Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data Article Swipe
Xuhai Xu
,
Bingsheng Yao
,
Yuanzhe Dong
,
Saadia Gabriel
,
Hong Yu
,
James Hendler
,
Marzyeh Ghassemi
,
Anind K. Dey
,
Dakuo Wang
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2307.14385
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2307.14385
Advances in large language models (LLMs) have empowered a variety of applications. However, there is still a significant gap in research when it comes to understanding and enhancing the capabilities of LLMs in the field of mental health. In this work, we present a comprehensive evaluation of multiple LLMs on various mental health prediction tasks via online text data, including Alpaca, Alpaca-LoRA, FLAN-T5, GPT-3.5, and GPT-4. We conduct a broad range of experiments, covering zero-shot prompting, few-shot prompting, and instruction fine-tuning. The results indicate a promising yet limited performance of LLMs with zero-shot and few-shot prompt designs for mental health tasks. More importantly, our experiments show that instruction finetuning can significantly boost the performance of LLMs for all tasks simultaneously. Our best-finetuned models, Mental-Alpaca and Mental-FLAN-T5, outperform the best prompt design of GPT-3.5 (25 and 15 times bigger) by 10.9% on balanced accuracy and the best of GPT-4 (250 and 150 times bigger) by 4.8%. They further perform on par with the state-of-the-art task-specific language model. We also conduct an exploratory case study on LLMs' capability on mental health reasoning tasks, illustrating the promising capability of certain models such as GPT-4. We summarize our findings into a set of action guidelines for potential methods to enhance LLMs' capability for mental health tasks. Meanwhile, we also emphasize the important limitations before achieving deployability in real-world mental health settings, such as known racial and gender bias. We highlight the important ethical risks accompanying this line of research.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2307.14385
- https://arxiv.org/pdf/2307.14385
- OA Status
- green
- Cited By
- 59
- References
- 122
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4385373745
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4385373745Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2307.14385Digital Object Identifier
- Title
-
Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text DataWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-07-26Full publication date if available
- Authors
-
Xuhai Xu, Bingsheng Yao, Yuanzhe Dong, Saadia Gabriel, Hong Yu, James Hendler, Marzyeh Ghassemi, Anind K. Dey, Dakuo WangList of authors in order
- Landing page
-
https://arxiv.org/abs/2307.14385Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2307.14385Direct 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/2307.14385Direct OA link when available
- Concepts
-
Mental health, Set (abstract data type), Computer science, Task (project management), Variety (cybernetics), Artificial intelligence, Psychology, Psychiatry, Engineering, Systems engineering, Programming languageTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
59Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 29, 2024: 27, 2023: 3Per-year citation counts (last 5 years)
- References (count)
-
122Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4385373745 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2307.14385 |
| ids.doi | https://doi.org/10.48550/arxiv.2307.14385 |
| ids.openalex | https://openalex.org/W4385373745 |
| fwci | 30.18361527 |
| type | preprint |
| title | Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12488 |
| topics[0].field.id | https://openalex.org/fields/32 |
| topics[0].field.display_name | Psychology |
| topics[0].score | 0.9936000108718872 |
| topics[0].domain.id | https://openalex.org/domains/2 |
| topics[0].domain.display_name | Social Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/3207 |
| topics[0].subfield.display_name | Social Psychology |
| topics[0].display_name | Mental Health via Writing |
| topics[1].id | https://openalex.org/T13702 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9487000107765198 |
| 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 | Machine Learning in Healthcare |
| topics[2].id | https://openalex.org/T10028 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9326000213623047 |
| 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 | Topic Modeling |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C134362201 |
| concepts[0].level | 2 |
| concepts[0].score | 0.6714977025985718 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q317309 |
| concepts[0].display_name | Mental health |
