LaFFi: Leveraging Hybrid Natural Language Feedback for Fine-tuning Language Models Article Swipe
Qianxi Li
,
Yingyue Cao
,
Jikun Kang
,
Tianpei Yang
,
Xi Chen
,
Jun Jin
,
Matthew E. Taylor
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2401.00907
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2401.00907
Fine-tuning Large Language Models (LLMs) adapts a trained model to specific downstream tasks, significantly improving task-specific performance. Supervised Fine-Tuning (SFT) is a common approach, where an LLM is trained to produce desired answers. However, LLMs trained with SFT sometimes make simple mistakes and result in hallucinations on reasoning tasks such as question-answering. Without external feedback, it is difficult for SFT to learn a good mapping between the question and the desired answer, especially with a small dataset. This paper introduces an alternative to SFT called Natural Language Feedback for Finetuning LLMs (LaFFi). LaFFi has LLMs directly predict the feedback they will receive from an annotator. We find that requiring such reflection can significantly improve the accuracy in in-domain question-answering tasks, providing a promising direction for the application of natural language feedback in the realm of SFT LLMs. Additional ablation studies show that the portion of human-annotated data in the annotated datasets affects the fine-tuning performance.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2401.00907
- https://arxiv.org/pdf/2401.00907
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4390573228
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4390573228Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2401.00907Digital Object Identifier
- Title
-
LaFFi: Leveraging Hybrid Natural Language Feedback for Fine-tuning Language ModelsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-12-31Full publication date if available
- Authors
-
Qianxi Li, Yingyue Cao, Jikun Kang, Tianpei Yang, Xi Chen, Jun Jin, Matthew E. TaylorList of authors in order
- Landing page
-
https://arxiv.org/abs/2401.00907Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2401.00907Direct 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/2401.00907Direct OA link when available
- Concepts
-
Computer science, Fine-tuning, Realm, Natural language, Natural (archaeology), Language model, Natural language understanding, Task (project management), Artificial intelligence, Natural language processing, Engineering, Political science, Systems engineering, History, Law, Physics, Archaeology, Quantum mechanicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4390573228 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2401.00907 |
| ids.doi | https://doi.org/10.48550/arxiv.2401.00907 |
| ids.openalex | https://openalex.org/W4390573228 |
| fwci | |
| type | preprint |
| title | LaFFi: Leveraging Hybrid Natural Language Feedback for Fine-tuning Language Models |
| 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 | 0.9998000264167786 |
| 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 | 0.9973999857902527 |
| 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/T11714 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9787999987602234 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Multimodal Machine Learning Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7516388893127441 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C157524613 |
| concepts[1].level | 2 |
| concepts[1].score | 0.5379059910774231 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q2828883 |
| concepts[1].display_name | Fine-tuning |
| concepts[2].id | https://openalex.org/C2778757428 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5300939679145813 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1250464 |
| concepts[2].display_name | Realm |
| concepts[3].id | https://openalex.org/C195324797 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5180930495262146 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q33742 |
| concepts[3].display_name | Natural language |
| concepts[4].id | https://openalex.org/C2776608160 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5063101053237915 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q4785462 |
| concepts[4].display_name | Natural (archaeology) |
| concepts[5].id | https://openalex.org/C137293760 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4877832531929016 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q3621696 |
| concepts[5].display_name | Language model |
| concepts[6].id | https://openalex.org/C2779439875 |
| concepts[6].level | 3 |
| concepts[6].score | 0.4730973541736603 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q1078276 |
| concepts[6].display_name | Natural language understanding |
| concepts[7].id | https://openalex.org/C2780451532 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4555976092815399 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[7].display_name | Task (project management) |
| concepts[8].id | https://openalex.org/C154945302 |
| concepts[8].level | 1 |
| concepts[8].score | 0.45478805899620056 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[8].display_name | Artificial intelligence |
| concepts[9].id | https://openalex.org/C204321447 |
| concepts[9].level | 1 |
| concepts[9].score | 0.3429694175720215 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[9].display_name | Natural language processing |
| concepts[10].id | https://openalex.org/C127413603 |
| concepts[10].level | 0 |
