Efficient Post-Training Refinement of Latent Reasoning in Large Language Models

• URL: http://arxiv.org/abs/2506.08552v1
• Date: Tue, 10 Jun 2025 08:17:16 GMT
• Title: Efficient Post-Training Refinement of Latent Reasoning in Large Language Models
• Authors: Xinyuan Wang, Dongjie Wang, Wangyang Ying, Haoyue Bai, Nanxu Gong, Sixun Dong, Kunpeng Liu, Yanjie Fu,
• Abstract summary: Chain-of-Thought prompting suffers from sufficient token overhead and a fixed reasoning trajectory, preventing step-wise refinement.<n>Recent advances in latent reasoning address these limitations by refining internal reasoning processes directly in the model's latent space.<n>We propose a lightweight post-training framework that refines latent reasoning trajectories using two novel strategies.
• Score: 22.878147805601706
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reasoning is a key component of language understanding in Large Language Models. While Chain-of-Thought prompting enhances performance via explicit intermediate steps, it suffers from sufficient token overhead and a fixed reasoning trajectory, preventing step-wise refinement. Recent advances in latent reasoning address these limitations by refining internal reasoning processes directly in the model's latent space, without producing explicit outputs. However, a key challenge remains: how to effectively update reasoning embeddings during post-training to guide the model toward more accurate solutions. To overcome this challenge, we propose a lightweight post-training framework that refines latent reasoning trajectories using two novel strategies: 1) Contrastive reasoning feedback, which compares reasoning embeddings against strong and weak baselines to infer effective update directions via embedding enhancement; 2) Residual embedding refinement, which stabilizes updates by progressively integrating current and historical gradients, enabling fast yet controlled convergence. Extensive experiments and case studies are conducted on five reasoning benchmarks to demonstrate the effectiveness of the proposed framework. Notably, a 5\% accuracy gain on MathQA without additional training.

Related papers

• LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization [48.91511514636768]
  We present Length-Adaptive Policy Optimization (LAPO), a framework that transforms reasoning length control from an external constraint into an intrinsic model capability.<n>LAPO enables models to internalize an understanding of appropriate reasoning depth through a two-stage reinforcement learning process.<n> Experiments on mathematical reasoning benchmarks demonstrate that LAPO reduces token usage by up to 40.9% while improving accuracy by 2.3%.
  arXiv  Detail & Related papers  (2025-07-21T16:14:41Z)
• CTRLS: Chain-of-Thought Reasoning via Latent State-Transition [57.51370433303236]
  Chain-of-thought (CoT) reasoning enables large language models to break down complex problems into interpretable intermediate steps.<n>We introduce groundingS, a framework that formulates CoT reasoning as a Markov decision process (MDP) with latent state transitions.<n>We show improvements in reasoning accuracy, diversity, and exploration efficiency across benchmark reasoning tasks.
  arXiv  Detail & Related papers  (2025-07-10T21:32:18Z)
• ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation [53.149817480019834]
  Recent advancements in large reasoning models (LRMs) have achieved notable performance enhancements on complex reasoning tasks by scaling up the generation length by Chain-of-Thought (CoT)<n>We propose a framework dubbed ConciseHint, which continuously encourages the reasoning model to speak concisely by injecting the textual hint during the token generation of the reasoning process.<n>Experiments on the state-of-the-art LRMs, including DeepSeek-R1 and Qwen-3 series, demonstrate that our method can effectively produce concise reasoning processes while maintaining performance well.
  arXiv  Detail & Related papers  (2025-06-23T16:20:44Z)
• SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought [37.53215651690168]
  Chain of Thought (CoT) prompting improves the reasoning performance of large language models (LLMs) by encouraging step by step thinking.<n>While promising, CoT-based approaches often require costly pretraining and lack a principled framework for how reasoning should evolve.<n>We propose SCOUT, a lightweight fine tuning framework that enables Flow CoT style reasoning without the need for pretraining.
  arXiv  Detail & Related papers  (2025-05-30T03:43:24Z)
• Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens [51.90059610606049]
  This paper revisits the efficiency of such reasoning processes through an information-theoretic lens.<n>We propose two metrics, InfoBias and InfoGain, to quantify divergence from ideal reasoning paths and stepwise information contribution.<n>Motivated by these findings, we introduce an entropy-based Adaptive Think strategy that dynamically halts reasoning once confidence is sufficiently high.
  arXiv  Detail & Related papers  (2025-05-23T13:38:56Z)
• Short-Path Prompting in LLMs: Analyzing Reasoning Instability and Solutions for Robust Performance [33.16322104912836]
  Large language models' (LLMs) reasoning is largely due to the chain-of-thought (CoT) approaches.<n>LLMs are instruction-tuned to provide long and detailed CoT pathways when responding to reasoning-related questions.<n>Human beings are naturally cognitive misers and will prompt language models to give rather short responses.
  arXiv  Detail & Related papers  (2025-04-13T14:12:14Z)
• Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models [54.04678363287392]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks.<n>Recent advancements in OpenAI o1 and DeepSeek-R1 have further improved performance in System-2 reasoning domains.
  arXiv  Detail & Related papers  (2025-03-20T17:59:38Z)
• Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback [94.25162866972077]
  Step-KTO is a training framework that combines process-level and outcome-level binary feedback.<n>Our experiments show that Step-KTO significantly improves both final answer accuracy and the quality of intermediate reasoning steps.
  arXiv  Detail & Related papers  (2025-01-18T15:38:03Z)
• Verbosity-Aware Rationale Reduction: Effective Reduction of Redundant Rationale via Principled Criteria [18.612187958340407]
  Large Language Models (LLMs) rely on generating extensive intermediate reasoning units (e.g., tokens, sentences) to enhance final answer quality.<n>Previous methods adopting token-level reduction without clear criteria result in poor performance compared to models trained with complete rationale.<n>We propose a novel sentence-level rationale reduction framework leveraging likelihood-based criteria, verbosity, to identify and remove redundant reasoning sentences.
  arXiv  Detail & Related papers  (2024-12-30T15:15:08Z)
• Rethinking Chain-of-Thought from the Perspective of Self-Training [10.722453877596998]
  Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent capabilities in LLMs.<n>We propose a novel CoT framework to improve reasoning performance.<n>Our framework integrates two key components: (i) a task-specific prompt module that optimize the initial reasoning process, and (ii) an adaptive reasoning module that dynamically refines the reasoning process.
  arXiv  Detail & Related papers  (2024-12-14T13:12:50Z)
• Think Beyond Size: Adaptive Prompting for More Effective Reasoning [0.0]
  We introduce Adaptive Prompting, a dynamic and iterative framework designed to enhance reasoning by incorporating real-time adjustments to prompt structures and validation mechanisms.<n>Results demonstrate that Adaptive Prompting significantly improves performance on diverse reasoning benchmarks, including arithmetic reasoning (GSM8K, MultiArithm), logical reasoning and commonsense tasks.<n>Our approach enables smaller models to achieve competitive performance with larger counterparts, such as GPT-4, while maintaining computational efficiency.
  arXiv  Detail & Related papers  (2024-10-10T17:14:36Z)
• Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing [61.98556945939045]
  We propose a framework to learn planning-based reasoning through Direct Preference Optimization (DPO) on collected trajectories. Our results on challenging logical reasoning benchmarks demonstrate the effectiveness of our learning framework.
  arXiv  Detail & Related papers  (2024-02-01T15:18:33Z)

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.