SEAL: Steerable Reasoning Calibration of Large Language Models for Free

• URL: http://arxiv.org/abs/2504.07986v3
• Date: Sat, 25 Oct 2025 03:17:22 GMT
• Title: SEAL: Steerable Reasoning Calibration of Large Language Models for Free
• Authors: Runjin Chen, Zhenyu Zhang, Junyuan Hong, Souvik Kundu, Zhangyang Wang,
• Abstract summary: Large Language Models (LLMs) have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism.<n>Recent studies reveal substantial redundancy in the CoT reasoning traces, which negatively impacts model performance.<n>We introduce SEAL, a training-free approach that seamlessly calibrates the CoT process, improving accuracy while demonstrating significant efficiency gains.
• Score: 58.931194824519935
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs), such as OpenAI's o1-series have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism. However, recent studies reveal substantial redundancy in the CoT reasoning traces, which not only increases inference latency but also negatively impacts model performance by diverting attention to unnecessary reasoning paths. To address this issue, we investigate the internal reasoning structures of LLMs and categorize them into three primary thought types: execution, reflection, and transition thoughts. Moreover, our analysis reveals that excessive reflection and transition thoughts are strongly correlated with failure cases and these thought categories exhibit clear separation in the latent space. Based on these, we introduce SEAL (Steerable reasoning calibration), a training-free approach that seamlessly calibrates the CoT process, improving accuracy while demonstrating significant efficiency gains. SEAL consists of an offline stage for extracting the reasoning steering vector in the latent space, followed by an on-the-fly calibration of the reasoning trace through representation intervention using the steering vector. Notably, the steering vector exhibits strong transferability across various tasks. Extensive experiments across multiple models (DeepSeek-R1-Distill and QwQ-32B-Preview) and benchmarks (Math500, GSM8K, LiveCodeBench) validate the effectiveness of SEAL, up to a 11% improvement in accuracy while reducing reasoning tokens by 11.8% to 50.4%. Our code is publicly available at https://github.com/VITA-Group/SEAL.

Related papers

• Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution [79.98699884805636]
  Reasoning Execution by Multiple Listeners (REMUL) is a multi-party reinforcement learning approach.<n>REMUL builds on the hypothesis that reasoning traces which other parties can follow will be more faithful.<n>Speakers are rewarded for producing reasoning that is clear to listeners.
  arXiv  Detail & Related papers  (2026-02-18T02:55:55Z)
• Beyond Correctness: Learning Robust Reasoning via Transfer [51.403609251508904]
  We adopt a simple philosophical view, robust reasoning should remain useful beyond the mind that produced it.<n>We introduce Reinforcement Learning with Transferable Reward, which operationalizes robustness via transfer reward.<n>Our approach improves sampling consistency while improving final answer accuracy, and it reaches comparable performance in substantially fewer training steps.
  arXiv  Detail & Related papers  (2026-02-09T10:41:44Z)
• Internalizing LLM Reasoning via Discovery and Replay of Latent Actions [4.830503861275364]
  Internalization of chain-of-thought processes into hidden states has emerged as a highly efficient paradigm for scaling test-time compute.<n>We propose STIR (Self-Distilled Tools for Internal Reasoning), a framework that reformulates reasoning enhancement as a dynamic latent trajectory control problem.
  arXiv  Detail & Related papers  (2026-02-04T08:44:57Z)
• Identifying and Transferring Reasoning-Critical Neurons: Improving LLM Inference Reliability via Activation Steering [50.63386303357225]
  We propose AdaRAS, a lightweight test-time framework that improves reasoning reliability by selectively intervening on neuron activations.<n>AdaRAS identifies Reasoning-Critical Neurons (RCNs) via a polarity-aware mean-difference criterion and adaptively steers their activations during inference.<n> Experiments on 10 mathematics and coding benchmarks demonstrate consistent improvements, including over 13% gains on AIME-24 and AIME-25.
  arXiv  Detail & Related papers  (2026-01-27T17:53:01Z)
• EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs [9.412828452977553]
  Existing approaches reinforce successful reasoning paths, incurring a substantial calibration cost.<n>This failure has been characterized as a form of model collapse in alignment.<n>We proposeEpiCaR as a training objective that jointly optimize reasoning performance and calibration.
  arXiv  Detail & Related papers  (2026-01-11T06:21:13Z)
• Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization [56.59356959631999]
  Gated Perception-Reasoning Optimization (GPRO) is a meta-reasoning controller that dynamically routes computation among three decision paths.<n>GPRO substantially improves both accuracy and efficiency, outperforming recent slow-thinking methods.
  arXiv  Detail & Related papers  (2026-01-07T23:05:17Z)
• Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time [22.9491443902816]
  We study the structure of reasoning trajectories and uncover specialized attention heads that correlate with distinct cognitive behaviors.<n>We propose CREST, a training-free method for Cognitive REasoning Steering at Test-time.<n>CREST adaptively suppresses unproductive reasoning behaviors, yielding both higher accuracy and lower computational cost.