| concepts[10].score | 0.06598910689353943 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[10].display_name | Engineering |
| concepts[11].id | https://openalex.org/C17744445 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q36442 |
| concepts[11].display_name | Political science |
| concepts[12].id | https://openalex.org/C201995342 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q682496 |
| concepts[12].display_name | Systems engineering |
| concepts[13].id | https://openalex.org/C95457728 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q309 |
| concepts[13].display_name | History |
| concepts[14].id | https://openalex.org/C199539241 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q7748 |
| concepts[14].display_name | Law |
| concepts[15].id | https://openalex.org/C121332964 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[15].display_name | Physics |
| concepts[16].id | https://openalex.org/C166957645 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q23498 |
| concepts[16].display_name | Archaeology |
| concepts[17].id | https://openalex.org/C62520636 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[17].display_name | Quantum mechanics |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7516388893127441 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/fine-tuning |
| keywords[1].score | 0.5379059910774231 |
| keywords[1].display_name | Fine-tuning |
| keywords[2].id | https://openalex.org/keywords/realm |
| keywords[2].score | 0.5300939679145813 |
| keywords[2].display_name | Realm |
| keywords[3].id | https://openalex.org/keywords/natural-language |
| keywords[3].score | 0.5180930495262146 |
| keywords[3].display_name | Natural language |
| keywords[4].id | https://openalex.org/keywords/natural |
| keywords[4].score | 0.5063101053237915 |
| keywords[4].display_name | Natural (archaeology) |
| keywords[5].id | https://openalex.org/keywords/language-model |
| keywords[5].score | 0.4877832531929016 |
| keywords[5].display_name | Language model |
| keywords[6].id | https://openalex.org/keywords/natural-language-understanding |
| keywords[6].score | 0.4730973541736603 |
| keywords[6].display_name | Natural language understanding |
| keywords[7].id | https://openalex.org/keywords/task |
| keywords[7].score | 0.4555976092815399 |
| keywords[7].display_name | Task (project management) |
| keywords[8].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[8].score | 0.45478805899620056 |
| keywords[8].display_name | Artificial intelligence |
| keywords[9].id | https://openalex.org/keywords/natural-language-processing |
| keywords[9].score | 0.3429694175720215 |
| keywords[9].display_name | Natural language processing |
| keywords[10].id | https://openalex.org/keywords/engineering |
| keywords[10].score | 0.06598910689353943 |
| keywords[10].display_name | Engineering |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2401.00907 |
| 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/2401.00907 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| 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/2401.00907 |
| locations[1].id | doi:10.48550/arxiv.2401.00907 |
| 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 | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| 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.2401.00907 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5004870418 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Qianxi Li |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Li, Qianxi |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5109663270 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Yingyue Cao |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Cao, Yingyue |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5021430632 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Jikun Kang |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Kang, Jikun |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5101619771 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-5497-7146 |
| authorships[3].author.display_name | Tianpei Yang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Yang, Tianpei |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5100330018 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-0970-8876 |
| authorships[4].author.display_name | Xi Chen |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Chen, Xi |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5112668737 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-4413-8565 |
| authorships[5].author.display_name | Jun Jin |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Jin, Jun |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5070914351 |
| authorships[6].author.orcid | https://orcid.org/0000-0001-8946-0211 |
| authorships[6].author.display_name | Matthew E. Taylor |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Taylor, Matthew E. |
| authorships[6].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/2401.00907 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | LaFFi: Leveraging Hybrid Natural Language Feedback for Fine-tuning Language Models |
| 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 | 0.9998000264167786 |
| 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/W3023285645, https://openalex.org/W3037551068, https://openalex.org/W3023594376, https://openalex.org/W4287802662, https://openalex.org/W2367925007, https://openalex.org/W4288263119, https://openalex.org/W3015724364, https://openalex.org/W2967994095, https://openalex.org/W4285240985, https://openalex.org/W2900126711 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2401.00907 |
