Beyond True or False: Retrieval-Augmented Hierarchical Analysis of Nuanced Claims

Claims made by individuals or entities are oftentimes nuanced and cannot be clearly labeled as entirely "true" or false"-as is frequently the case with scientific and political claims. However, a claim (e.g., "vaccine A is better than vaccine B") can be dissected into its integral aspects and sub-aspects (e.g., efficacy, safety, distribution), which are individually easier to validate. This enables a more comprehensive, structured response that provides a well-rounded perspective on a given problem while also allowing the reader to prioritize specific angles of interest within the claim (e.g., safety towards children). Thus, we propose CLAIMSPECT, a retrieval-augmented generation-based framework for automatically constructing a hierarchy of aspects typically considered when addressing a claim and enriching them with corpusspecific perspectives. This structure hierarchically partitions an input corpus to retrieve relevant segments, which assist in discovering new sub-aspects. Moreover, these segments enable the discovery of varying perspectives towards an aspect of the claim (e.g., support, neutral, or oppose) and their respective prevalence (e.g., "how many biomedical papers believe vaccine A is more transportable than B?"). We apply CLAIMSPECT to a wide variety of real-world scientific and political claims featured in our constructed dataset, showcasing its robustness and accuracy in deconstructing a nuanced claim and representing perspectives within a corpus. Through real-world case studies and human evaluation, we validate its effectiveness over multiple baselines. * Equal contribution. Claim: "Vaccine A is better than Vaccine B" Efficacy Distribution Safety Safety for Children Safety for Elderly Affirmative (80% of papers): A has a lower rate of severe allergic reactions in adults than B. Opposition (20% of papers): B has a lower rate of blood clotting incidents in adults than A.