Merging Facts, Crafting Fallacies: Evaluating the Contradictory Nature of Aggregated Factual Claims in Long-Form Generations

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chiang, Cheng-Han, Lee, Hung-yi
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914828871794688
author Chiang, Cheng-Han
Lee, Hung-yi
author_facet Chiang, Cheng-Han
Lee, Hung-yi
contents Long-form generations from large language models (LLMs) contain a mix of factual and non-factual claims, making evaluating factuality difficult. Prior works evaluate the factuality of a long paragraph by decomposing it into multiple facts, verifying those facts independently, and aggregating the results. Such methods assume that combining factual claims forms a factual paragraph. The above assumption can be violated: we show that strong open-source models like Llama-chat can generate paragraphs that contain verifiable facts, but the facts are combined into a non-factual paragraph due to entity ambiguity. We further reveal that existing factuality metrics, including FActScore and citation recall, cannot properly evaluate these non-factual paragraphs and overestimate their factuality. To address this, we introduce an enhanced metric, D-FActScore, specifically designed for content with ambiguous entities. We evaluate the D-FActScores of people biographies generated by retrieval-augmented LLMs. We show that D-FActScore can better assess the factuality of paragraphs with entity ambiguity than FActScore. We also find that four widely used open-source LLMs tend to mix information of distinct entities to form non-factual paragraphs, making their D-FActScore much lower than FActScore by over 10%.
format Preprint
id arxiv_https___arxiv_org_abs_2402_05629
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Merging Facts, Crafting Fallacies: Evaluating the Contradictory Nature of Aggregated Factual Claims in Long-Form Generations
Chiang, Cheng-Han
Lee, Hung-yi
Computation and Language
Long-form generations from large language models (LLMs) contain a mix of factual and non-factual claims, making evaluating factuality difficult. Prior works evaluate the factuality of a long paragraph by decomposing it into multiple facts, verifying those facts independently, and aggregating the results. Such methods assume that combining factual claims forms a factual paragraph. The above assumption can be violated: we show that strong open-source models like Llama-chat can generate paragraphs that contain verifiable facts, but the facts are combined into a non-factual paragraph due to entity ambiguity. We further reveal that existing factuality metrics, including FActScore and citation recall, cannot properly evaluate these non-factual paragraphs and overestimate their factuality. To address this, we introduce an enhanced metric, D-FActScore, specifically designed for content with ambiguous entities. We evaluate the D-FActScores of people biographies generated by retrieval-augmented LLMs. We show that D-FActScore can better assess the factuality of paragraphs with entity ambiguity than FActScore. We also find that four widely used open-source LLMs tend to mix information of distinct entities to form non-factual paragraphs, making their D-FActScore much lower than FActScore by over 10%.
title Merging Facts, Crafting Fallacies: Evaluating the Contradictory Nature of Aggregated Factual Claims in Long-Form Generations
topic Computation and Language
url https://arxiv.org/abs/2402.05629