  arXiv  Detail & Related papers  (2025-12-31T02:46:04Z)
• When Actions Teach You to Think: Reasoning-Action Synergy via Reinforcement Learning in Conversational Agents [2.689316553293938]
  Supervised fine-tuning (SFT) has emerged as one of the most effective ways to improve the performance of large language models (LLMs) in downstream tasks.<n>We propose a pipeline in which LLMs generate reasoning steps that guide both the invocation of tools and the final answer generation for conversational agents.
  arXiv  Detail & Related papers  (2025-12-12T04:44:40Z)
• Efficient Thought Space Exploration through Strategic Intervention [54.35208611253168]
  We propose a novel Hint-Practice Reasoning (HPR) framework that operationalizes this insight through two synergistic components.<n>The framework's core innovation lies in Distributional Inconsistency Reduction (DIR), which dynamically identifies intervention points.<n> Experiments across arithmetic and commonsense reasoning benchmarks demonstrate HPR's state-of-the-art efficiency-accuracy tradeoffs.
  arXiv  Detail & Related papers  (2025-11-13T07:26:01Z)
• Efficient Reasoning for Large Reasoning Language Models via Certainty-Guided Reflection Suppression [30.653381666162275]
  Certainty-Guided Reflection Suppression (CGRS) is a novel method that mitigates overthinking in Large Reasoning Language Models (LRLMs)<n>CGRS operates by dynamically suppressing the model's generation of reflection triggers when it exhibits high confidence in its current response.<n>Our approach is model-agnostic, requires no retraining or architectural modifications, and can be integrated seamlessly with existing autoregressive generation pipelines.
  arXiv  Detail & Related papers  (2025-08-07T12:38:22Z)
• Teaching LLM to Reason: Reinforcement Learning from Algorithmic Problems without Code [76.80306464249217]
  We propose TeaR, which aims at teaching LLMs to reason better.<n>TeaR leverages careful data curation and reinforcement learning to guide models in discovering optimal reasoning paths through code-related tasks.<n>We conduct extensive experiments using two base models and three long-CoT distillation models, with model sizes ranging from 1.5 billion to 32 billion parameters, and across 17 benchmarks spanning Math, Knowledge, Code, and Logical Reasoning.
  arXiv  Detail & Related papers  (2025-07-10T07:34:05Z)
• 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)
• Excessive Reasoning Attack on Reasoning LLMs [26.52688123765127]
  In this work, we expose a novel threat: adversarial inputs can be crafted to exploit excessive reasoning behaviors.<n>Our results demonstrate a 3x to 9x increase in reasoning length with comparable utility performance.<n>Our crafted adversarial inputs exhibit transferability, inducing computational overhead in o3-mini, o1-mini, DeepSeek-R1, and QWQ models.
  arXiv  Detail & Related papers  (2025-06-17T10:16:52Z)
• KG-TRACES: Enhancing Large Language Models with Knowledge Graph-constrained Trajectory Reasoning and Attribution Supervision [8.025866693669622]
  Large language models (LLMs) have made remarkable strides in various natural language processing tasks, but their performance on complex reasoning problems remains hindered by a lack of explainability and trustworthiness.<n>We propose Knowledge Graph-constrained Trajectory Reasoning Attribution and Chain Explanation Supervision (KG-TRACES) to enhance the reasoning ability of LLMs.<n> KG-TRACES jointly supervises the model to: (1) predict symbolic relation paths, (2) predict full triple-level reasoning paths, and (3) generate attribution-aware reasoning processes grounded in the reasoning paths.
  arXiv  Detail & Related papers  (2025-06-01T02:20:45Z)
• Steering LLM Reasoning Through Bias-Only Adaptation [4.486093197820339]
  Reinforcement-learning finetuning does not create new capabilities but strengthens reasoning patterns already latent in the pretrained network.<n>We test this claim by training steering vectors: layer-wise biases that additively amplify selected hidden features.<n>Experiments on four base models across the GSM8K and MATH benchmarks show that steering vectors recover, and in several cases exceed, the accuracy of fully-tuned counterparts.
  arXiv  Detail & Related papers  (2025-05-24T13:55:38Z)
• Fractured Chain-of-Thought Reasoning [61.647243580650446]
  We introduce Fractured Sampling, a unified inference-time strategy that interpolates between full CoT and solution-only sampling.<n>We show that Fractured Sampling consistently achieves superior accuracy-cost trade-offs, yielding steep log-linear scaling gains in Pass@k versus token budget.
