CoSER: Coordinating LLM-Based Persona Simulation of Established Roles Article Swipe
Xintao Wang
,
Heng Wang
,
Yifei Zhang
,
Xinfeng Yuan
,
Rui‐Hua Xu
,
Jen-tse Huang
,
Siyu Yuan
,
Haoran Guo
,
Jiangjie Chen
,
Wei Wang
,
Yanghua Xiao
,
Shuchang Zhou
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2502.09082
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2502.09082
Role-playing language agents (RPLAs) have emerged as promising applications of large language models (LLMs). However, simulating established characters presents a challenging task for RPLAs, due to the lack of authentic character datasets and nuanced evaluation methods using such data. In this paper, we present CoSER, a collection of a high-quality dataset, open models, and an evaluation protocol towards effective RPLAs of established characters. The CoSER dataset covers 17,966 characters from 771 renowned books. It provides authentic dialogues with real-world intricacies, as well as diverse data types such as conversation setups, character experiences and internal thoughts. Drawing from acting methodology, we introduce given-circumstance acting for training and evaluating role-playing LLMs, where LLMs sequentially portray multiple characters in book scenes. Using our dataset, we develop CoSER 8B and CoSER 70B, i.e., advanced open role-playing LLMs built on LLaMA-3.1 models. Extensive experiments demonstrate the value of the CoSER dataset for RPLA training, evaluation and retrieval. Moreover, CoSER 70B exhibits state-of-the-art performance surpassing or matching GPT-4o on our evaluation and three existing benchmarks, i.e., achieving 75.80% and 93.47% accuracy on the InCharacter and LifeChoice benchmarks respectively.
Related Topics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2502.09082
- https://arxiv.org/pdf/2502.09082
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4407571828
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4407571828Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2502.09082Digital Object Identifier
- Title
-
CoSER: Coordinating LLM-Based Persona Simulation of Established RolesWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-02-13Full publication date if available
- Authors
-
Xintao Wang, Heng Wang, Yifei Zhang, Xinfeng Yuan, Rui‐Hua Xu, Jen-tse Huang, Siyu Yuan, Haoran Guo, Jiangjie Chen, Wei Wang, Yanghua Xiao, Shuchang ZhouList of authors in order
- Landing page
-
https://arxiv.org/abs/2502.09082Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2502.09082Direct 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/2502.09082Direct OA link when available
- Concepts
-
Persona, Computer science, Psychology, Human–computer interaction, EngineeringTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4407571828 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2502.09082 |
| ids.doi | https://doi.org/10.48550/arxiv.2502.09082 |
| ids.openalex | https://openalex.org/W4407571828 |
| fwci | |
| type | preprint |
| title | CoSER: Coordinating LLM-Based Persona Simulation of Established Roles |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T14074 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.995199978351593 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1709 |
| topics[0].subfield.display_name | Human-Computer Interaction |
| topics[0].display_name | Persona Design and Applications |
| topics[1].id | https://openalex.org/T10350 |
| topics[1].field.id | https://openalex.org/fields/36 |
| topics[1].field.display_name | Health Professions |
| topics[1].score | 0.9296000003814697 |
| topics[1].domain.id | https://openalex.org/domains/4 |
| topics[1].domain.display_name | Health Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/3605 |
| topics[1].subfield.display_name | Health Information Management |
| topics[1].display_name | Electronic Health Records Systems |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C313442 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8934690952301025 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q778556 |
| concepts[0].display_name | Persona |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.3667870759963989 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C15744967 |
| concepts[2].level | 0 |
| concepts[2].score | 0.3622381091117859 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[2].display_name | Psychology |
| concepts[3].id | https://openalex.org/C107457646 |
| concepts[3].level | 1 |
| concepts[3].score | 0.34456685185432434 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q207434 |
| concepts[3].display_name | Human–computer interaction |
| concepts[4].id | https://openalex.org/C127413603 |
| concepts[4].level | 0 |
| concepts[4].score | 0.3290766477584839 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[4].display_name | Engineering |
| keywords[0].id | https://openalex.org/keywords/persona |
| keywords[0].score | 0.8934690952301025 |
| keywords[0].display_name | Persona |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.3667870759963989 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/psychology |
| keywords[2].score | 0.3622381091117859 |
| keywords[2].display_name | Psychology |
| keywords[3].id | https://openalex.org/keywords/human–computer-interaction |
| keywords[3].score | 0.34456685185432434 |
| keywords[3].display_name | Human–computer interaction |
