finance) |
| keywords[3].id | https://openalex.org/keywords/workflow |
| keywords[3].score | 0.5766139030456543 |
| keywords[3].display_name | Workflow |
| keywords[4].id | https://openalex.org/keywords/reinforcement-learning |
| keywords[4].score | 0.5505990982055664 |
| keywords[4].display_name | Reinforcement learning |
| keywords[5].id | https://openalex.org/keywords/quality |
| keywords[5].score | 0.5438211560249329 |
| keywords[5].display_name | Quality (philosophy) |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.5050414204597473 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/sample |
| keywords[7].score | 0.4818357229232788 |
| keywords[7].display_name | Sample (material) |
| keywords[8].id | https://openalex.org/keywords/metric |
| keywords[8].score | 0.4478797912597656 |
| keywords[8].display_name | Metric (unit) |
| keywords[9].id | https://openalex.org/keywords/task |
| keywords[9].score | 0.4163625240325928 |
| keywords[9].display_name | Task (project management) |
| keywords[10].id | https://openalex.org/keywords/human–computer-interaction |
| keywords[10].score | 0.35027986764907837 |
| keywords[10].display_name | Human–computer interaction |
| keywords[11].id | https://openalex.org/keywords/psychology |
| keywords[11].score | 0.19561269879341125 |
| keywords[11].display_name | Psychology |
| keywords[12].id | https://openalex.org/keywords/communication |
| keywords[12].score | 0.09520962834358215 |
| keywords[12].display_name | Communication |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2401.05033 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2401.05033 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2401.05033 |
| locations[1].id | pmh:oai:pure.atira.dk:openaire/a6e2dd9e-6851-42bf-9d0a-52f7e84d87b1 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400216 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | Research Portal (King's College London) |
| locations[1].source.host_organization | https://openalex.org/I183935753 |
| locations[1].source.host_organization_name | King's College London |
| locations[1].source.host_organization_lineage | https://openalex.org/I183935753 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | submittedVersion |
| locations[1].raw_type | contributionToPeriodical |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | Ulmer, D T, Mansimov, E, Lin, K, Sun, J, Gao, X & Zhang, Y 2024, Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk. in L-W Ku, A Martins & V Srikumar (eds), Findings of the Association for Computational Linguistics ACL 2024. vol. Findings of the Association for Computational Linguistics ACL 2024, Association for Computational Linguistics, Bangkok, pp. 9500–9522. https://doi.org/10.48550/arXiv.2401.05033 |
| locations[1].landing_page_url | https://pure.itu.dk/portal/da/publications/a6e2dd9e-6851-42bf-9d0a-52f7e84d87b1 |
| locations[2].id | doi:10.48550/arxiv.2401.05033 |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S4306400194 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | True |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | arXiv (Cornell University) |
| locations[2].source.host_organization | https://openalex.org/I205783295 |
| locations[2].source.host_organization_name | Cornell University |
| locations[2].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[2].license | cc-by |
| locations[2].pdf_url | |
| locations[2].version | |
| locations[2].raw_type | article |
| locations[2].license_id | https://openalex.org/licenses/cc-by |
| locations[2].is_accepted | False |
| locations[2].is_published | |
| locations[2].raw_source_name | |
| locations[2].landing_page_url | https://doi.org/10.48550/arxiv.2401.05033 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5001376704 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Dennis Ulmer |
| authorships[0].countries | DK, US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I1343180700, https://openalex.org/I139025015, https://openalex.org/I83467386 |
