Pith. sign in

REVIEW 10 cited by

Question Decomposition Improves the Faithfulness of Model-Generated Reasoning

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 2307.11768 v2 pith:JN4KZW5T submitted 2023-07-17 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords reasoningfaithfulnessmodelmodel-generatedmodelstasksanswerapproach
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

As large language models (LLMs) perform more difficult tasks, it becomes harder to verify the correctness and safety of their behavior. One approach to help with this issue is to prompt LLMs to externalize their reasoning, e.g., by having them generate step-by-step reasoning as they answer a question (Chain-of-Thought; CoT). The reasoning may enable us to check the process that models use to perform tasks. However, this approach relies on the stated reasoning faithfully reflecting the model's actual reasoning, which is not always the case. To improve over the faithfulness of CoT reasoning, we have models generate reasoning by decomposing questions into subquestions. Decomposition-based methods achieve strong performance on question-answering tasks, sometimes approaching that of CoT while improving the faithfulness of the model's stated reasoning on several recently-proposed metrics. By forcing the model to answer simpler subquestions in separate contexts, we greatly increase the faithfulness of model-generated reasoning over CoT, while still achieving some of the performance gains of CoT. Our results show it is possible to improve the faithfulness of model-generated reasoning; continued improvements may lead to reasoning that enables us to verify the correctness and safety of LLM behavior.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

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

  1. Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning

    cs.CL 2025-06 conditional novelty 7.0 of 10

    A pre-RL fine-tuning intervention called verbalization fine-tuning makes language models explicitly acknowledge when prompt cues drive them to reward-hack, cutting undetected reward hacking from 88% to 6% after RL.

  2. Training Large Language Models for Self-Explanation Faithfulness

    cs.LG 2026-07 conditional novelty 6.0 of 10

    RL fine-tuning with a counterfactual mention/influence reward raises LLM self-explanation faithfulness (Phi-CCT) from near zero to ~0.66 in-distribution for two 8B models, with partial transfer to held-out tasks.

  3. REFACT: Adaptive Fact Restatement for Compact and Faithful Chain-of-Thought Reasoning

    cs.CL 2026-07 conditional novelty 6.0 of 10

    REFACT teaches LLMs to adaptively cite only the source facts needed during chain-of-thought reasoning, improving faithfulness and shortening reasoning traces.

  4. CASE: Causal Alignment and Structural Enforcement for Improving Chain-of-Thought Faithfulness

    cs.CL 2026-07 conditional novelty 6.0 of 10

    CASE improves CoT faithfulness by training on counterfactual/biased/empty instructions and masking instruction-to-answer attention, reporting 37% average relative faithfulness gains.

  5. Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"

    cs.CL 2026-02 conditional novelty 6.0 of 10

    Disagreement between direct and decomposed prompting is a training-free error signal that outperforms standard uncertainty baselines for closed-book QA abstention.

  6. Synthetic Heuristic Evaluation: A Comparison between AI- and Human-Powered Usability Evaluation

    cs.HC 2025-07 reject novelty 6.0 of 10

    An LLM prompted to conduct heuristic evaluation reported more usability issues on two apps than five human experts, but the ground truth included the LLM's own findings.

  7. Agentic Enterprise: AI-Centric User to User-Centric AI

    cs.AI 2025-06 unverdicted novelty 5.0 of 10

    Enterprise AI should be reorganized into a user-centric market of specialized agents guided by six tenets rather than built around general-purpose assistants.

  8. Socratic-MCTS: Test-Time Visual Reasoning by Asking the Right Questions

    cs.CV 2025-06 conditional novelty 5.0 of 10

    Socratic-MCTS uses the model's own subquestions and answers in a Monte Carlo Tree Search to improve multimodal multiple-choice accuracy without fine-tuning.

  9. A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models

    cs.CL 2025-09 conditional novelty 4.0 of 10

    A structured literature survey concluding that reasoning capabilities do not automatically make LLMs more trustworthy and can introduce new vulnerabilities in safety, robustness, and privacy.

  10. The Science of Evaluating Foundation Models

    cs.CL 2025-02 conditional novelty 3.0 of 10

    A survey-and-checklist proposal that organizes LLM evaluation into an ABCD framework (Algorithm, Big Data, Computation, Domain Expertise) for context-aware, documented assessment.

Pith tools