Self-Training Large Language Models with Confident Reasoning

• URL: http://arxiv.org/abs/2505.17454v1
• Date: Fri, 23 May 2025 04:25:10 GMT
• Title: Self-Training Large Language Models with Confident Reasoning
• Authors: Hyosoon Jang, Yunhui Jang, Sungjae Lee, Jungseul Ok, Sungsoo Ahn,
• Abstract summary: Large language models (LLMs) have shown impressive performance by generating reasoning paths before final answers.<n>We propose a new self-training method, CORE-PO, that fine-tunes LLMs to prefer high-COnfidence REasoning paths through Policy Optimization.<n>Our experiments show that CORE-PO improves the accuracy of outputs on four in-distribution and two out-of-distribution benchmarks, compared to existing self-training methods.
• Score: 15.260831996769962
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have shown impressive performance by generating reasoning paths before final answers, but learning such a reasoning path requires costly human supervision. To address this issue, recent studies have explored self-training methods that improve reasoning capabilities using pseudo-labels generated by the LLMs themselves. Among these, confidence-based self-training fine-tunes LLMs to prefer reasoning paths with high-confidence answers, where confidence is estimated via majority voting. However, such methods exclusively focus on the quality of the final answer and may ignore the quality of the reasoning paths, as even an incorrect reasoning path leads to a correct answer by chance. Instead, we advocate the use of reasoning-level confidence to identify high-quality reasoning paths for self-training, supported by our empirical observations. We then propose a new self-training method, CORE-PO, that fine-tunes LLMs to prefer high-COnfidence REasoning paths through Policy Optimization. Our experiments show that CORE-PO improves the accuracy of outputs on four in-distribution and two out-of-distribution benchmarks, compared to existing self-training methods.

Related papers

• Post-Training Large Language Models via Reinforcement Learning from Self-Feedback [3.73824942136665]
  Large Language Models (LLMs) often produce plausible but poorly-calibrated answers.<n>We present Reinforcement Learning from Self-Feedback (RLSF), a post-training stage that uses the model's own confidence as an intrinsic reward.
  arXiv  Detail & Related papers  (2025-07-29T15:46:26Z)
• Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning [87.7836502955847]
  We propose a novel self-rewarding reinforcement learning framework to enhance Large Language Model (LLM) reasoning.<n>Our key insight is that correct responses often exhibit consistent trajectory patterns in terms of model likelihood.<n>We introduce CoVo, an intrinsic reward mechanism that integrates Consistency and Volatility via a robust vector-space aggregation strategy.
  arXiv  Detail & Related papers  (2025-06-10T12:40:39Z)
• Can Large Reasoning Models Self-Train? [58.953117118687096]
  Scaling the performance of large language models increasingly depends on methods that reduce reliance on human supervision.<n>We propose an online self-training reinforcement learning algorithm that leverages the model's self-consistency to infer correctness signals and train without any ground-truth supervision.
  arXiv  Detail & Related papers  (2025-05-27T17:16:00Z)
• Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique [66.94905631175209]
  We propose a novel inference-time scaling approach -- stepwise natural language self-critique (PANEL)<n>It employs self-generated natural language critiques as feedback to guide the step-level search process.<n>This approach bypasses the need for task-specific verifiers and the associated training overhead.
  arXiv  Detail & Related papers  (2025-03-21T17:59:55Z)
• R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization [86.32257216965229]
  We propose a new online reinforcement learning framework that enables MLLMs to self-improve reasoning ability via simple, effective and dense step-wise rewarding.<n>StepGRPO introduces two novel rule-based reasoning rewards: Step-wise Reasoning Accuracy Reward (StepRAR) and Step-wise Reasoning Validity Reward (StepRVR)<n>With the proposed StepGRPO, we introduce R1-VL, a series of MLLMs with outstanding capabilities in step-by-step reasoning.
  arXiv  Detail & Related papers  (2025-03-17T08:51:44Z)
• Scalable Best-of-N Selection for Large Language Models via Self-Certainty [65.31658824274894]
  Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models.<n>We propose self-certainty, a novel and efficient metric to estimate response quality without requiring external reward models.<n>Our findings establish self-certainty as a practical and efficient way for improving LLM reasoning capabilities.
  arXiv  Detail & Related papers  (2025-02-25T19:08:07Z)
• Confidence Improves Self-Consistency in LLMs [9.764747744761085]
  We introduce Confidence-Informed Self-Consistency (CISC)<n>CISC performs a weighted majority vote based on confidence scores obtained directly from the model.<n>When tested on nine models and four datasets, CISC outperforms self-consistency in nearly all configurations.
  arXiv  Detail & Related papers  (2025-02-10T08:10:29Z)
• Lachesis: Predicting LLM Inference Accuracy using Structural Properties of Reasoning Paths [12.377041655669728]
  We introduce Lachesis, a predictive model for self-consistency based LLM inferences.<n>We empirically evaluate it using AutoFL, a recently proposed LLM-based fault localisation technique.<n>Results suggest that Lachesis can predict the correctness of answers with a precision of up to 0.8136.
  arXiv  Detail & Related papers  (2024-12-11T10:56:47Z)
• Self-Improvement in Language Models: The Sharpening Mechanism [70.9248553790022]
  We offer a new perspective on the capabilities of self-improvement through a lens we refer to as sharpening.<n>Motivated by the observation that language models are often better at verifying response quality than they are at generating correct responses, we formalize self-improvement as using the model itself as a verifier during post-training.<n>We analyze two natural families of self-improvement algorithms based on SFT and RLHF.
  arXiv  Detail & Related papers  (2024-12-02T20:24:17Z)
• Self-Training Meets Consistency: Improving LLMs' Reasoning with Consistency-Driven Rationale Evaluation [15.124701883286436]
  Self-training approach for large language models (LLMs) improves reasoning abilities by training the models on their self-generated rationales.<n>Previous approaches have labeled rationales that produce correct answers for a given question as appropriate for training.<n>We propose CREST (Consistency-driven Rationale Evaluation for Self-Training), a self-training framework that further evaluates each rationale through follow-up questions.
  arXiv  Detail & Related papers  (2024-11-10T08:11:05Z)
• ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement [70.09541267910974]
  Post-training Large Language Models (LLMs) with explicit reasoning trajectories can enhance their reasoning abilities.<n>Existing self-synthesizing methods suffer from poor generalization to out-of-domain (OOD) reasoning tasks.<n>We propose Reasoning Generalist via Self-Improvement (ReGenesis), a method to self-synthesize reasoning paths as post-training data.
  arXiv  Detail & Related papers  (2024-10-03T00:09:15Z)
• SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales [29.33581578047835]
  SaySelf is a training framework that teaches large language models to express more accurate fine-grained confidence estimates. In addition, SaySelf directs LLMs to produce self-reflective rationales that clearly identify gaps in their parametric knowledge. We show that the generated self-reflective rationales are reasonable and can further contribute to the calibration.
  arXiv  Detail & Related papers  (2024-05-31T16:21:16Z)

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.