| authorships[0].affiliations[0].raw_affiliation_string | IT University of Copenhagen Pioneer Centre for Artificial Intelligence AWS AI Labs |
| authorships[0].institutions[0].id | https://openalex.org/I83467386 |
| authorships[0].institutions[0].ror | https://ror.org/02309jg23 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I83467386 |
| authorships[0].institutions[0].country_code | DK |
| authorships[0].institutions[0].display_name | IT University of Copenhagen |
| authorships[0].institutions[1].id | https://openalex.org/I1343180700 |
| authorships[0].institutions[1].ror | https://ror.org/01ek73717 |
| authorships[0].institutions[1].type | company |
| authorships[0].institutions[1].lineage | https://openalex.org/I1343180700 |
| authorships[0].institutions[1].country_code | US |
| authorships[0].institutions[1].display_name | Intel (United States) |
| authorships[0].institutions[2].id | https://openalex.org/I139025015 |
| authorships[0].institutions[2].ror | https://ror.org/05jke7315 |
| authorships[0].institutions[2].type | company |
| authorships[0].institutions[2].lineage | https://openalex.org/I139025015, https://openalex.org/I4210104019 |
| authorships[0].institutions[2].country_code | US |
| authorships[0].institutions[2].display_name | Pioneer (United States) |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Dennis Ulmer |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | IT University of Copenhagen Pioneer Centre for Artificial Intelligence AWS AI Labs |
| authorships[1].author.id | https://openalex.org/A5045225880 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Elman Mansimov |
| authorships[1].countries | DK, US |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I1343180700, https://openalex.org/I139025015, https://openalex.org/I83467386 |
| authorships[1].affiliations[0].raw_affiliation_string | IT University of Copenhagen Pioneer Centre for Artificial Intelligence AWS AI Labs |
| authorships[1].institutions[0].id | https://openalex.org/I83467386 |
| authorships[1].institutions[0].ror | https://ror.org/02309jg23 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I83467386 |
| authorships[1].institutions[0].country_code | DK |
| authorships[1].institutions[0].display_name | IT University of Copenhagen |
| authorships[1].institutions[1].id | https://openalex.org/I1343180700 |
| authorships[1].institutions[1].ror | https://ror.org/01ek73717 |
| authorships[1].institutions[1].type | company |
| authorships[1].institutions[1].lineage | https://openalex.org/I1343180700 |
| authorships[1].institutions[1].country_code | US |
| authorships[1].institutions[1].display_name | Intel (United States) |
| authorships[1].institutions[2].id | https://openalex.org/I139025015 |
| authorships[1].institutions[2].ror | https://ror.org/05jke7315 |
| authorships[1].institutions[2].type | company |
| authorships[1].institutions[2].lineage | https://openalex.org/I139025015, https://openalex.org/I4210104019 |
| authorships[1].institutions[2].country_code | US |
| authorships[1].institutions[2].display_name | Pioneer (United States) |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Elman Mansimov |
| authorships[1].is_corresponding | True |
| authorships[1].raw_affiliation_strings | IT University of Copenhagen Pioneer Centre for Artificial Intelligence AWS AI Labs |
| authorships[2].author.id | https://openalex.org/A5100443077 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-8626-8934 |
| authorships[2].author.display_name | Kaixiang Lin |
| authorships[2].countries | DK, US |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I1343180700, https://openalex.org/I139025015, https://openalex.org/I83467386 |
| authorships[2].affiliations[0].raw_affiliation_string | IT University of Copenhagen Pioneer Centre for Artificial Intelligence AWS AI Labs |
| authorships[2].institutions[0].id | https://openalex.org/I83467386 |
| authorships[2].institutions[0].ror | https://ror.org/02309jg23 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I83467386 |
