Pith. sign in

REVIEW 5 cited by

What Evidence Do Language Models Find Convincing?

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.11782 v2 pith:M6FLPXZI submitted 2024-02-19 cs.CL cs.LG

classification cs.CLcs.LG
keywords findevidencemodelsqueriesconvincingdatasetfeatureslanguage
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Retrieval-augmented language models are being increasingly tasked with subjective, contentious, and conflicting queries such as "is aspartame linked to cancer". To resolve these ambiguous queries, one must search through a large range of websites and consider "which, if any, of this evidence do I find convincing?". In this work, we study how LLMs answer this question. In particular, we construct ConflictingQA, a dataset that pairs controversial queries with a series of real-world evidence documents that contain different facts (e.g., quantitative results), argument styles (e.g., appeals to authority), and answers (Yes or No). We use this dataset to perform sensitivity and counterfactual analyses to explore which text features most affect LLM predictions. Overall, we find that current models rely heavily on the relevance of a website to the query, while largely ignoring stylistic features that humans find important such as whether a text contains scientific references or is written with a neutral tone. Taken together, these results highlight the importance of RAG corpus quality (e.g., the need to filter misinformation), and possibly even a shift in how LLMs are trained to better align with human judgements.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Generative Engine Optimization: How to Dominate AI Search

    cs.IR 2025-09 conditional novelty 6.0 of 10

    Across hundreds of query comparisons, AI search engines systematically favor earned media over brand-owned and social sources, and vary strongly by engine and language.

  2. ImportSnare: Directed "Code Manual" Hijacking in Retrieval-Augmented Code Generation

    cs.CR 2025-09 conditional novelty 6.0 of 10

    Documentation poisoning with hidden ranking and suggestion sequences can make RAG-based code generators confidently recommend malicious dependencies, even at 0.01% poisoning ratios.

  3. Do as We Do, Not as You Think: the Conformity of Large Language Models

    cs.CL 2025-01 conditional novelty 6.0 of 10

    In multi-agent question answering, all 11 tested LLMs abandon some correct answers to follow a unanimous wrong majority, with the effect strongest under the Doubt protocol.

  4. Evaluating Large Language Models for Evidence-Based Clinical Question Answering

    cs.CL 2025-09 conditional novelty 5.0 of 10

    A new multi-source clinical QA benchmark shows GPT models answer structured guideline questions best, perform worse on narrative texts and systematic reviews, and improve with retrieved abstracts.

  5. Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models

    cs.CL 2024-12 conditional novelty 3.0 of 10

    Current LLMs are about as persuasive as humans, can deceive strategically, but show small effect sizes; future techniques may increase this risk.

Pith tools