RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain
Large Language Models (LLMs) increasingly support applications in a wide range of domains, some with potential high societal impact such as biomedicine, yet their reliability in realistic use cases is under-researched. In this work we introduce the Reliability AssesMent for Biomedical LLM Assistants...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2024-03 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Bolton, William James Poyiadzi, Rafael Morrell, Edward R Gabriela van Bergen Gonzalez Bueno Goetz, Lea |
description | Large Language Models (LLMs) increasingly support applications in a wide range of domains, some with potential high societal impact such as biomedicine, yet their reliability in realistic use cases is under-researched. In this work we introduce the Reliability AssesMent for Biomedical LLM Assistants (RAmBLA) framework and evaluate whether four state-of-the-art foundation LLMs can serve as reliable assistants in the biomedical domain. We identify prompt robustness, high recall, and a lack of hallucinations as necessary criteria for this use case. We design shortform tasks and tasks requiring LLM freeform responses mimicking real-world user interactions. We evaluate LLM performance using semantic similarity with a ground truth response, through an evaluator LLM. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2973279159</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2973279159</sourcerecordid><originalsourceid>FETCH-proquest_journals_29732791593</originalsourceid><addsrcrecordid>eNqNys0OwUAUQOGJRELwDjexltSMqtrVXyxq09jLxZTLdIa5U-LtiXgAq7M4X0O0pVLDwWQkZUv0mC9RFMlxIuNYtQUWWTXLsylksPJY6afzVyidh-UDTY2B7AnCWUOhDeGeDIUXuBLyfMOADBkzcUAbGMh-4YxcpY90QAMLVyHZrmiWaFj3fu2I_mq5na8HN-_uteawu7ja28_ayTRRMkmHcar-U28mikOj</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2973279159</pqid></control><display><type>article</type><title>RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain</title><source>Free E- Journals</source><creator>Bolton, William James ; Poyiadzi, Rafael ; Morrell, Edward R ; Gabriela van Bergen Gonzalez Bueno ; Goetz, Lea</creator><creatorcontrib>Bolton, William James ; Poyiadzi, Rafael ; Morrell, Edward R ; Gabriela van Bergen Gonzalez Bueno ; Goetz, Lea</creatorcontrib><description>Large Language Models (LLMs) increasingly support applications in a wide range of domains, some with potential high societal impact such as biomedicine, yet their reliability in realistic use cases is under-researched. In this work we introduce the Reliability AssesMent for Biomedical LLM Assistants (RAmBLA) framework and evaluate whether four state-of-the-art foundation LLMs can serve as reliable assistants in the biomedical domain. We identify prompt robustness, high recall, and a lack of hallucinations as necessary criteria for this use case. We design shortform tasks and tasks requiring LLM freeform responses mimicking real-world user interactions. We evaluate LLM performance using semantic similarity with a ground truth response, through an evaluator LLM.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Large language models ; Performance evaluation ; Reliability analysis</subject><ispartof>arXiv.org, 2024-03</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Bolton, William James</creatorcontrib><creatorcontrib>Poyiadzi, Rafael</creatorcontrib><creatorcontrib>Morrell, Edward R</creatorcontrib><creatorcontrib>Gabriela van Bergen Gonzalez Bueno</creatorcontrib><creatorcontrib>Goetz, Lea</creatorcontrib><title>RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain</title><title>arXiv.org</title><description>Large Language Models (LLMs) increasingly support applications in a wide range of domains, some with potential high societal impact such as biomedicine, yet their reliability in realistic use cases is under-researched. In this work we introduce the Reliability AssesMent for Biomedical LLM Assistants (RAmBLA) framework and evaluate whether four state-of-the-art foundation LLMs can serve as reliable assistants in the biomedical domain. We identify prompt robustness, high recall, and a lack of hallucinations as necessary criteria for this use case. We design shortform tasks and tasks requiring LLM freeform responses mimicking real-world user interactions. We evaluate LLM performance using semantic similarity with a ground truth response, through an evaluator LLM.</description><subject>Large language models</subject><subject>Performance evaluation</subject><subject>Reliability analysis</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNys0OwUAUQOGJRELwDjexltSMqtrVXyxq09jLxZTLdIa5U-LtiXgAq7M4X0O0pVLDwWQkZUv0mC9RFMlxIuNYtQUWWTXLsylksPJY6afzVyidh-UDTY2B7AnCWUOhDeGeDIUXuBLyfMOADBkzcUAbGMh-4YxcpY90QAMLVyHZrmiWaFj3fu2I_mq5na8HN-_uteawu7ja28_ayTRRMkmHcar-U28mikOj</recordid><startdate>20240321</startdate><enddate>20240321</enddate><creator>Bolton, William James</creator><creator>Poyiadzi, Rafael</creator><creator>Morrell, Edward R</creator><creator>Gabriela van Bergen Gonzalez Bueno</creator><creator>Goetz, Lea</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20240321</creationdate><title>RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain</title><author>Bolton, William James ; Poyiadzi, Rafael ; Morrell, Edward R ; Gabriela van Bergen Gonzalez Bueno ; Goetz, Lea</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_29732791593</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Large language models</topic><topic>Performance evaluation</topic><topic>Reliability analysis</topic><toplevel>online_resources</toplevel><creatorcontrib>Bolton, William James</creatorcontrib><creatorcontrib>Poyiadzi, Rafael</creatorcontrib><creatorcontrib>Morrell, Edward R</creatorcontrib><creatorcontrib>Gabriela van Bergen Gonzalez Bueno</creatorcontrib><creatorcontrib>Goetz, Lea</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Bolton, William James</au><au>Poyiadzi, Rafael</au><au>Morrell, Edward R</au><au>Gabriela van Bergen Gonzalez Bueno</au><au>Goetz, Lea</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain</atitle><jtitle>arXiv.org</jtitle><date>2024-03-21</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Large Language Models (LLMs) increasingly support applications in a wide range of domains, some with potential high societal impact such as biomedicine, yet their reliability in realistic use cases is under-researched. In this work we introduce the Reliability AssesMent for Biomedical LLM Assistants (RAmBLA) framework and evaluate whether four state-of-the-art foundation LLMs can serve as reliable assistants in the biomedical domain. We identify prompt robustness, high recall, and a lack of hallucinations as necessary criteria for this use case. We design shortform tasks and tasks requiring LLM freeform responses mimicking real-world user interactions. We evaluate LLM performance using semantic similarity with a ground truth response, through an evaluator LLM.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2024-03 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2973279159 |
source | Free E- Journals |
subjects | Large language models Performance evaluation Reliability analysis |
title | RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T00%3A05%3A28IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=RAmBLA:%20A%20Framework%20for%20Evaluating%20the%20Reliability%20of%20LLMs%20as%20Assistants%20in%20the%20Biomedical%20Domain&rft.jtitle=arXiv.org&rft.au=Bolton,%20William%20James&rft.date=2024-03-21&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2973279159%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2973279159&rft_id=info:pmid/&rfr_iscdi=true |