| authorships[2].institutions[0].country_code | DK |
| authorships[2].institutions[0].display_name | IT University of Copenhagen |
| authorships[2].institutions[1].id | https://openalex.org/I1343180700 |
| authorships[2].institutions[1].ror | https://ror.org/01ek73717 |
| authorships[2].institutions[1].type | company |
| authorships[2].institutions[1].lineage | https://openalex.org/I1343180700 |
| authorships[2].institutions[1].country_code | US |
| authorships[2].institutions[1].display_name | Intel (United States) |
| authorships[2].institutions[2].id | https://openalex.org/I139025015 |
| authorships[2].institutions[2].ror | https://ror.org/05jke7315 |
| authorships[2].institutions[2].type | company |
| authorships[2].institutions[2].lineage | https://openalex.org/I139025015, https://openalex.org/I4210104019 |
| authorships[2].institutions[2].country_code | US |
| authorships[2].institutions[2].display_name | Pioneer (United States) |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Kaixiang Lin |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | IT University of Copenhagen Pioneer Centre for Artificial Intelligence AWS AI Labs |
| authorships[3].author.id | https://openalex.org/A5020079535 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-1879-1598 |
| authorships[3].author.display_name | Justin Sun |
| authorships[3].countries | DK, US |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I1343180700, https://openalex.org/I139025015, https://openalex.org/I83467386 |
| authorships[3].affiliations[0].raw_affiliation_string | IT University of Copenhagen Pioneer Centre for Artificial Intelligence AWS AI Labs |
| authorships[3].institutions[0].id | https://openalex.org/I83467386 |
| authorships[3].institutions[0].ror | https://ror.org/02309jg23 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I83467386 |
| authorships[3].institutions[0].country_code | DK |
| authorships[3].institutions[0].display_name | IT University of Copenhagen |
| authorships[3].institutions[1].id | https://openalex.org/I1343180700 |
| authorships[3].institutions[1].ror | https://ror.org/01ek73717 |
| authorships[3].institutions[1].type | company |
| authorships[3].institutions[1].lineage | https://openalex.org/I1343180700 |
| authorships[3].institutions[1].country_code | US |
| authorships[3].institutions[1].display_name | Intel (United States) |
| authorships[3].institutions[2].id | https://openalex.org/I139025015 |
| authorships[3].institutions[2].ror | https://ror.org/05jke7315 |
| authorships[3].institutions[2].type | company |
| authorships[3].institutions[2].lineage | https://openalex.org/I139025015, https://openalex.org/I4210104019 |
| authorships[3].institutions[2].country_code | US |
| authorships[3].institutions[2].display_name | Pioneer (United States) |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Justin Sun |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | IT University of Copenhagen Pioneer Centre for Artificial Intelligence AWS AI Labs |
| authorships[4].author.id | https://openalex.org/A5067794533 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-6644-2640 |
| authorships[4].author.display_name | Xibin Gao |
| authorships[4].countries | DK, US |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I1343180700, https://openalex.org/I139025015, https://openalex.org/I83467386 |
| authorships[4].affiliations[0].raw_affiliation_string | IT University of Copenhagen Pioneer Centre for Artificial Intelligence AWS AI Labs |
| authorships[4].institutions[0].id | https://openalex.org/I83467386 |
| authorships[4].institutions[0].ror | https://ror.org/02309jg23 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I83467386 |
| authorships[4].institutions[0].country_code | DK |
| authorships[4].institutions[0].display_name | IT University of Copenhagen |
| authorships[4].institutions[1].id | https://openalex.org/I1343180700 |
| authorships[4].institutions[1].ror | https://ror.org/01ek73717 |
| authorships[4].institutions[1].type | company |