| keywords[4].id | https://openalex.org/keywords/engineering |
| keywords[4].score | 0.3290766477584839 |
| keywords[4].display_name | Engineering |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2502.09082 |
| 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/2502.09082 |
| 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/2502.09082 |
| locations[1].id | doi:10.48550/arxiv.2502.09082 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2502.09082 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5101538534 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-6585-8604 |
| authorships[0].author.display_name | Xintao Wang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Wang, Xintao |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100453986 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-3692-0848 |
| authorships[1].author.display_name | Heng Wang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Wang, Heng |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5021535403 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-7068-1700 |
| authorships[2].author.display_name | Yifei Zhang |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Zhang, Yifei |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5111178474 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Xinfeng Yuan |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Yuan, Xinfeng |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5101613292 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-9771-8534 |
| authorships[4].author.display_name | Rui‐Hua Xu |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Xu, Rui |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5047584018 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-3446-0083 |
| authorships[5].author.display_name | Jen-tse Huang |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Huang, Jen-tse |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5103134216 |
| authorships[6].author.orcid | https://orcid.org/0009-0004-4439-0984 |
| authorships[6].author.display_name | Siyu Yuan |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Yuan, Siyu |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5103196727 |
| authorships[7].author.orcid | https://orcid.org/0000-0001-8244-5545 |
| authorships[7].author.display_name | Haoran Guo |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Guo, Haoran |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5044059576 |
| authorships[8].author.orcid | https://orcid.org/0000-0002-2613-0386 |
| authorships[8].author.display_name | Jiangjie Chen |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Chen, Jiangjie |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5051392171 |
| authorships[9].author.orcid | https://orcid.org/0000-0002-9610-4810 |
| authorships[9].author.display_name | Wei Wang |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | Wang, Wei |
| authorships[9].is_corresponding | False |
| authorships[10].author.id | https://openalex.org/A5090455375 |
| authorships[10].author.orcid | https://orcid.org/0000-0001-8403-9591 |
| authorships[10].author.display_name | Yanghua Xiao |
| authorships[10].author_position | middle |
| authorships[10].raw_author_name | Xiao, Yanghua |
| authorships[10].is_corresponding | False |
| authorships[11].author.id | https://openalex.org/A5008993224 |
| authorships[11].author.orcid | https://orcid.org/0000-0002-7294-5869 |
| authorships[11].author.display_name | Shuchang Zhou |
| authorships[11].author_position | last |
| authorships[11].raw_author_name | Zhou, Shuchang |
| authorships[11].is_corresponding | False |
| 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/2502.09082 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | CoSER: Coordinating LLM-Based Persona Simulation of Established Roles |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T14074 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.995199978351593 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1709 |
| primary_topic.subfield.display_name | Human-Computer Interaction |
| primary_topic.display_name | Persona Design and Applications |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2795366572, https://openalex.org/W2886588594, https://openalex.org/W3005214328, https://openalex.org/W3091061106, https://openalex.org/W2610743940, https://openalex.org/W4312802148, https://openalex.org/W4389400787 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2502.09082 |
| 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/2502.09082 |
| 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/2502.09082 |
| primary_location.id | pmh:oai:arXiv.org:2502.09082 |
| 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/2502.09082 |
| 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/2502.09082 |
| publication_date | 2025-02-13 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 19, 45, 48 |
| abstract_inverted_index.8B | 124 |
| abstract_inverted_index.In | 39 |
| abstract_inverted_index.It | 73 |
| abstract_inverted_index.an | 54 |
| abstract_inverted_index.as | 6, 80, 82, 87 |
| abstract_inverted_index.in | 115 |
| abstract_inverted_index.of | 9, 28, 47, 60, 142 |
| abstract_inverted_index.on | 134, 162, 175 |
| abstract_inverted_index.or | 159 |
| abstract_inverted_index.to | 25 |