| concepts[1].id | https://openalex.org/C177264268 |
| concepts[1].level | 2 |
| concepts[1].score | 0.5975016951560974 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1514741 |
| concepts[1].display_name | Set (abstract data type) |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.5678638219833374 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C2780451532 |
| concepts[3].level | 2 |
| concepts[3].score | 0.49703481793403625 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[3].display_name | Task (project management) |
| concepts[4].id | https://openalex.org/C136197465 |
| concepts[4].level | 2 |
| concepts[4].score | 0.43695753812789917 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q1729295 |
| concepts[4].display_name | Variety (cybernetics) |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.300961434841156 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C15744967 |
| concepts[6].level | 0 |
| concepts[6].score | 0.28460514545440674 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[6].display_name | Psychology |
| concepts[7].id | https://openalex.org/C118552586 |
| concepts[7].level | 1 |
| concepts[7].score | 0.14710181951522827 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q7867 |
| concepts[7].display_name | Psychiatry |
| concepts[8].id | https://openalex.org/C127413603 |
| concepts[8].level | 0 |
| concepts[8].score | 0.09671485424041748 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[8].display_name | Engineering |
| concepts[9].id | https://openalex.org/C201995342 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q682496 |
| concepts[9].display_name | Systems engineering |
| concepts[10].id | https://openalex.org/C199360897 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[10].display_name | Programming language |
| keywords[0].id | https://openalex.org/keywords/mental-health |
| keywords[0].score | 0.6714977025985718 |
| keywords[0].display_name | Mental health |
| keywords[1].id | https://openalex.org/keywords/set |
| keywords[1].score | 0.5975016951560974 |
| keywords[1].display_name | Set (abstract data type) |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.5678638219833374 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/task |
| keywords[3].score | 0.49703481793403625 |
| keywords[3].display_name | Task (project management) |
| keywords[4].id | https://openalex.org/keywords/variety |
| keywords[4].score | 0.43695753812789917 |
| keywords[4].display_name | Variety (cybernetics) |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.300961434841156 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/psychology |
| keywords[6].score | 0.28460514545440674 |
| keywords[6].display_name | Psychology |
| keywords[7].id | https://openalex.org/keywords/psychiatry |
| keywords[7].score | 0.14710181951522827 |
| keywords[7].display_name | Psychiatry |
| keywords[8].id | https://openalex.org/keywords/engineering |
| keywords[8].score | 0.09671485424041748 |
| keywords[8].display_name | Engineering |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2307.14385 |
| 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/2307.14385 |
| 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/2307.14385 |
| locations[1].id | doi:10.48550/arxiv.2307.14385 |
| 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-journal |
| 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.2307.14385 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5066796307 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-5930-3899 |
| authorships[0].author.display_name | Xuhai Xu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Xuhai Xu |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5033744502 |
| authorships[1].author.orcid | https://orcid.org/0009-0004-8329-4610 |
| authorships[1].author.display_name | Bingsheng Yao |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Bingsheng Yao |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5023221439 |
| authorships[2].author.orcid | https://orcid.org/0009-0006-2013-1157 |
| authorships[2].author.display_name | Yuanzhe Dong |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Yuanzhe Dong |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5015792268 |
| authorships[3].author.orcid | https://orcid.org/0009-0001-9353-951X |
| authorships[3].author.display_name | Saadia Gabriel |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Saadia Gabriel |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5017601806 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-9263-5035 |
| authorships[4].author.display_name | Hong Yu |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Hong Yu |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5010414972 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-3056-1960 |