| 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/2401.00907 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| 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/2401.00907 |
| primary_location.id | pmh:oai:arXiv.org:2401.00907 |
| 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/2401.00907 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| 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/2401.00907 |
| publication_date | 2023-12-31 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 6, 21, 62, 74, 121 |
| abstract_inverted_index.We | 105 |
| abstract_inverted_index.an | 25, 80, 103 |
| abstract_inverted_index.as | 50 |
| abstract_inverted_index.in | 44, 116, 131, 147 |
| abstract_inverted_index.is | 20, 27, 56 |
| abstract_inverted_index.it | 55 |
| abstract_inverted_index.of | 127, 134, 144 |
| abstract_inverted_index.on | 46 |
| abstract_inverted_index.to | 9, 29, 60, 82 |
| abstract_inverted_index.LLM | 26 |
| abstract_inverted_index.SFT | 37, 59, 83, 135 |
| abstract_inverted_index.and | 42, 68 |
| abstract_inverted_index.can | 111 |
| abstract_inverted_index.for | 58, 88, 124 |
| abstract_inverted_index.has | 93 |
| abstract_inverted_index.the | 66, 69, 97, 114, 125, 132, 142, 148, 152 |
| abstract_inverted_index.LLMs | 34, 90, 94 |
| abstract_inverted_index.This | 77 |
| abstract_inverted_index.data | 146 |
| abstract_inverted_index.find | 106 |
| abstract_inverted_index.from | 102 |
| abstract_inverted_index.good | 63 |
| abstract_inverted_index.make | 39 |
| abstract_inverted_index.show | 140 |
| abstract_inverted_index.such | 49, 109 |
| abstract_inverted_index.that | 107, 141 |
| abstract_inverted_index.they | 99 |
| abstract_inverted_index.will | 100 |
| abstract_inverted_index.with | 36, 73 |
| abstract_inverted_index.(SFT) | 19 |
| abstract_inverted_index.LLMs. | 136 |
| abstract_inverted_index.LaFFi | 92 |
| abstract_inverted_index.Large | 1 |
| abstract_inverted_index.learn | 61 |
| abstract_inverted_index.model | 8 |
| abstract_inverted_index.paper | 78 |
| abstract_inverted_index.realm | 133 |
| abstract_inverted_index.small | 75 |
| abstract_inverted_index.tasks | 48 |
| abstract_inverted_index.where | 24 |
| abstract_inverted_index.(LLMs) | 4 |
| abstract_inverted_index.Models | 3 |
| abstract_inverted_index.adapts | 5 |
| abstract_inverted_index.called | 84 |
| abstract_inverted_index.common | 22 |
| abstract_inverted_index.result | 43 |
| abstract_inverted_index.simple | 40 |
| abstract_inverted_index.tasks, | 12, 119 |
| abstract_inverted_index.Natural | 85 |
| abstract_inverted_index.Without | 52 |
| abstract_inverted_index.affects | 151 |
| abstract_inverted_index.answer, | 71 |
| abstract_inverted_index.between | 65 |
| abstract_inverted_index.desired | 31, 70 |
| abstract_inverted_index.improve | 113 |
| abstract_inverted_index.mapping | 64 |
| abstract_inverted_index.natural | 128 |
| abstract_inverted_index.portion | 143 |
| abstract_inverted_index.predict | 96 |
| abstract_inverted_index.produce | 30 |
| abstract_inverted_index.receive | 101 |
| abstract_inverted_index.studies | 139 |
| abstract_inverted_index.trained | 7, 28, 35 |
| abstract_inverted_index.(LaFFi). | 91 |
| abstract_inverted_index.Feedback | 87 |
| abstract_inverted_index.However, | 33 |
| abstract_inverted_index.Language | 2, 86 |
| abstract_inverted_index.ablation | 138 |
| abstract_inverted_index.accuracy | 115 |
| abstract_inverted_index.answers. | 32 |
| abstract_inverted_index.dataset. | 76 |
| abstract_inverted_index.datasets | 150 |
| abstract_inverted_index.directly | 95 |
| abstract_inverted_index.external | 53 |
| abstract_inverted_index.feedback | 98, 130 |
| abstract_inverted_index.language | 129 |
| abstract_inverted_index.mistakes | 41 |
| abstract_inverted_index.question | 67 |
| abstract_inverted_index.specific | 10 |
| abstract_inverted_index.annotated | 149 |
| abstract_inverted_index.approach, | 23 |
| abstract_inverted_index.difficult | 57 |
| abstract_inverted_index.direction | 123 |
| abstract_inverted_index.feedback, | 54 |
| abstract_inverted_index.improving | 14 |
| abstract_inverted_index.in-domain | 117 |
| abstract_inverted_index.promising | 122 |
| abstract_inverted_index.providing | 120 |
| abstract_inverted_index.reasoning | 47 |
| abstract_inverted_index.requiring | 108 |
| abstract_inverted_index.sometimes | 38 |
| abstract_inverted_index.Additional | 137 |
| abstract_inverted_index.Finetuning | 89 |
| abstract_inverted_index.Supervised | 17 |
| abstract_inverted_index.annotator. | 104 |
| abstract_inverted_index.downstream | 11 |
| abstract_inverted_index.especially | 72 |
| abstract_inverted_index.introduces | 79 |
| abstract_inverted_index.reflection | 110 |
| abstract_inverted_index.Fine-Tuning | 18 |
| abstract_inverted_index.Fine-tuning | 0 |
| abstract_inverted_index.alternative | 81 |
| abstract_inverted_index.application | 126 |
| abstract_inverted_index.fine-tuning | 153 |
| abstract_inverted_index.performance. | 16, 154 |
| abstract_inverted_index.significantly | 13, 112 |
| abstract_inverted_index.task-specific | 15 |
| abstract_inverted_index.hallucinations | 45 |
| abstract_inverted_index.human-annotated | 145 |
| abstract_inverted_index.question-answering | 118 |
| abstract_inverted_index.question-answering. | 51 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.8199999928474426 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile |