Pith. sign in

REVIEW 12 cited by

Faithful Reasoning Using Large Language Models

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 2208.14271 v1 pith:SKZPINNY submitted 2022-08-30 cs.AI cs.CL

Faithful Reasoning Using Large Language Models

classification cs.AI cs.CL
keywords reasoningmulti-stepdemonstratefaithfullanguagelargelogicalmodel
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Although contemporary large language models (LMs) demonstrate impressive question-answering capabilities, their answers are typically the product of a single call to the model. This entails an unwelcome degree of opacity and compromises performance, especially on problems that are inherently multi-step. To address these limitations, we show how LMs can be made to perform faithful multi-step reasoning via a process whose causal structure mirrors the underlying logical structure of the problem. Our approach works by chaining together reasoning steps, where each step results from calls to two fine-tuned LMs, one for selection and one for inference, to produce a valid reasoning trace. Our method carries out a beam search through the space of reasoning traces to improve reasoning quality. We demonstrate the effectiveness of our model on multi-step logical deduction and scientific question-answering, showing that it outperforms baselines on final answer accuracy, and generates humanly interpretable reasoning traces whose validity can be checked by the user.

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. Tree of Thoughts: Deliberate Problem Solving with Large Language Models

    cs.CL 2023-05 accept novelty 8.0

    Tree of Thoughts enables language models to solve complex planning tasks by generating, evaluating, and searching over coherent intermediate thoughts in a tree, raising Game of 24 success from 4% to 74% with GPT-4.

  2. HIVE: Understanding Post-Hallucination Reasoning in Vision Language Models

    cs.CV 2026-07 conditional novelty 7.0

    Hallucinated captions systematically improve VLM accuracy on vision-language tasks across nine models and nine datasets, with gains linked to broadened semantic coverage and modulated reasoning entropy.

  3. Visual Perceptual to Conceptual First-Order Rule Learning Networks

    cs.AI 2026-04 unverdicted novelty 7.0

    γILP is a differentiable pipeline for inducing first-order rules from unlabeled image data, showing strong performance on symbolic relational datasets, relational images, and pure image datasets such as Kandinsky patterns.

  4. PuzzleWorld: A Benchmark for Multimodal, Open-Ended Reasoning in Puzzlehunts

    cs.CL 2025-06 conditional novelty 7.0

    PuzzleWorld benchmark reveals state-of-the-art AI models solve only 18% of complex puzzlehunt problems with 40% stepwise accuracy, matching novices but trailing enthusiasts, while fine-tuning on traces yields modest gains.

  5. TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis

    cs.LG 2024-10 unverdicted novelty 7.0

    TS-Reasoner is a domain-oriented agent using LLMs, computational tools, and error feedback for multi-step time series inference, showing better performance than general LLMs on understanding and reasoning benchmarks.

  6. Measuring Faithfulness in Chain-of-Thought Reasoning

    cs.AI 2023-07 conditional novelty 7.0

    Chain-of-Thought reasoning in LLMs is often unfaithful, with models relying on it variably by task and less so as models scale larger.

  7. When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel

    cs.AI 2026-05 unverdicted novelty 6.0

    CoT traces align with internal answer commitment in only 61.9% of steps on average, dominated by confabulated continuations after commitment has stabilized.

  8. Language Models can Solve Computer Tasks

    cs.CL 2023-03 accept novelty 6.0

    Pre-trained LLMs using recursive criticism and improvement prompting achieve state-of-the-art results on the MiniWoB++ computer task benchmark with only a handful of demonstrations and no task-specific reward function.

  9. Know Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning

    cs.AI 2026-06 unverdicted novelty 5.0

    Formal structure boosts LLM accuracy on legal entailment but does not produce faithful reasoning, with scope laundering and other failures persisting across models on ContractNLI.

  10. LLM Reasoning Is Latent, Not the Chain of Thought

    cs.AI 2026-04 unverdicted novelty 5.0

    LLM reasoning is primarily mediated by latent-state trajectories rather than by explicit surface chain-of-thought outputs.

  11. Learning to Draw ASCII Improves Spatial Reasoning in Language Models

    cs.AI 2026-04 unverdicted novelty 5.0

    Training LLMs on text-to-ASCII spatial layout construction improves text-only spatial reasoning and transfers to external benchmarks.

  12. Intelligence as Managed Autonomy: Failure, Escalation, and Governance for Agentic AI Systems

    cs.AI 2026-05 unverdicted novelty 4.0

    Introduces the SMARt four-layer model with timed guarded Petri nets to formalize detection of epistemic drift, recovery, and controlled surrender of autonomy in AI agents.