| authorships[5].author.display_name | James Hendler |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | James Hendler |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5070063054 |
| authorships[6].author.orcid | https://orcid.org/0000-0001-6349-7251 |
| authorships[6].author.display_name | Marzyeh Ghassemi |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Marzyeh Ghassemi |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5032134965 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-3004-0770 |
| authorships[7].author.display_name | Anind K. Dey |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Anind K. Dey |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5062817658 |
| authorships[8].author.orcid | https://orcid.org/0000-0001-9371-9441 |
| authorships[8].author.display_name | Dakuo Wang |
| authorships[8].author_position | last |
| authorships[8].raw_author_name | Dakuo Wang |
| authorships[8].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/2307.14385 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T12488 |
| primary_topic.field.id | https://openalex.org/fields/32 |
| primary_topic.field.display_name | Psychology |
| primary_topic.score | 0.9936000108718872 |
| primary_topic.domain.id | https://openalex.org/domains/2 |
| primary_topic.domain.display_name | Social Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/3207 |
| primary_topic.subfield.display_name | Social Psychology |
| primary_topic.display_name | Mental Health via Writing |
| related_works | https://openalex.org/W2032233321, https://openalex.org/W3121970507, https://openalex.org/W2110028391, https://openalex.org/W54497855, https://openalex.org/W217960748, https://openalex.org/W3125814499, https://openalex.org/W2090827041, https://openalex.org/W2094012830, https://openalex.org/W187246281, https://openalex.org/W4386392971 |
| cited_by_count | 59 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 29 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 27 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 3 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2307.14385 |
| 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/2307.14385 |
| 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/2307.14385 |
| primary_location.id | pmh:oai:arXiv.org:2307.14385 |
| 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/2307.14385 |
| 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/2307.14385 |
| publication_date | 2023-07-26 |
| publication_year | 2023 |
| referenced_works | https://openalex.org/W3184144760, https://openalex.org/W4319837253, https://openalex.org/W3036236864, https://openalex.org/W4307079201, https://openalex.org/W2109664771, https://openalex.org/W4285209895, https://openalex.org/W2795743556, https://openalex.org/W4385573087, https://openalex.org/W2106686523, https://openalex.org/W4295067194, https://openalex.org/W2537052583, https://openalex.org/W2182854643, https://openalex.org/W2972890723, https://openalex.org/W2889391310, https://openalex.org/W2252031683, https://openalex.org/W2897583329, https://openalex.org/W2087564028, https://openalex.org/W4388092464, https://openalex.org/W2900152803, https://openalex.org/W4389523706, https://openalex.org/W3168867926, https://openalex.org/W3031532441, https://openalex.org/W2741216199, https://openalex.org/W4360765018, https://openalex.org/W4286987939, https://openalex.org/W2739819123, https://openalex.org/W2739681832, https://openalex.org/W4285211483, https://openalex.org/W2888487925, https://openalex.org/W4377009978, https://openalex.org/W1968199606, https://openalex.org/W4224308101, https://openalex.org/W4320854854, https://openalex.org/W3162081707, https://openalex.org/W4385442373, https://openalex.org/W2157035150, https://openalex.org/W4389523957, https://openalex.org/W3087893815, https://openalex.org/W3192247156, https://openalex.org/W4220883868, https://openalex.org/W2252128283, https://openalex.org/W4379769651, https://openalex.org/W3013908145, https://openalex.org/W4322708560, https://openalex.org/W2094553285, https://openalex.org/W2998535576, https://openalex.org/W4360836968, https://openalex.org/W2898410082, https://openalex.org/W4367623495, https://openalex.org/W2613843855, https://openalex.org/W3135440523, https://openalex.org/W2911378332, https://openalex.org/W4221143046, https://openalex.org/W4386415037, https://openalex.org/W4361230825, https://openalex.org/W2755222014, https://openalex.org/W4386249236, https://openalex.org/W4281483047, https://openalex.org/W4281557260, https://openalex.org/W2405042511, https://openalex.org/W4288089799, https://openalex.org/W2