# Don't Take the Premise for Granted: Evaluating the Premise Critique Ability of Large Language Models

arXiv: https://arxiv.org/abs/2505.23715 · HTML: https://mlsanity.com/paper/2505.23715/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 22 of its 43 references that are in the map.
- First posted on arXiv 29 May 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 22 of 22)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems](https://mlsanity.com/paper/2402.14008/) (2024)
- [Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset](https://mlsanity.com/paper/2402.14804/) (2024)
- [LIMO: Less is More for Reasoning](https://mlsanity.com/paper/2502.03387/) (2025)
- [JudgeBench: A Benchmark for Evaluating LLM-based Judges](https://mlsanity.com/paper/2410.12784/) (2024)
- [LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts](https://mlsanity.com/paper/2407.04973/) (2024)
- [PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts](https://mlsanity.com/paper/2306.04528/) (2023)
- [A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems](https://mlsanity.com/paper/2504.09037/) (2025)
- [Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate](https://mlsanity.com/paper/2305.13160/) (2023)
- [BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models](https://mlsanity.com/paper/2401.12242/) (2024)
- [CREPE: Open-Domain Question Answering with False Presuppositions](https://mlsanity.com/paper/2211.17257/) (2022)
- [Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?](https://mlsanity.com/paper/2504.06514/) (2025)
- [Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering](https://mlsanity.com/paper/2101.00391/) (2021)
- [Enhancing Large Language Models Against Inductive Instructions with Dual-critique Prompting](https://mlsanity.com/paper/2305.13733/) (2023)
- [Preemptive Answer "Attacks" on Chain-of-Thought Reasoning](https://mlsanity.com/paper/2405.20902/) (2024)
- [How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformation](https://mlsanity.com/paper/2503.09598/) (2025)
- [Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning](https://mlsanity.com/paper/2504.06438/) (2025)
- [ArithmAttack: Evaluating Robustness of LLMs to Noisy Context in Math Problem Solving](https://mlsanity.com/paper/2501.08203/) (2025)
- [Stepwise Reasoning Error Disruption Attack of LLMs](https://mlsanity.com/paper/2412.11934/) (2024)
- [Investigating the Robustness of Deductive Reasoning with Large Language Models](https://mlsanity.com/paper/2502.04352/) (2025)
- [RuozhiBench: Evaluating LLMs with Logical Fallacies and Misleading Premises](https://mlsanity.com/paper/2502.13125/) (2025)
- [MathDebugger: Detecting and Diagnosing Errors in Synthetic Mathematical Data](https://mlsanity.com/paper/2502.19058/) (2025)

## Built on by (most cited first, 8 of 8)

- [Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priors](https://mlsanity.com/paper/2512.06393/) (2025)
- [Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability](https://mlsanity.com/paper/2508.04017/) (2025)
- [Judge Before Answer: Can MLLM Discern the False Premise in Question?](https://mlsanity.com/paper/2510.10965/) (2025)
- [Refining Critical Thinking in LLM Code Generation: A Faulty Premise-based Evaluation Framework](https://mlsanity.com/paper/2508.03622/) (2025)
- [MMPCBench: Benchmarking Multimodal Large Language Models on Proactive Critique of Flawed Inputs](https://mlsanity.com/paper/2608.29286/) (2026)
- [RPCBench: A Benchmark for Proactive Premise Critique in LLM-based Recommendation](https://mlsanity.com/paper/2609.00918/) (2026)
- [Governed Deduction: Policy-Grounded Premise Authorization Beyond Relevance](https://mlsanity.com/paper/2609.31029/) (2026)
- [ConflictVLA-Bench: Benchmarking Behavioral Responses of Vision-Language-Action Models to Premise Conflicts](https://mlsanity.com/paper/2609.31792/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have witnessed rapid advancements, demonstrating remarkable capabilities. However, a notable vulnerability persists: LLMs often uncritically accept flawed or contradictory premises, leading to inefficient reasoning and unreliable outputs. This emphasizes the significance of possessing the Premise Critique Ability for LLMs, defined as the capacity to proactively identify and articulate errors in input premises. Most existing studies assess LLMs' reasoning ability in ideal settings, largely ignoring their vulnerabilities when faced with flawed premises. Thus, we introduce the Premise Critique Bench (PCBench), designed by incorporating four error types across three difficulty levels, paired with multi-faceted evaluation metrics. We conducted systematic evaluations of 15 representative LLMs. Our findings reveal: (1) Most models rely heavily on explicit prompts to detect errors, with limited autonomous critique; (2) Premise critique ability depends on question difficulty and error type, with direct contradictions being easier to detect than complex or procedural errors; (3) Reasoning ability does not consistently correlate with the premise critique ability; (4) Flawed premises trigger overthinking in reasoning models, markedly lengthening responses due to repeated attempts at resolving conflicts. These insights underscore the urgent need to enhance LLMs' proactive evaluation of input validity, positioning premise critique as a foundational capability for developing reliable, human-centric systems. The code is available at https://github.com/MLGroupJLU/PremiseCritique.