| authorships[4].institutions[1].lineage | https://openalex.org/I1343180700 |
| authorships[4].institutions[1].country_code | US |
| authorships[4].institutions[1].display_name | Intel (United States) |
| authorships[4].institutions[2].id | https://openalex.org/I139025015 |
| authorships[4].institutions[2].ror | https://ror.org/05jke7315 |
| authorships[4].institutions[2].type | company |
| authorships[4].institutions[2].lineage | https://openalex.org/I139025015, https://openalex.org/I4210104019 |
| authorships[4].institutions[2].country_code | US |
| authorships[4].institutions[2].display_name | Pioneer (United States) |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Xibin Gao |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | IT University of Copenhagen Pioneer Centre for Artificial Intelligence AWS AI Labs |
| authorships[5].author.id | https://openalex.org/A5100388367 |
| authorships[5].author.orcid | https://orcid.org/0009-0007-7269-8187 |
| authorships[5].author.display_name | Yi Zhang |
| authorships[5].countries | DK, US |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I1343180700, https://openalex.org/I139025015, https://openalex.org/I83467386 |
| authorships[5].affiliations[0].raw_affiliation_string | IT University of Copenhagen Pioneer Centre for Artificial Intelligence AWS AI Labs |
| authorships[5].institutions[0].id | https://openalex.org/I83467386 |
| authorships[5].institutions[0].ror | https://ror.org/02309jg23 |
| authorships[5].institutions[0].type | education |
| authorships[5].institutions[0].lineage | https://openalex.org/I83467386 |
| authorships[5].institutions[0].country_code | DK |
| authorships[5].institutions[0].display_name | IT University of Copenhagen |
| authorships[5].institutions[1].id | https://openalex.org/I1343180700 |
| authorships[5].institutions[1].ror | https://ror.org/01ek73717 |
| authorships[5].institutions[1].type | company |
| authorships[5].institutions[1].lineage | https://openalex.org/I1343180700 |
| authorships[5].institutions[1].country_code | US |
| authorships[5].institutions[1].display_name | Intel (United States) |
| authorships[5].institutions[2].id | https://openalex.org/I139025015 |
| authorships[5].institutions[2].ror | https://ror.org/05jke7315 |
| authorships[5].institutions[2].type | company |
| authorships[5].institutions[2].lineage | https://openalex.org/I139025015, https://openalex.org/I4210104019 |
| authorships[5].institutions[2].country_code | US |
| authorships[5].institutions[2].display_name | Pioneer (United States) |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Yi Zhang |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | IT University of Copenhagen Pioneer Centre for Artificial Intelligence AWS AI Labs |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2401.05033 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10028 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9998999834060669 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Topic Modeling |
| related_works | https://openalex.org/W2899084033, https://openalex.org/W1968552888, https://openalex.org/W1534274833, https://openalex.org/W2374116601, https://openalex.org/W3093134843, https://openalex.org/W1511346092, https://openalex.org/W1527532029, https://openalex.org/W2378167147, https://openalex.org/W3210777354, https://openalex.org/W2281307425 |
| cited_by_count | 3 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 3 |
| locations_count | 3 |
| best_oa_location.id | pmh:oai:arXiv.org:2401.05033 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2401.05033 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2401.05033 |
| primary_location.id | pmh:oai:arXiv.org:2401.05033 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2401.05033 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2401.05033 |
| publication_date | 2024-01-10 |
| publication_year | 2024 |