914514892, https://openalex.org/W2748635631, https://openalex.org/W4321524280, https://openalex.org/W4307309259, https://openalex.org/W3209409148, https://openalex.org/W3103163889, https://openalex.org/W3199761064, https://openalex.org/W2489334776, https://openalex.org/W4317757464, https://openalex.org/W4360891289, https://openalex.org/W2927148761, https://openalex.org/W4384918448, https://openalex.org/W4292779060, https://openalex.org/W2965373594, https://openalex.org/W2901416577, https://openalex.org/W4322718191, https://openalex.org/W2402700, https://openalex.org/W4296151718, https://openalex.org/W4210736086, https://openalex.org/W4226157316, https://openalex.org/W4311026115, https://openalex.org/W4363671699, https://openalex.org/W2890787190, https://openalex.org/W3178912721, https://openalex.org/W4389523718, https://openalex.org/W2277876591, https://openalex.org/W2987392802, https://openalex.org/W2898390306, https://openalex.org/W4376133361, https://openalex.org/W201361503, https://openalex.org/W3007384022, https://openalex.org/W2076151421, https://openalex.org/W4312811953, https://openalex.org/W3004493409, https://openalex.org/W2160367613, https://openalex.org/W2252191003, https://openalex.org/W4297328641, https://openalex.org/W2000594564, https://openalex.org/W4323570543, https://openalex.org/W4384520874, https://openalex.org/W2104925568, https://openalex.org/W4378498682, https://openalex.org/W4381930847, https://openalex.org/W2985355520, https://openalex.org/W4386352630, https://openalex.org/W2937284856, https://openalex.org/W3202915159, https://openalex.org/W4297630849, https://openalex.org/W4366591012, https://openalex.org/W4387075354, https://openalex.org/W2896457183, https://openalex.org/W1537829113, https://openalex.org/W3148026034, https://openalex.org/W4224326626, https://openalex.org/W2977128309, https://openalex.org/W78677904, https://openalex.org/W3154272574, https://openalex.org/W4297686483, https://openalex.org/W2597891111, https://openalex.org/W4308610353, https://openalex.org/W2101807845 |
| referenced_works_count | 122 |
| abstract_inverted_index.a | 8, 16, 43, 68, 84, 196 |
| abstract_inverted_index.15 | 135 |
| abstract_inverted_index.In | 38 |
| abstract_inverted_index.We | 66, 166, 191, 234 |
| abstract_inverted_index.an | 169 |
| abstract_inverted_index.as | 189, 228 |
| abstract_inverted_index.by | 138, 153 |
| abstract_inverted_index.in | 1, 19, 32, 222 |
| abstract_inverted_index.is | 14 |
| abstract_inverted_index.it | 22 |
| abstract_inverted_index.of | 10, 30, 35, 46, 71, 89, 114, 131, 146, 185, 198, 243 |
| abstract_inverted_index.on | 49, 140, 158, 173, 176 |
| abstract_inverted_index.to | 24, 204 |
| abstract_inverted_index.we | 41, 213 |
| abstract_inverted_index.(25 | 133 |
| abstract_inverted_index.150 | 150 |
| abstract_inverted_index.Our | 120 |
| abstract_inverted_index.The | 81 |
| abstract_inverted_index.all | 117 |
| abstract_inverted_index.and | 26, 64, 78, 93, 124, 134, 143, 149, 231 |
| abstract_inverted_index.can | 109 |
| abstract_inverted_index.for | 97, 116, 201, 208 |
| abstract_inverted_index.gap | 18 |
| abstract_inverted_index.our | 103, 193 |
| abstract_inverted_index.par | 159 |
| abstract_inverted_index.set | 197 |
| abstract_inverted_index.the | 28, 33, 112, 127, 144, 161, 182, 216, 236 |
| abstract_inverted_index.via | 55 |
| abstract_inverted_index.yet | 86 |
| abstract_inverted_index.(250 | 148 |
| abstract_inverted_index.LLMs | 31, 48, 90, 115 |
| abstract_inverted_index.More | 101 |
| abstract_inverted_index.They | 155 |
| abstract_inverted_index.also | 167, 214 |
| abstract_inverted_index.best | 128, 145 |
| abstract_inverted_index.case | 171 |
| abstract_inverted_index.have | 6 |
| abstract_inverted_index.into | 195 |
| abstract_inverted_index.line | 242 |
| abstract_inverted_index.show | 105 |
| abstract_inverted_index.such | 188, 227 |
| abstract_inverted_index.text | 57 |
| abstract_inverted_index.that | 106 |
| abstract_inverted_index.this | 39, 241 |
| abstract_inverted_index.when | 21 |
| abstract_inverted_index.with | 91, 160 |
| abstract_inverted_index.10.9% | 139 |
| abstract_inverted_index.4.8%. | 154 |
| abstract_inverted_index.GPT-4 | 147 |
| abstract_inverted_index.LLMs' | 174, 206 |
| abstract_inverted_index.bias. | 233 |
| abstract_inverted_index.boost | 111 |
| abstract_inverted_index.broad | 69 |
| abstract_inverted_index.comes | 23 |
| abstract_inverted_index.data, | 58 |
| abstract_inverted_index.field | 34 |
| abstract_inverted_index.known | 229 |
| abstract_inverted_index.large | 2 |
| abstract_inverted_index.range | 70 |
| abstract_inverted_index.risks | 239 |
| abstract_inverted_index.still | 15 |
| abstract_inverted_index.study | 172 |
