ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretability

• URL: http://arxiv.org/abs/2510.09062v1
• Date: Fri, 10 Oct 2025 07:08:44 GMT
• Title: ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretability
• Authors: Chung-En Sun, Ge Yan, Akshay Kulkarni, Tsui-Wei Weng,
• Abstract summary: We argue that usable reasoning systems must be trustworthy, characterized by three properties: interpretability, faithfulness, and reliability.<n>We propose ReFIne, a new training framework that integrates supervised fine-tuning with GRPO to encourage models to improve interpretability.<n>Our experimental results show that ReFIne models generate clearer and better-structured reasoning traces.
• Score: 23.70973331911138
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in long chain-of-thought (CoT) reasoning have largely prioritized answer accuracy and token efficiency, while overlooking aspects critical to trustworthiness. We argue that usable reasoning systems must be trustworthy, characterized by three properties: interpretability, faithfulness, and reliability. To this end, we propose ReFIne, a new training framework that integrates supervised fine-tuning with GRPO to encourage models to: (i) improve interpretability by producing structured, tag-based traces with high-level planning that are easier for humans to follow; (ii) enhance faithfulness by explicitly disclosing the decisive information guiding each solution, with consistent cross-section references; and (iii) promote reliability by providing self-assessments of both the derivation's soundness and the confidence of the final answer. We apply ReFIne to the Qwen3 models at multiple scales (1.7B/4B/8B) and evaluate across mathematical benchmarks of varying difficulty. Our experimental results show that ReFIne models generate clearer and better-structured reasoning traces (interpretability +44.0%), more faithfully expose their underlying decision process (faithfulness +18.8%), and offer informative confidence estimates (reliability +42.4%). These findings highlight an overlooked but important direction: reasoning models should be optimized not only for accuracy, but also for broader dimensions of trustworthiness. Our code is available at: https://github.com/Trustworthy-ML-Lab/Training_Trustworthy_LRM_with_Refine

Related papers

• Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems [94.9141394384021]
  Individual agents in multi-agent systems often lack robustness, tending to blindly conform to misleading peers.<n>We show this weakness stems from both sycophancy and inadequate ability to evaluate peer reliability.<n>We first formalize the learning problem of history-aware reference, introducing the historical interactions of peers as additional input.<n>We then develop Epistemic Context Learning (ECL), a reasoning framework that conditions predictions on explicitly-built peer profiles from history.
  arXiv  Detail & Related papers  (2026-01-29T13:59:32Z)
• Revisiting the Reliability of Language Models in Instruction-Following [15.281163913211818]
  LLMs have achieved near-ceiling instruction-following accuracy on benchmarks such as IFEval.<n>We study nuance-oriented reliability: whether models exhibit consistent competence across cousin prompts that convey analogous user intents but with subtle nuances.<n>Our findings highlight nuance-oriented reliability as a crucial yet underexplored next step toward more dependable and trustworthy LLM behavior.
  arXiv  Detail & Related papers  (2025-12-15T02:57:55Z)
• ConfTuner: Training Large Language Models to Express Their Confidence Verbally [58.63318088243125]
  Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as science, law, and healthcare.<n>LLMs are often observed to generate incorrect answers with high confidence, a phenomenon known as "overconfidence"
  arXiv  Detail & Related papers  (2025-08-26T09:25:32Z)
• Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation [63.49409574310576]
  Large language models (LLMs) exhibit overconfidence, assigning high confidence scores to incorrect predictions.<n>We introduce FineCE, a novel confidence estimation method that delivers accurate, fine-grained confidence scores during text generation.<n>Our code and all baselines used in the paper are available on GitHub.
  arXiv  Detail & Related papers  (2025-08-16T13:29:35Z)
• Deliberative Searcher: Improving LLM Reliability via Reinforcement Learning with constraints [18.10515528600634]
  We propose textbfDeliberative Searcher, the first framework to integrate certainty calibration with retrieval-based search for open-domain question answering.<n>The agent performs multi-step reflection and verification over Wikipedia data and is trained with a reinforcement learning algorithm that optimize for accuracy under a soft reliability constraint.
  arXiv  Detail & Related papers  (2025-07-22T16:09:34Z)
• Aligning Large Language Models for Faithful Integrity Against Opposing Argument [71.33552795870544]
  Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks.<n>They can be easily misled by unfaithful arguments during conversations, even when their original statements are correct.<n>We propose a novel framework, named Alignment for Faithful Integrity with Confidence Estimation.
  arXiv  Detail & Related papers  (2025-01-02T16:38:21Z)
• Large Language Model Confidence Estimation via Black-Box Access [30.490207799344333]
  We explore the problem of estimating confidence for responses of large language models (LLMs) with simply black-box or query access to them.<n>We propose a simple and generalize framework where, we engineer novel features and train a (interpretable) model (viz. logistic regression) on these features to estimate the confidence.<n>We empirically demonstrate that our simple framework is effective in estimating confidence of Flan-ul2,-13b, Mistral-7b and GPT-4 on four benchmark Q&A tasks as well as Pegasus-large and BART-large on two benchmark summarization tasks.
  arXiv  Detail & Related papers  (2024-06-01T02:08:44Z)
• Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models [14.5291643644017]
  We introduce the concept of Confidence-Probability Alignment. We probe the alignment between models' internal and expressed confidence. Among the models analyzed, OpenAI's GPT-4 showed the strongest confidence-probability alignment.
  arXiv  Detail & Related papers  (2024-05-25T15:42:04Z)
• More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness [24.843692458375436]
  This study investigates how models aligned with general-purpose preference data perform across five trustworthiness verticals.<n>Our results demonstrate that RLHF on human preferences doesn't automatically guarantee trustworthiness, and reverse effects are often observed.<n>We propose to adapt efficient influence function based data attribution methods to the RLHF setting to better understand the influence of fine-tuning data on individual trustworthiness benchmarks.
  arXiv  Detail & Related papers  (2024-04-29T17:00:53Z)
• When to Trust LLMs: Aligning Confidence with Response Quality [49.371218210305656]
  We propose CONfidence-Quality-ORDer-preserving alignment approach (CONQORD) It integrates quality reward and order-preserving alignment reward functions. Experiments demonstrate that CONQORD significantly improves the alignment performance between confidence and response accuracy.
  arXiv  Detail & Related papers  (2024-04-26T09:42:46Z)
• Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression [109.23761449840222]
  This study conducts the first, thorough evaluation of leading Large Language Models (LLMs) We find that quantization is currently a more effective approach than pruning in achieving efficiency and trustworthiness simultaneously.
  arXiv  Detail & Related papers  (2024-03-18T01:38:19Z)
• Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection [90.71323430635593]
  We propose a novel self-detection paradigm that considers the comprehensive answer space beyond LLM-generated answers. Building upon this paradigm, we introduce a two-step framework, which firstly instructs LLM to reflect and provide justifications for each candidate answer. This framework can be seamlessly integrated with existing approaches for superior self-detection.
  arXiv  Detail & Related papers  (2024-03-15T02:38:26Z)
• Prompting GPT-3 To Be Reliable [117.23966502293796]
  This work decomposes reliability into four facets: generalizability, fairness, calibration, and factuality. We find that GPT-3 outperforms smaller-scale supervised models by large margins on all these facets.
  arXiv  Detail & Related papers  (2022-10-17T14:52:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.