Pith. sign in

REVIEW 12 cited by

LLMs cannot find reasoning errors, but can correct them given the error location

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 2311.08516 v3 pith:7JXLSP7T submitted 2023-11-14 cs.AI cs.CLcs.LG

LLMs cannot find reasoning errors, but can correct them given the error location

classification cs.AI cs.CLcs.LG
keywords llmsmistakereasoningcorrectlocationlogicalmistakesperformance
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

While self-correction has shown promise in improving LLM outputs in terms of style and quality (e.g. Chen et al., 2023b; Madaan et al., 2023), recent attempts to self-correct logical or reasoning errors often cause correct answers to become incorrect, resulting in worse performances overall (Huang et al., 2023). In this paper, we show that poor self-correction performance stems from LLMs' inability to find logical mistakes, rather than their ability to correct a known mistake. Firstly, we benchmark several state-of-the-art LLMs on their mistake-finding ability and demonstrate that they generally struggle with the task, even in highly objective, unambiguous cases. Secondly, we test the correction abilities of LLMs -- separately from mistake finding -- using a backtracking setup that feeds ground truth mistake location information to the model. We show that this boosts downstream task performance across our 5 reasoning tasks, indicating that LLMs' correction abilities are robust. Finally, we show that it is possible to obtain mistake location information without ground truth labels or in-domain training data. We train a small classifier with out-of-domain data, which exhibits stronger mistake-finding performance than prompting a large model. We release our dataset of LLM-generated logical mistakes, BIG-Bench Mistake, to enable further research into locating LLM reasoning mistakes.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

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

  1. DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination

    cs.LG 2026-06 unverdicted novelty 7.0

    DICE formalizes multi-agent LLM coordination as discounted incomplete-information Markov games and introduces Heterogeneous Quantal Response Equilibrium (HQRE) to achieve unique stable equilibria with bounded regret, ...

  2. DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination

    cs.LG 2026-06 conditional novelty 6.5

    HQRE entropy regularization makes multi-agent LLM coordination well-posed, yielding unique equilibria, linear mirror convergence, bounded Bayesian regret, and DICE gains of 4.3–8.5 pp on reasoning/planning tasks.

  3. Multi-Turn On-Policy Distillation with Prefix Replay

    cs.LG 2026-07 conditional novelty 6.0

    ReOPD offline-distills multi-turn agentic LLMs via teacher-prefix replay plus step-decay sampling, matching online OPD accuracy at ≥4× speed with zero tool calls.

  4. ATTAIN: Automated Exploit Failure Analysis through Trace-Driven Diff Analysis

    cs.SE 2026-06 unverdicted novelty 6.0

    ATTAIN is a three-module trace-driven framework that combines exploit execution, LLM-guided diff search, and evidence-based judgment to identify affected library versions for CVEs, reporting 93.24% F1 on 224 CVEs acro...

  5. The Self-Correction Illusion: LLMs Correct Others but Not Themselves

    cs.AI 2026-06 conditional novelty 6.0

    Relabeling an identical erroneous claim from the model's own thought role to an external chat role increases explicit correction rates by 23-93 percentage points across 13 model-domain cells, indicating a chat-templat...

  6. Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution

    cs.CL 2026-05 unverdicted novelty 6.0

    SCA framework applies Information Bottleneck to assign step-level confidence in black-box LLM reasoning traces, flagging errors and boosting self-correction success by up to 13.5% on math and QA tasks.

  7. Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution

    cs.CL 2026-05 unverdicted novelty 6.0

    SCA applies the Information Bottleneck principle via NIBS and GIBS methods to identify erroneous steps in black-box LLM reasoning and boosts self-correction success by up to 13.5%.

  8. Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs

    cs.CL 2026-05 unverdicted novelty 6.0

    Four axioms (Causality, Minimality, Separability, Stability) are formalized for latent thought representations; audits of open LLMs on 23 tasks show none satisfy all four and representations add little beyond input em...

  9. LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

    cs.SE 2024-03 unverdicted novelty 6.0

    LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.

  10. From Hallucination to Structure Snowballing: The Alignment Tax of Constrained Decoding in LLM Reflection

    cs.CL 2026-04 unverdicted novelty 5.0

    Enforcing structured reflection via Outlines-based constrained decoding on an 8B LLM triggers structure snowballing instead of better self-correction, producing near-perfect syntax but persistent semantic errors and r...

  11. Gemma 3 Technical Report

    cs.CL 2025-03 accept novelty 4.0

    Gemma 3 introduces multimodal open models with architectural changes for efficient long context, trained via distillation and a new post-training recipe that makes the 4B version competitive with prior 27B models and ...

  12. LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods

    cs.CL 2024-12 accept novelty 3.0

    A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.