| abstract_inverted_index.tasks | 54, 118 |
| abstract_inverted_index.there | 13 |
| abstract_inverted_index.times | 136, 151 |
| abstract_inverted_index.work, | 40 |
| abstract_inverted_index.(LLMs) | 5 |
| abstract_inverted_index.GPT-4. | 65, 190 |
| abstract_inverted_index.action | 199 |
| abstract_inverted_index.before | 219 |
| abstract_inverted_index.design | 130 |
| abstract_inverted_index.gender | 232 |
| abstract_inverted_index.health | 52, 99, 178, 210, 225 |
| abstract_inverted_index.mental | 36, 51, 98, 177, 209, 224 |
| abstract_inverted_index.model. | 165 |
| abstract_inverted_index.models | 4, 187 |
| abstract_inverted_index.online | 56 |
| abstract_inverted_index.prompt | 95, 129 |
| abstract_inverted_index.racial | 230 |
| abstract_inverted_index.tasks, | 180 |
| abstract_inverted_index.tasks. | 100, 211 |
| abstract_inverted_index.Alpaca, | 60 |
| abstract_inverted_index.GPT-3.5 | 132 |
| abstract_inverted_index.bigger) | 137, 152 |
| abstract_inverted_index.certain | 186 |
| abstract_inverted_index.conduct | 67, 168 |
| abstract_inverted_index.designs | 96 |
| abstract_inverted_index.enhance | 205 |
| abstract_inverted_index.ethical | 238 |
| abstract_inverted_index.further | 156 |
| abstract_inverted_index.health. | 37 |
| abstract_inverted_index.limited | 87 |
| abstract_inverted_index.methods | 203 |
| abstract_inverted_index.models, | 122 |
| abstract_inverted_index.perform | 157 |
| abstract_inverted_index.present | 42 |
| abstract_inverted_index.results | 82 |
| abstract_inverted_index.variety | 9 |
| abstract_inverted_index.various | 50 |
| abstract_inverted_index.Advances | 0 |
| abstract_inverted_index.FLAN-T5, | 62 |
| abstract_inverted_index.GPT-3.5, | 63 |
| abstract_inverted_index.However, | 12 |
| abstract_inverted_index.accuracy | 142 |
| abstract_inverted_index.balanced | 141 |
| abstract_inverted_index.covering | 73 |
| abstract_inverted_index.few-shot | 76, 94 |
| abstract_inverted_index.findings | 194 |
| abstract_inverted_index.indicate | 83 |
| abstract_inverted_index.language | 3, 164 |
| abstract_inverted_index.multiple | 47 |
| abstract_inverted_index.research | 20 |
| abstract_inverted_index.achieving | 220 |
| abstract_inverted_index.emphasize | 215 |
| abstract_inverted_index.empowered | 7 |
| abstract_inverted_index.enhancing | 27 |
| abstract_inverted_index.highlight | 235 |
| abstract_inverted_index.important | 217, 237 |
| abstract_inverted_index.including | 59 |
| abstract_inverted_index.potential | 202 |
| abstract_inverted_index.promising | 85, 183 |
| abstract_inverted_index.reasoning | 179 |
| abstract_inverted_index.research. | 244 |
| abstract_inverted_index.settings, | 226 |
| abstract_inverted_index.summarize | 192 |
| abstract_inverted_index.zero-shot | 74, 92 |
| abstract_inverted_index.Meanwhile, | 212 |
| abstract_inverted_index.capability | 175, 184, 207 |
| abstract_inverted_index.evaluation | 45 |
| abstract_inverted_index.finetuning | 108 |
| abstract_inverted_index.guidelines | 200 |
| abstract_inverted_index.outperform | 126 |
| abstract_inverted_index.prediction | 53 |
| abstract_inverted_index.prompting, | 75, 77 |
| abstract_inverted_index.real-world | 223 |
| abstract_inverted_index.experiments | 104 |
| abstract_inverted_index.exploratory | 170 |
| abstract_inverted_index.instruction | 79, 107 |
| abstract_inverted_index.limitations | 218 |
| abstract_inverted_index.performance | 88, 113 |
| abstract_inverted_index.significant | 17 |
| abstract_inverted_index.Alpaca-LoRA, | 61 |
| abstract_inverted_index.accompanying | 240 |
| abstract_inverted_index.capabilities | 29 |
| abstract_inverted_index.experiments, | 72 |
| abstract_inverted_index.fine-tuning. | 80 |
| abstract_inverted_index.illustrating | 181 |
| abstract_inverted_index.importantly, | 102 |
| abstract_inverted_index.Mental-Alpaca | 123 |
| abstract_inverted_index.applications. | 11 |
| abstract_inverted_index.comprehensive | 44 |
| abstract_inverted_index.deployability | 221 |
| abstract_inverted_index.significantly | 110 |
| abstract_inverted_index.task-specific | 163 |
| abstract_inverted_index.understanding | 25 |
| abstract_inverted_index.best-finetuned | 121 |
| abstract_inverted_index.Mental-FLAN-T5, | 125 |
| abstract_inverted_index.simultaneously. | 119 |
| abstract_inverted_index.state-of-the-art | 162 |
| cited_by_percentile_year.max | 100 |
| cited_by_percentile_year.min | 96 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 9 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.6700000166893005 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile.value | 0.99775469 |
| citation_normalized_percentile.is_in_top_1_percent | True |
| citation_normalized_percentile.is_in_top_10_percent | True |