| abstract_inverted_index.we | 42, 99, 121 |
| abstract_inverted_index.70B | 154 |
| abstract_inverted_index.771 | 70 |
| abstract_inverted_index.The | 63 |
| abstract_inverted_index.and | 32, 53, 92, 105, 125, 150, 165, 172, 178 |
| abstract_inverted_index.due | 24 |
| abstract_inverted_index.for | 22, 103, 146 |
| abstract_inverted_index.our | 119, 163 |
| abstract_inverted_index.the | 26, 140, 143, 176 |
| abstract_inverted_index.70B, | 127 |
| abstract_inverted_index.LLMs | 110, 132 |
| abstract_inverted_index.RPLA | 147 |
| abstract_inverted_index.book | 116 |
| abstract_inverted_index.data | 84 |
| abstract_inverted_index.from | 69, 96 |
| abstract_inverted_index.have | 4 |
| abstract_inverted_index.lack | 27 |
| abstract_inverted_index.open | 51, 130 |
| abstract_inverted_index.such | 37, 86 |
| abstract_inverted_index.task | 21 |
| abstract_inverted_index.this | 40 |
| abstract_inverted_index.well | 81 |
| abstract_inverted_index.with | 77 |
| abstract_inverted_index.CoSER | 64, 123, 126, 144, 153 |
| abstract_inverted_index.LLMs, | 108 |
| abstract_inverted_index.RPLAs | 59 |
| abstract_inverted_index.Using | 118 |
| abstract_inverted_index.built | 133 |
| abstract_inverted_index.data. | 38 |
| abstract_inverted_index.i.e., | 128, 169 |
| abstract_inverted_index.large | 10 |
| abstract_inverted_index.three | 166 |
| abstract_inverted_index.types | 85 |
| abstract_inverted_index.using | 36 |
| abstract_inverted_index.value | 141 |
| abstract_inverted_index.where | 109 |
| abstract_inverted_index.17,966 | 67 |
| abstract_inverted_index.75.80% | 171 |
| abstract_inverted_index.93.47% | 173 |
| abstract_inverted_index.CoSER, | 44 |
| abstract_inverted_index.GPT-4o | 161 |
| abstract_inverted_index.RPLAs, | 23 |
| abstract_inverted_index.acting | 97, 102 |
| abstract_inverted_index.agents | 2 |
| abstract_inverted_index.books. | 72 |
| abstract_inverted_index.covers | 66 |
| abstract_inverted_index.models | 12 |
| abstract_inverted_index.paper, | 41 |
| abstract_inverted_index.(LLMs). | 13 |
| abstract_inverted_index.(RPLAs) | 3 |
| abstract_inverted_index.Drawing | 95 |
| abstract_inverted_index.dataset | 65, 145 |
| abstract_inverted_index.develop | 122 |
| abstract_inverted_index.diverse | 83 |
| abstract_inverted_index.emerged | 5 |
| abstract_inverted_index.methods | 35 |
| abstract_inverted_index.models, | 52 |
| abstract_inverted_index.models. | 136 |
| abstract_inverted_index.nuanced | 33 |
| abstract_inverted_index.portray | 112 |
| abstract_inverted_index.present | 43 |
| abstract_inverted_index.scenes. | 117 |
| abstract_inverted_index.setups, | 89 |
| abstract_inverted_index.towards | 57 |
| abstract_inverted_index.However, | 14 |
| abstract_inverted_index.accuracy | 174 |
| abstract_inverted_index.advanced | 129 |
| abstract_inverted_index.dataset, | 50, 120 |
| abstract_inverted_index.datasets | 31 |
| abstract_inverted_index.exhibits | 155 |
| abstract_inverted_index.existing | 167 |
| abstract_inverted_index.internal | 93 |
| abstract_inverted_index.language | 1, 11 |
| abstract_inverted_index.matching | 160 |
| abstract_inverted_index.multiple | 113 |
| abstract_inverted_index.presents | 18 |
| abstract_inverted_index.protocol | 56 |
| abstract_inverted_index.provides | 74 |
| abstract_inverted_index.renowned | 71 |
| abstract_inverted_index.training | 104 |
| abstract_inverted_index.Extensive | 137 |
| abstract_inverted_index.LLaMA-3.1 | 135 |
| abstract_inverted_index.Moreover, | 152 |
| abstract_inverted_index.achieving | 170 |
| abstract_inverted_index.authentic | 29, 75 |
| abstract_inverted_index.character | 30, 90 |
| abstract_inverted_index.dialogues | 76 |
| abstract_inverted_index.effective | 58 |
| abstract_inverted_index.introduce | 100 |
| abstract_inverted_index.promising | 7 |
| abstract_inverted_index.thoughts. | 94 |
| abstract_inverted_index.training, | 148 |
| abstract_inverted_index.LifeChoice | 179 |
| abstract_inverted_index.benchmarks | 180 |
| abstract_inverted_index.characters | 17, 68, 114 |
| abstract_inverted_index.collection | 46 |
| abstract_inverted_index.evaluating | 106 |
| abstract_inverted_index.evaluation | 34, 55, 149, 164 |
| abstract_inverted_index.real-world | 78 |
| abstract_inverted_index.retrieval. | 151 |
| abstract_inverted_index.simulating | 15 |
| abstract_inverted_index.surpassing | 158 |
| abstract_inverted_index.InCharacter | 177 |
| abstract_inverted_index.benchmarks, | 168 |
| abstract_inverted_index.challenging | 20 |
| abstract_inverted_index.characters. | 62 |
| abstract_inverted_index.demonstrate | 139 |
| abstract_inverted_index.established | 16, 61 |
| abstract_inverted_index.experiences | 91 |
| abstract_inverted_index.experiments | 138 |
| abstract_inverted_index.performance | 157 |
| abstract_inverted_index.Role-playing | 0 |
| abstract_inverted_index.applications | 8 |
| abstract_inverted_index.conversation | 88 |
| abstract_inverted_index.high-quality | 49 |
| abstract_inverted_index.intricacies, | 79 |
| abstract_inverted_index.methodology, | 98 |
| abstract_inverted_index.role-playing | 107, 131 |
| abstract_inverted_index.sequentially | 111 |
| abstract_inverted_index.respectively. | 181 |
| abstract_inverted_index.state-of-the-art | 156 |
| abstract_inverted_index.given-circumstance | 101 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 12 |
| citation_normalized_percentile |