# Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes

arXiv: https://arxiv.org/abs/2507.22940 · HTML: https://mlsanity.com/paper/2507.22940/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 30 of its 75 references that are in the map.
- First posted on arXiv 25 Jul 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 30 of 30)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [LoRA Learns Less and Forgets Less](https://mlsanity.com/paper/2405.09673/) (2024)
- [Rethinking with Retrieval: Faithful Large Language Model Inference](https://mlsanity.com/paper/2301.00303/) (2022)
- [Internet-augmented language models through few-shot prompting for open-domain question answering](https://mlsanity.com/paper/2203.05115/) (2022)
- [Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture](https://mlsanity.com/paper/2306.16092/) (2023)
- [INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent](https://mlsanity.com/paper/2412.18174/) (2024)
- [Large Language Models for Disease Diagnosis: A Scoping Review](https://mlsanity.com/paper/2409.00097/) (2024)
- [SAIL: Search-Augmented Instruction Learning](https://mlsanity.com/paper/2305.15225/) (2023)
- [Towards Robust Legal Reasoning: Harnessing Logical LLMs in Law](https://mlsanity.com/paper/2502.17638/) (2025)
- [Evaluating LLM -- Generated Multimodal Diagnosis from Medical Images and Symptom Analysis](https://mlsanity.com/paper/2402.01730/) (2024)
- [Order Matters in Hallucination: Reasoning Order as Benchmark and Reflexive Prompting for Large-Language-Models](https://mlsanity.com/paper/2408.05093/) (2024)
- [Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning](https://mlsanity.com/paper/2502.05675/) (2025)
- [The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Models](https://mlsanity.com/paper/2305.13669/) (2023)

## Built on by (most cited first, 1 of 1)

- [Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution](https://mlsanity.com/paper/2605.19228/) (2026)

## Abstract (arXiv)

We present a novel framework addressing a critical vulnerability in Large Language Models (LLMs): the prevalence of factual inaccuracies within intermediate reasoning steps despite correct final answers. This phenomenon poses substantial risks in high-stakes domains including healthcare, legal analysis, and scientific research, where erroneous yet confidently presented reasoning can mislead users into dangerous decisions. Our framework integrates three core components: (1) a specialized fact-checking classifier trained on counterfactually augmented data to detect subtle factual inconsistencies within reasoning chains; (2) an enhanced Group Relative Policy Optimization (GRPO) reinforcement learning approach that balances factuality, coherence, and structural correctness through multi-dimensional rewards; and (3) a mechanistic interpretability method examining how factuality improvements manifest in model activations during reasoning processes. Extensive evaluation across multi state-of-the-art models reveals concerning patterns: even leading models like Claude-3.7 and GPT-o1 demonstrate reasoning factual accuracy of only 81.93% and 82.57% respectively. Our approach significantly enhances factual robustness (up to 49.90% improvement) while maintaining or improving performance on challenging benchmarks including Math-500, AIME-2024, and GPQA. Furthermore, our neural activation-level analysis provides actionable insights into how factual enhancements reshape reasoning trajectories within model architectures, establishing foundations for future training methodologies that explicitly target factual robustness through activation-guided optimization.