# Self-Contradictory Reasoning Evaluation and Detection

arXiv: https://arxiv.org/abs/2311.09603 · HTML: https://mlsanity.com/paper/2311.09603/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 27 of its 45 references that are in the map.
- First posted on arXiv 16 Nov 2023.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 27 of 27)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Chain-of-Verification Reduces Hallucination in Large Language Models](https://mlsanity.com/paper/2309.11495/) (2023)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [Faithful Chain-of-Thought Reasoning](https://mlsanity.com/paper/2301.13379/) (2023)
- [Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters](https://mlsanity.com/paper/2212.10001/) (2022)
- [ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning](https://mlsanity.com/paper/2212.07919/) (2022)
- [The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning](https://mlsanity.com/paper/2205.03401/) (2022)
- [Measuring Association Between Labels and Free-Text Rationales](https://mlsanity.com/paper/2010.12762/) (2020)
- [Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation](https://mlsanity.com/paper/2305.15852/) (2023)
- [Few-Shot Self-Rationalization with Natural Language Prompts](https://mlsanity.com/paper/2111.08284/) (2021)
- [Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment](https://mlsanity.com/paper/2311.08596/) (2023)
- [PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales](https://mlsanity.com/paper/2211.01562/) (2022)
- [Commonsense for Generative Multi-Hop Question Answering Tasks](https://mlsanity.com/paper/1809.06309/) (2018)
- [Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning](https://mlsanity.com/paper/2210.12217/) (2022)
- [GPT-4 as an Effective Zero-Shot Evaluator for Scientific Figure Captions](https://mlsanity.com/paper/2310.15405/) (2023)
- [Tailoring Self-Rationalizers with Multi-Reward Distillation](https://mlsanity.com/paper/2311.02805/) (2023)
- [WikiContradiction: Detecting Self-Contradiction Articles on Wikipedia](https://mlsanity.com/paper/2111.08543/) (2021)
- [Does Self-Rationalization Improve Robustness to Spurious Correlations?](https://mlsanity.com/paper/2210.13575/) (2022)
- [Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering](https://mlsanity.com/paper/2305.14901/) (2023)

## Built on by (most cited first, 14 of 14)

- [LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models](https://mlsanity.com/paper/2404.05221/) (2024)
- [Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus](https://mlsanity.com/paper/2411.12498/) (2024)
- [Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning](https://mlsanity.com/paper/2504.06438/) (2025)
- [Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning](https://mlsanity.com/paper/2402.18344/) (2024)
- [Garbage In, Reasoning Out? Why Benchmark Scores are Unreliable and What to Do About It](https://mlsanity.com/paper/2506.23864/) (2025)
- [Beg to Differ: Understanding Reasoning-Answer Misalignment Across Languages](https://mlsanity.com/paper/2512.22712/) (2025)
- [Lie to Me: Knowledge Graphs for Robust Hallucination Self-Detection in LLMs](https://mlsanity.com/paper/2512.23547/) (2025)
- [Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detection](https://mlsanity.com/paper/2601.19245/) (2026)
- [Weather-R1: Logically Consistent Reinforcement Fine-Tuning for Multimodal Reasoning in Meteorology](https://mlsanity.com/paper/2601.14044/) (2026)
- [m2sv: A Scalable Benchmark for Map-to-Street-View Spatial Reasoning](https://mlsanity.com/paper/2601.19099/) (2026)
- [Should We be Pedantic About Reasoning Errors in Machine Translation?](https://mlsanity.com/paper/2604.09890/) (2026)
- [ForEx: A Formal Verification Framework for Explainable Reasoning in Logical Fallacy Detection and Annotation](https://mlsanity.com/paper/2606.21867/) (2026)
- [The Consistency Dilemma in LLMs: Generator-Evaluator Agreement and Vulnerability to Mistakes](https://mlsanity.com/paper/2606.30653/) (2026)
- [WordPolo: Evaluating Language Models Through Iterative Semantic Feedback](https://mlsanity.com/paper/2609.19006/) (2026)

## Abstract (arXiv)

In a plethora of recent work, large language models (LLMs) demonstrated impressive reasoning ability, but many proposed downstream reasoning tasks only focus on final answers. Two fundamental questions persist: 1) how consistent is the reasoning, and 2) can models detect unreliable reasoning? In this paper, we investigate self-contradictory (Self-Contra) reasoning, where the model reasoning does not support its answers. To answer 1), we define and assess the Self-Contra rate across three datasets and delve into finer-grained categories of Self-Contra reasoning. We find that LLMs often contradict themselves in reasoning tasks involving contextual information understanding or commonsense. The model may generate correct answers by taking shortcuts in reasoning or overlooking contextual evidence, leading to compromised reasoning. For 2), we task the state-of-the-art model GPT-4 with identifying Self-Contra reasoning and finer-grained fallacies. We find that finer-grained categories enhanced detection can improve GPT-4's ability to detect Self-Contra. However, it is only able to detect Self-Contra with a 52.2% F1 score, much lower compared to 66.7% for humans. Our results indicate that current LLMs lack the robustness necessary for reliable reasoning and we emphasize the urgent need for establishing best practices in comprehensive reasoning evaluations beyond pure performance-based metrics.