# What Evidence Do Language Models Find Convincing?

arXiv: https://arxiv.org/abs/2402.11782 · HTML: https://mlsanity.com/paper/2402.11782/

## Key facts

- Cited by 75 papers in the map (data through 14 Oct 2026).
- Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 30 of its 50 references that are in the map.
- First posted on arXiv 19 Feb 2024.

## Placed in

- Retrieval-augmented generation / [Medical and biomedical RAG](https://mlsanity.com/rag/medical-and-biomedical-rag/)

## Builds on (most cited first, 30 of 30)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Adversarial Examples for Evaluating Reading Comprehension Systems](https://mlsanity.com/paper/1707.07328/) (2017)
- [TinyStories: How Small Can Language Models Be and Still Speak Coherent English?](https://mlsanity.com/paper/2305.07759/) (2023)
- [Augmented Language Models: a Survey](https://mlsanity.com/paper/2302.07842/) (2023)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [Entity-Based Knowledge Conflicts in Question Answering](https://mlsanity.com/paper/2109.05052/) (2021)
- [Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts](https://mlsanity.com/paper/2305.13300/) (2023)
- [Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling](https://mlsanity.com/paper/2104.06967/) (2021)
- [SituatedQA: Incorporating Extra-Linguistic Contexts into QA](https://mlsanity.com/paper/2109.06157/) (2021)
- [Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence](https://mlsanity.com/paper/2210.13701/) (2022)
- [Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information](https://mlsanity.com/paper/1805.04655/) (2018)
- [A Large-scale Dataset for Argument Quality Ranking: Construction and Analysis](https://mlsanity.com/paper/1911.11408/) (2019)
- [Automatic Argument Quality Assessment -- New Datasets and Methods](https://mlsanity.com/paper/1909.01007/) (2019)
- [Synthetic Disinformation Attacks on Automated Fact Verification Systems](https://mlsanity.com/paper/2202.09381/) (2022)
- [Attacking Open-domain Question Answering by Injecting Misinformation](https://mlsanity.com/paper/2110.07803/) (2021)
- [Are You Convinced? Choosing the More Convincing Evidence with a Siamese Network](https://mlsanity.com/paper/1907.08971/) (2019)
- [Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems](https://mlsanity.com/paper/2209.03755/) (2022)
- [Answering Ambiguous Questions with a Database of Questions, Answers, and Revisions](https://mlsanity.com/paper/2308.08661/) (2023)

## Built on by (most cited first, 30 of 75)

- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models](https://mlsanity.com/paper/2506.01062/) (2025)
- [Retrieval-Augmented Generation with Conflicting Evidence](https://mlsanity.com/paper/2504.13079/) (2025)
- [MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate](https://mlsanity.com/paper/2406.14711/) (2024)
- [Do as We Do, Not as You Think: the Conformity of Large Language Models](https://mlsanity.com/paper/2501.13381/) (2025)
- [Adversarial Search Engine Optimization for Large Language Models](https://mlsanity.com/paper/2406.18382/) (2024)
- [Prompting Techniques for Reducing Social Bias in LLMs through System 1 and System 2 Cognitive Processes](https://mlsanity.com/paper/2404.17218/) (2024)
- [DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models](https://mlsanity.com/paper/2407.17023/) (2024)
- [From Distributional to Overton Pluralism: Investigating Large Language Model Alignment](https://mlsanity.com/paper/2406.17692/) (2024)
- [How Susceptible are LLMs to Influence in Prompts?](https://mlsanity.com/paper/2408.11865/) (2024)
- [DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs](https://mlsanity.com/paper/2506.08500/) (2025)
- [Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?](https://mlsanity.com/paper/2406.19354/) (2024)
- [Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation](https://mlsanity.com/paper/2404.06809/) (2024)
- [AmbigDocs: Reasoning across Documents on Different Entities under the Same Name](https://mlsanity.com/paper/2404.12447/) (2024)
- [Teaching Models to Balance Resisting and Accepting Persuasion](https://mlsanity.com/paper/2410.14596/) (2024)
- [Open Domain Question Answering with Conflicting Contexts](https://mlsanity.com/paper/2410.12311/) (2024)
- [Generative Engine Optimization: How to Dominate AI Search](https://mlsanity.com/paper/2509.08919/) (2025)
- [Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering](https://mlsanity.com/paper/2409.10790/) (2024)
- [VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare](https://mlsanity.com/paper/2502.13775/) (2025)
- [Task Matters: Knowledge Requirements Shape LLM Responses to Context-Memory Conflict](https://mlsanity.com/paper/2506.06485/) (2025)
- [DebateQA: Evaluating Question Answering on Debatable Knowledge](https://mlsanity.com/paper/2408.01419/) (2024)
- [ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation](https://mlsanity.com/paper/2508.20131/) (2025)
- [Whose Facts Win? LLM Source Preferences under Knowledge Conflicts](https://mlsanity.com/paper/2601.03746/) (2026)
- [Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style](https://mlsanity.com/paper/2409.10955/) (2024)
- [Open-World Evaluation for Retrieving Diverse Perspectives](https://mlsanity.com/paper/2409.18110/) (2024)
- [Bias Beware: The Impact of Cognitive Biases on LLM-Driven Product Recommendations](https://mlsanity.com/paper/2502.01349/) (2025)
- [Generating Media Background Checks for Automated Source Critical Reasoning](https://mlsanity.com/paper/2409.00781/) (2024)
- [A Reality Check on Context Utilisation for Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.17031/) (2024)
- [Can Large Language Models Match the Conclusions of Systematic Reviews?](https://mlsanity.com/paper/2505.22787/) (2025)

## Abstract (arXiv)

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.