Dissociation of Faithful and Unfaithful Reasoning in LLMs

• URL: http://arxiv.org/abs/2405.15092v2
• Date: Mon, 2 Sep 2024 22:40:20 GMT
• Title: Dissociation of Faithful and Unfaithful Reasoning in LLMs
• Authors: Evelyn Yee, Alice Li, Chenyu Tang, Yeon Ho Jung, Ramamohan Paturi, Leon Bergen,
• Abstract summary: We investigate how large language models (LLMs) recover from errors in Chain of Thought. We find evidence for unfaithfulness in Chain of Thought, which occurs when models arrive at the correct answer despite invalid reasoning text.
• Score: 2.4893095725361922
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) often improve their performance in downstream tasks when they generate Chain of Thought reasoning text before producing an answer. We investigate how LLMs recover from errors in Chain of Thought. Through analysis of error recovery behaviors, we find evidence for unfaithfulness in Chain of Thought, which occurs when models arrive at the correct answer despite invalid reasoning text. We identify factors that shift LLM recovery behavior: LLMs recover more frequently from obvious errors and in contexts that provide more evidence for the correct answer. Critically, these factors have divergent effects on faithful and unfaithful recoveries. Our results indicate that there are distinct mechanisms driving faithful and unfaithful error recoveries. Selective targeting of these mechanisms may be able to drive down the rate of unfaithful reasoning and improve model interpretability.

