@inproceedings{yue-etal-2023-automatic, title = "Automatic Evaluation of Attribution by Large Language Models", author = "Yue, Xiang and Wang, Boshi and Chen, Ziru and Zhang, Kai and Su, Yu and Sun, Huan", editor = "Bouamor, Houda and Pino, Juan and Bali, Kalika", booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023", month = dec, year = "2023", address = "Singapore", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2023.findings-emnlp.307", doi = "10.18653/v1/2023.findings-emnlp.307", pages = "4615--4635", abstract = "A recent focus of large language model (LLM) development, as exemplified by generative search engines, is to incorporate external references to generate and support its claims. However, evaluating the attribution, i.e., verifying whether the generated statement is fully supported by the cited reference, remains an open problem. Although human evaluation is common practice, it is costly and time-consuming. In this paper, we investigate automatic evaluation of attribution given by LLMs. We begin by defining different types of attribution errors, and then explore two approaches for automatic evaluation: prompting LLMs and fine-tuning smaller LMs. The fine-tuning data is repurposed from related tasks such as question answering, fact-checking, natural language inference, and summarization. We manually curate a set of test examples covering 12 domains from a generative search engine, New Bing. Our results on this curated test set and simulated examples from existing benchmarks highlight both promising signals and challenges. We hope our problem formulation, testbeds, and findings will help lay the foundation for future studies on this important problem.", }
<?xml version="1.0" encoding="UTF-8"?> <modsCollection xmlns="http://www.loc.gov/mods/v3"> <mods ID="yue-etal-2023-automatic"> <titleInfo> <title>Automatic Evaluation of Attribution by Large Language Models</title> </titleInfo> <name type="personal"> <namePart type="given">Xiang</namePart> <namePart type="family">Yue</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Boshi</namePart> <namePart type="family">Wang</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Ziru</namePart> <namePart type="family">Chen</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Kai</namePart> <namePart type="family">Zhang</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Yu</namePart> <namePart type="family">Su</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Huan</namePart> <namePart type="family">Sun</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <originInfo> <dateIssued>2023-12</dateIssued> </originInfo> <typeOfResource>text</typeOfResource> <relatedItem type="host"> <titleInfo> <title>Findings of the Association for Computational Linguistics: EMNLP 2023</title> </titleInfo> <name type="personal"> <namePart type="given">Houda</namePart> <namePart type="family">Bouamor</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Juan</namePart> <namePart type="family">Pino</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Kalika</namePart> <namePart type="family">Bali</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <originInfo> <publisher>Association for Computational Linguistics</publisher> <place> <placeTerm type="text">Singapore</placeTerm> </place> </originInfo> <genre authority="marcgt">conference publication</genre> </relatedItem> <abstract>A recent focus of large language model (LLM) development, as exemplified by generative search engines, is to incorporate external references to generate and support its claims. However, evaluating the attribution, i.e., verifying whether the generated statement is fully supported by the cited reference, remains an open problem. Although human evaluation is common practice, it is costly and time-consuming. In this paper, we investigate automatic evaluation of attribution given by LLMs. We begin by defining different types of attribution errors, and then explore two approaches for automatic evaluation: prompting LLMs and fine-tuning smaller LMs. The fine-tuning data is repurposed from related tasks such as question answering, fact-checking, natural language inference, and summarization. We manually curate a set of test examples covering 12 domains from a generative search engine, New Bing. Our results on this curated test set and simulated examples from existing benchmarks highlight both promising signals and challenges. We hope our problem formulation, testbeds, and findings will help lay the foundation for future studies on this important problem.</abstract> <identifier type="citekey">yue-etal-2023-automatic</identifier> <identifier type="doi">10.18653/v1/2023.findings-emnlp.307</identifier> <location> <url>https://aclanthology.org/2023.findings-emnlp.307</url> </location> <part> <date>2023-12</date> <extent unit="page"> <start>4615</start> <end>4635</end> </extent> </part> </mods> </modsCollection>
%0 Conference Proceedings %T Automatic Evaluation of Attribution by Large Language Models %A Yue, Xiang %A Wang, Boshi %A Chen, Ziru %A Zhang, Kai %A Su, Yu %A Sun, Huan %Y Bouamor, Houda %Y Pino, Juan %Y Bali, Kalika %S Findings of the Association for Computational Linguistics: EMNLP 2023 %D 2023 %8 December %I Association for Computational Linguistics %C Singapore %F yue-etal-2023-automatic %X A recent focus of large language model (LLM) development, as exemplified by generative search engines, is to incorporate external references to generate and support its claims. However, evaluating the attribution, i.e., verifying whether the generated statement is fully supported by the cited reference, remains an open problem. Although human evaluation is common practice, it is costly and time-consuming. In this paper, we investigate automatic evaluation of attribution given by LLMs. We begin by defining different types of attribution errors, and then explore two approaches for automatic evaluation: prompting LLMs and fine-tuning smaller LMs. The fine-tuning data is repurposed from related tasks such as question answering, fact-checking, natural language inference, and summarization. We manually curate a set of test examples covering 12 domains from a generative search engine, New Bing. Our results on this curated test set and simulated examples from existing benchmarks highlight both promising signals and challenges. We hope our problem formulation, testbeds, and findings will help lay the foundation for future studies on this important problem. %R 10.18653/v1/2023.findings-emnlp.307 %U https://aclanthology.org/2023.findings-emnlp.307 %U https://doi.org/10.18653/v1/2023.findings-emnlp.307 %P 4615-4635
Markdown (Informal)
[Automatic Evaluation of Attribution by Large Language Models](https://aclanthology.org/2023.findings-emnlp.307) (Yue et al., Findings 2023)