| referenced_works | https://openalex.org/W2132994929, https://openalex.org/W2154652894, https://openalex.org/W3153451655, https://openalex.org/W2963096510, https://openalex.org/W4226278401, https://openalex.org/W3118210634, https://openalex.org/W4385573440, https://openalex.org/W2766447205, https://openalex.org/W2806600904, https://openalex.org/W4322718191, https://openalex.org/W4378718328, https://openalex.org/W4302305863, https://openalex.org/W3211686893, https://openalex.org/W4321455981, https://openalex.org/W4311991106, https://openalex.org/W4379251563, https://openalex.org/W4385574182, https://openalex.org/W4287687520, https://openalex.org/W4386080611, https://openalex.org/W4287365906, https://openalex.org/W4387835442, https://openalex.org/W2963283805, https://openalex.org/W4322759378, https://openalex.org/W3168867926, https://openalex.org/W4378765257, https://openalex.org/W4377865937, https://openalex.org/W4365205411, https://openalex.org/W4378771755, https://openalex.org/W4385572854, https://openalex.org/W3172407229, https://openalex.org/W2953183526, https://openalex.org/W2784070054, https://openalex.org/W3122890974, https://openalex.org/W4282968607, https://openalex.org/W4390430574, https://openalex.org/W2611081871, https://openalex.org/W4226462293, https://openalex.org/W2970252402, https://openalex.org/W4411630224, https://openalex.org/W2257979135, https://openalex.org/W2938704169, https://openalex.org/W4376312605, https://openalex.org/W2041367235, https://openalex.org/W4361807044 |
| referenced_works_count | 44 |
| abstract_inverted_index.a | 13, 47, 76, 80, 105, 116, 124, 151 |
| abstract_inverted_index.In | 189 |
| abstract_inverted_index.We | 140 |
| abstract_inverted_index.a) | 53 |
| abstract_inverted_index.an | 39, 142 |
| abstract_inverted_index.as | 38, 213 |
| abstract_inverted_index.b) | 59 |
| abstract_inverted_index.be | 17, 56, 133, 207 |
| abstract_inverted_index.by | 30, 87 |
| abstract_inverted_index.do | 43 |
| abstract_inverted_index.et | 33 |
| abstract_inverted_index.in | 91, 115, 118, 167 |
| abstract_inverted_index.is | 70, 155, 164 |
| abstract_inverted_index.of | 49, 83, 97, 129, 150, 178, 200 |
| abstract_inverted_index.on | 24, 172 |
| abstract_inverted_index.or | 58 |
| abstract_inverted_index.to | 42, 61, 71, 99, 145, 157, 209 |
| abstract_inverted_index.we | 103, 181, 191 |
| abstract_inverted_index.LLM | 74, 168 |
| abstract_inverted_index.and | 26, 94, 135, 175, 203 |
| abstract_inverted_index.are | 4 |
| abstract_inverted_index.but | 8 |
| abstract_inverted_index.can | 16, 132, 206 |
| abstract_inverted_index.fed | 165 |
| abstract_inverted_index.for | 109, 137, 169 |
| abstract_inverted_index.has | 36 |
| abstract_inverted_index.how | 204 |
| abstract_inverted_index.not | 55 |
| abstract_inverted_index.our | 173 |
| abstract_inverted_index.so, | 44 |
| abstract_inverted_index.the | 68, 73, 88, 95, 147, 159, 193, 198 |
| abstract_inverted_index.use | 96 |
| abstract_inverted_index.via | 127 |
| abstract_inverted_index.way | 144 |
| abstract_inverted_index.yet | 45 |
| abstract_inverted_index.LLMs | 98, 113, 130 |
| abstract_inverted_index.This | 121, 153 |
| abstract_inverted_index.al., | 34 |
| abstract_inverted_index.back | 166 |
| abstract_inverted_index.cost | 65 |
| abstract_inverted_index.data | 50, 110, 126, 162, 186 |
| abstract_inverted_index.goal | 69 |
| abstract_inverted_index.i.e. | 21 |
| abstract_inverted_index.make | 72 |
| abstract_inverted_index.more | 106 |
| abstract_inverted_index.such | 184 |
| abstract_inverted_index.that | 52, 131, 163, 183, 196 |
| abstract_inverted_index.them | 10 |
| abstract_inverted_index.they | 205 |
| abstract_inverted_index.this | 64 |
| abstract_inverted_index.used | 156 |
| abstract_inverted_index.when | 67 |
| abstract_inverted_index.Based | 171 |
| abstract_inverted_index.Large | 0 |
| abstract_inverted_index.data. | 215 |
| abstract_inverted_index.human | 101, 176 |
| abstract_inverted_index.might | 54 |
| abstract_inverted_index.their | 210 |
| abstract_inverted_index.(LLMs) | 3 |
| abstract_inverted_index.2022), | 35 |
| abstract_inverted_index.costly | 60 |