Related papers

• Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution [79.98699884805636]
  Reasoning Execution by Multiple Listeners (REMUL) is a multi-party reinforcement learning approach.<n>REMUL builds on the hypothesis that reasoning traces which other parties can follow will be more faithful.<n>Speakers are rewarded for producing reasoning that is clear to listeners.
  arXiv  Detail & Related papers  (2026-02-18T02:55:55Z)
• Are Reasoning LLMs Robust to Interventions on Their Chain-of-Thought? [79.86483056611105]
  Reasoning LLMs generate step-by-step chains of thought before giving an answer.<n>How robust are these reasoning traces to disruptions that occur within them?<n>We introduce a controlled evaluation framework that perturbs a model's own CoT at fixed timesteps.
  arXiv  Detail & Related papers  (2026-02-07T10:02:58Z)
• Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflicts [74.47786985522762]
  We identify a critical failure mode termed textual inertia, where models tend to blindly adhere to the erroneous text while neglecting conflicting visual evidence.<n>We propose the LogicGraph Perturbation Protocol that structurally injects perturbations into the reasoning chains of diverse LMMs.<n>Results reveal that models successfully self-correct in less than 10% of cases and predominantly succumb to blind textual error propagation.
  arXiv  Detail & Related papers  (2026-01-07T16:39:34Z)
• Causal Reflection with Language Models [0.276240219662896]
  We introduce Causal Reflection, a framework that explicitly models causality as a dynamic function over state, action, time, and perturbation.<n>We define a formal Reflect mechanism that identifies mismatches between predicted and observed outcomes and generates causal hypotheses to revise the agent's internal model.<n>Our framework lays the theoretical groundwork for Causal Reflective agents that can adapt, self-correct, and communicate causal understanding in evolving environments.
  arXiv  Detail & Related papers  (2025-08-06T14:44:23Z)
• Lost at the Beginning of Reasoning [82.18834329384514]
  We show that the first reasoning step exerts a disproportionately large influence on the final prediction.<n>We propose an efficient sampling strategy that leverages a reward model to identify and retain high-quality first reasoning steps.<n>We introduce a new benchmark specifically constructed with deliberately flawed first reasoning steps to systematically evaluate model self-correction capabilities.
  arXiv  Detail & Related papers  (2025-06-27T09:53:57Z)
• Misaligning Reasoning with Answers -- A Framework for Assessing LLM CoT Robustness [3.9930400744726273]
  We design a novel evaluation framework, MATCHA, to investigate the relationship between answer and reasoning.<n>In domains like education and healthcare, reasoning is key for model trustworthiness.<n>Our results show that LLMs exhibit greater vulnerability to input perturbations for multi-step and commonsense tasks than compared to logical tasks.
  arXiv  Detail & Related papers  (2025-05-23T02:42:16Z)
• Process or Result? Manipulated Ending Tokens Can Mislead Reasoning LLMs to Ignore the Correct Reasoning Steps [39.759594479826454]
  We explore how vulnerable are reasoning models to subtle errors in their input reasoning chains. We introduce "Compromising Thought" (CPT), a vulnerability where models presented with reasoning tokens containing manipulated calculation results tend to ignore correct reasoning steps and adopt incorrect results instead. Our work enhances understanding of reasoning robustness and highlights security considerations for reasoning-intensive applications.
  arXiv  Detail & Related papers  (2025-03-25T03:43:11Z)
• LaMOuR: Leveraging Language Models for Out-of-Distribution Recovery in Reinforcement Learning [16.093659272414527]
  We introduce Language Models for Out-of-Distribution Recovery (LaMOuR), which enables recovery learning without relying on uncertainty estimation. LaMOuR generates dense reward codes that guide the agent back to a state where it can successfully perform its original task. Experimental results show that LaMOuR substantially enhances recovery efficiency across diverse locomotion tasks.
  arXiv  Detail & Related papers  (2025-03-21T13:20:39Z)
• Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies [66.30619782227173]
  Large language models (LLMs) can produce erroneous responses that sound fluent and convincing. We identify several features of LLM responses that shape users' reliance. We find that explanations increase reliance on both correct and incorrect responses. We observe less reliance on incorrect responses when sources are provided or when explanations exhibit inconsistencies.
  arXiv  Detail & Related papers  (2025-02-12T16:35:41Z)
• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)
• Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback [14.120154004011084]
  Large Language Models (LLMs) often generate erroneous outputs, known as hallucinations. We present a novel alignment framework called Reinforcement Learning from Knowledge Feedback (RLKF)
  arXiv  Detail & Related papers  (2024-03-27T08:39:56Z)
• How Likely Do LLMs with CoT Mimic Human Reasoning? [31.86489714330338]
  Chain-of-thought (CoT) emerges as a promising technique to elicit reasoning capabilities from Large Language Models (LLMs) In this paper, we diagnose the underlying mechanism by comparing the reasoning process of LLMs with humans. Our empirical study reveals that LLMs often deviate from a causal chain, resulting in spurious correlations and potential consistency errors.
  arXiv  Detail & Related papers  (2024-02-25T10:13:04Z)
• Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate [75.10515686215177]
  Large Language Models (LLMs) excel in text generation, but their capability for producing faithful explanations in fact-checking remains underexamined. We propose the Multi-Agent Debate Refinement (MADR) framework, leveraging multiple LLMs as agents with diverse roles. MADR ensures that the final explanation undergoes rigorous validation, significantly reducing the likelihood of unfaithful elements and aligning closely with the provided evidence.
  arXiv  Detail & Related papers  (2024-02-12T04:32:33Z)
• Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives [45.87069217634753]
  Research indicates without external feedback, Large Language Model's intrinsic reflection is unstable. Our investigation unveils that the key bottleneck is the quality of the self-evaluated feedback. We advocate Self-Contrast: It adaptively explores diverse solving perspectives tailored to the request, contrasts the differences, and summarizes these discrepancies into a checklist which could be used to re-examine and eliminate discrepancies.
  arXiv  Detail & Related papers  (2024-01-04T00:32:33Z)
• A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning [73.77088902676306]
  We take a closer look at the self-verification abilities of large language models (LLMs) in the context of logical reasoning. Our main findings suggest that existing LLMs could struggle to identify fallacious reasoning steps accurately and may fall short of guaranteeing the validity of self-verification methods.
  arXiv  Detail & Related papers  (2023-11-14T07:13:10Z)
• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection [74.51523859064802]
  We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) Self-RAG enhances an LM's quality and factuality through retrieval and self-reflection. It significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-10-17T18:18:32Z)
• Language Models with Rationality [57.37201135072838]
  Large language models (LLMs) are proficient at question-answering (QA) It is not always clear how (or even if) an answer follows from their latent "beliefs"
  arXiv  Detail & Related papers  (2023-05-23T17:04:25Z)
• RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought [56.558892336235914]
  Reversing Chain-of-Thought (RCoT) is a novel method to improve large language models' reasoning abilities. RCoT automatically detects and rectifys factual inconsistency in generated solutions. We show that manually written fine-grained feedback can dramatically improve LLMs' reasoning abilities.
  arXiv  Detail & Related papers  (2023-05-19T08:02:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.