  arXiv  Detail & Related papers  (2025-05-19T11:30:41Z)
• Do Reasoning Models Show Better Verbalized Calibration? [19.776645881640178]
  We investigate the calibration properties of LRMs trained via supervised fine-tuning distillation on long reasoning traces.<n>Our findings reveal that LRMs significantly outperform instruction-tuned models on complex reasoning tasks in both accuracy and confidence calibration.<n>Our results provide evidence for a potentially critical role of reasoning-oriented RL training in improving LLMs' capacity for generating trustworthy, self-aware outputs.
  arXiv  Detail & Related papers  (2025-04-09T03:58:19Z)
• ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation [38.64751082999587]
  Large Reasoning Models (LRMs) exhibit remarkable reasoning abilities but rely primarily on parametric knowledge, limiting factual accuracy.<n>We propose ReaRAG, a factuality-enhanced reasoning model that explores diverse queries without excessive iterations.<n>Our study enhances LRMs' factuality while effectively integrating robust reasoning for Retrieval-Augmented Generation (RAG)
  arXiv  Detail & Related papers  (2025-03-27T17:44:18Z)
• GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training [62.536191233049614]
  Reinforcement learning with verifiable outcome rewards (RLVR) has effectively scaled up chain-of-thought (CoT) reasoning in large language models (LLMs)<n>This work investigates this problem through extensive experiments on complex card games, such as 24 points, and embodied tasks from ALFWorld.<n>We find that when rewards are based solely on action outcomes, RL fails to incentivize CoT reasoning in VLMs, instead leading to a phenomenon we termed thought collapse.
  arXiv  Detail & Related papers  (2025-03-11T15:17:02Z)
• R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model [70.77691645678804]
  We present the first successful replication of emergent characteristics for multimodal reasoning on only a non-SFT 2B model.<n>Our model achieves 59.47% accuracy on CVBench, outperforming the base model by approximately 30% and exceeding both SFT setting by 2%.<n>In addition, we share our failed attempts and insights in attempting to achieve R1-like reasoning using RL with instruct models.
  arXiv  Detail & Related papers  (2025-03-07T04:21:47Z)
• Quantifying Logical Consistency in Transformers via Query-Key Alignment [20.636818928993684]
  We propose a novel, lightweight evaluation strategy for logical reasoning.<n>By computing a single forward pass and extracting a "QK-score" from carefully chosen heads, our method reveals latent representations that reliably separate valid from invalid inferences.
  arXiv  Detail & Related papers  (2025-02-24T10:02:50Z)
• Unveiling Reasoning Thresholds in Language Models: Scaling, Fine-Tuning, and Interpretability through Attention Maps [3.8936716676293917]
  This study investigates the in-context learning capabilities of various decoder-only transformer-based language models with different model sizes and training data.<n>We identify a critical parameter threshold (1.6 billion), beyond which reasoning performance improves significantly in tasks such as commonsense reasoning in multiple-choice question answering and deductive reasoning.
  arXiv  Detail & Related papers  (2025-02-21T00:48:32Z)
• Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning [23.99454995087634]
  We explore the potential of rule-based reinforcement learning in large reasoning models.<n>We use synthetic logic puzzles as training data due to their controllable complexity and straightforward answer verification.<n>Our 7B model develops advanced reasoning skills-such as reflection, verification, and summarization-that are absent from the logic corpus.
  arXiv  Detail & Related papers  (2025-02-20T17:49:26Z)
• Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning [65.2421542320293]
  Reasoning abilities are crucial components of general intelligence.<n>Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning tasks.<n>This paper proposes a new RL framework, termed OREAL, to pursue the performance limit that can be achieved through textbfOutcome textbfREwtextbfArd-based reinforcement textbfLearning for mathematical reasoning tasks.
  arXiv  Detail & Related papers  (2025-02-10T18:57:29Z)
• Ladder-of-Thought: Using Knowledge as Steps to Elevate Stance Detection [73.31406286956535]
  We introduce the Ladder-of-Thought (LoT) for the stance detection task. LoT directs the small LMs to assimilate high-quality external knowledge, refining the intermediate rationales produced. Our empirical evaluations underscore LoT's efficacy, marking a 16% improvement over GPT-3.5 and a 10% enhancement compared to GPT-3.5 with CoT on stance detection task.
  arXiv  Detail & Related papers  (2023-08-31T14:31:48Z)
• Self-Evaluation Guided Beam Search for Reasoning [61.523627290397556]
  We introduce a stepwise self-evaluation mechanism to guide and calibrate the reasoning process of Large Language Model (LLM) We propose a decoding algorithm integrating the self-evaluation guidance via beam search. Our approach surpasses the corresponding Codex-backboned baselines in few-shot accuracy by $6.34%$, $9.56%$, and $5.46%$ on the GSM8K, AQuA, and StrategyQA.
  arXiv  Detail & Related papers  (2023-05-01T02:37:59Z)

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.