| abstract_inverted_index.filter | 158 |
| abstract_inverted_index.follow | 75 |
| abstract_inverted_index.humans | 31 |
| abstract_inverted_index.method | 41, 108 |
| abstract_inverted_index.metric | 154 |
| abstract_inverted_index.models | 2, 23 |
| abstract_inverted_index.number | 48 |
| abstract_inverted_index.proven | 37 |
| abstract_inverted_index.roles. | 120 |
| abstract_inverted_index.sample | 27 |
| abstract_inverted_index.single | 84 |
| abstract_inverted_index.tuning | 22 |
| abstract_inverted_index.within | 79 |
| abstract_inverted_index.(Ouyang | 32 |
| abstract_inverted_index.agents, | 7, 102 |
| abstract_inverted_index.examine | 192 |
| abstract_inverted_index.instead | 82 |
| abstract_inverted_index.measure | 146 |
| abstract_inverted_index.propose | 104 |
| abstract_inverted_index.quality | 199 |
| abstract_inverted_index.refined | 134 |
| abstract_inverted_index.samples | 51 |
| abstract_inverted_index.success | 149 |
| abstract_inverted_index.through | 112 |
| abstract_inverted_index.towards | 11 |
| abstract_inverted_index.tuning, | 20 |
| abstract_inverted_index.utility | 212 |
| abstract_inverted_index.various | 119, 194 |
| abstract_inverted_index.Inspired | 86 |
| abstract_inverted_index.approach | 122 |
| abstract_inverted_index.dialogue | 6, 81 |
| abstract_inverted_index.engaging | 114 |
| abstract_inverted_index.function | 15 |
| abstract_inverted_index.improves | 187 |
| abstract_inverted_index.language | 1 |
| abstract_inverted_index.learning | 93 |
| abstract_inverted_index.powerful | 5 |
| abstract_inverted_index.quality, | 180 |
| abstract_inverted_index.requires | 46 |
| abstract_inverted_index.results. | 188 |
| abstract_inverted_index.showcase | 197 |
| abstract_inverted_index.simulate | 100 |
| abstract_inverted_index.specific | 14, 77 |
| abstract_inverted_index.training | 125, 214 |
| abstract_inverted_index.utilized | 136 |
| abstract_inverted_index.workflow | 78 |
| abstract_inverted_index.(partial) | 148 |
| abstract_inverted_index.addition, | 190 |
| abstract_inverted_index.automated | 143, 174 |
| abstract_inverted_index.available | 57 |
| abstract_inverted_index.connected | 208 |
| abstract_inverted_index.dialogue. | 152 |
| abstract_inverted_index.dialogues | 202 |
| abstract_inverted_index.effective | 40, 107 |
| abstract_inverted_index.generate. | 62 |
| abstract_inverted_index.generated | 29, 160, 201 |
| abstract_inverted_index.generates | 123 |
| abstract_inverted_index.increases | 66 |
| abstract_inverted_index.introduce | 141 |
| abstract_inverted_index.potential | 211 |
| abstract_inverted_index.responses | 28 |
| abstract_inverted_index.self-play | 89 |
| abstract_inverted_index.self-talk | 185 |
| abstract_inverted_index.technique | 90 |
| abstract_inverted_index.training. | 170 |
| abstract_inverted_index.collection | 111 |
| abstract_inverted_index.fulfilling | 12 |
| abstract_inverted_index.supervised | 138 |
| abstract_inverted_index."self-talk" | 128 |
| abstract_inverted_index.Instructing | 19 |
| abstract_inverted_index.demonstrate | 182 |
| abstract_inverted_index.evaluations | 177 |
| abstract_inverted_index.instruction | 25 |
| abstract_inverted_index.Furthermore, | 63 |
| abstract_inverted_index.challenging. | 18 |
| abstract_inverted_index.conversation | 117, 179 |
| abstract_inverted_index.fine-tuning. | 139 |
| abstract_inverted_index.specializing | 9 |
| abstract_inverted_index.instructions. | 85 |
| abstract_inverted_index.reinforcement | 92 |
| abstract_inverted_index.conversational | 161 |
| abstract_inverted_index.characteristics | 195 |
| cited_by_percentile_year | |
| corresponding_author_ids | https://openalex.org/A5045225880 |
| countries_distinct_count | 2 |
| institutions_distinct_count | 6 |
| corresponding_institution_ids | https://openalex.org/I1343180700, https://openalex.org/I139025015, https://openalex.org/I83467386 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.6899999976158142 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile |