mlsanityData to 7 Oct 2026

GeoFaith: A Spatio-Temporal Dual View of Faithful Chain-of-Thought

arXiv 2605.26893 ↗First posted 26 May 2026cs.CL cs.AIcited by 0

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

Chain-of-Thought (CoT) reasoning has advanced large language models (LLMs), but outcome-based supervision leads to pervasive post-hoc rationalization, producing plausible yet unfaithful reasoning chains. Most prior faithfulness assessment methods are either unscalable, expensive, or unreliable. We propose GeoFaith, a spatio-temporal framework that leverages latent geometric structure and entropy dynamics to diagnose and enforce faithful reasoning. We develop a scalable bootstrapping pipeline expanding step-level annotations from 1k to 20k samples across four domains, train an 8B faithfulness detector outperforming GPT-5 on standard benchmarks, and design a faithfulness-aware reinforcement learning framework jointly optimizing outcome correctness, process faithfulness, and trajectory consistency. Experiments show the proposed method achieves superior performance on both faithfulness detection and downstream reasoning, producing shorter, more interpretable chains without sacrificing accuracy. Our code will be made available publicly.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 32 of its 55 references that are in the map. First posted on arXiv 26 May 2026.

Builds on

32 of 55 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Evaluating GRPO and DPO for Faithful Chain-of-Thought Reasoning in LLMs27 Dec
  2. 2025FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning5 Oct
  3. 2025Reasoning Models Don't Always Say What They Think8 May
  4. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models12 Mar
  5. 2025Chain-of-Thought Reasoning In The Wild Is Not Always Faithful11 Mar
  6. 2023Measuring Faithfulness in Chain-of-Thought Reasoning17 Jul
  7. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar

Other references · 25

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  3. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  4. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  5. 2024Robotic Control via Embodied Chain-of-Thought Reasoningcited by 340
  6. 2022Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thoughtcited by 334
  7. 2018Understanding disentangling in β-VAEcited by 332
  8. 2025DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoningcited by 261
  9. 2025Why Language Models Hallucinatecited by 205
  10. 2017Latent Space Oddity: on the Curvature of Deep Generative Modelscited by 169
  11. 2020LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoningcited by 68
  12. 2025Rethinking Entropy Interventions in RLVR: An Entropy Change Perspectivecited by 50
13 more
  1. 2025TruthRL: Incentivizing Truthful LLMs via Reinforcement Learningcited by 20
  2. 2026LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signalscited by 18
  3. 2025KnowRL: Exploring Knowledgeable Reinforcement Learning for Factualitycited by 17
  4. 2024Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcementcited by 12
  5. 2026RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Modelscited by 9
  6. 2024Decoder ensembling for learned latent geometriescited by 6
  7. 2025LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervisioncited by 6
  8. 2026Reasoning emerges from constrained inference manifolds in large language modelscited by 5
  9. 2026Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stabilitycited by 4
  10. 2025FaithLens: Detecting and Explaining Faithfulness Hallucinationcited by 3
  11. 2026GeoSteer: Faithful Chain-of-Thought Steering via Latent Manifold Gradientscited by 3
  12. 2024Geometric Analysis of Reasoning Trajectories: A Phase Space Approach to Understanding Valid and Invalid Multi-Hop Reasoning in LLMscited by 2
  13. 2026Does Inference Scaling Improve Reasoning Faithfulness? A Multi-Model Analysis of Self-Consistency Tradeoffscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning
  2. 2026C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning
  3. 2026Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?
  4. 2025FRIT: Using Causal Importance to Improve Chain-of-Thought Faithfulness
  5. 2026SIFT: Robust Meta-Faithfulness Verification of Chain-of-Thought Reasoning Under Distribution Shift
  6. 2026Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth
  7. 2026SpatialChain: A Benchmark for Auditing Spatial Reasoning Faithfulness in VLMs
  8. 2025A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models