Grounded Chess Reasoning in Language Models via Master Distillation

• URL: http://arxiv.org/abs/2603.20510v1
• Date: Fri, 20 Mar 2026 21:24:28 GMT
• Title: Grounded Chess Reasoning in Language Models via Master Distillation
• Abstract summary: Language models often lack grounded reasoning capabilities in specialized domains where training data is scarce but bespoke systems excel.<n>We introduce a general framework for distilling expert system reasoning into natural language chain-of-thought explanations.<n>We demonstrate this approach in chess, a canonical reasoning domain where language models continue to underperform.
• Score: 9.280187120219724
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language models often lack grounded reasoning capabilities in specialized domains where training data is scarce but bespoke systems excel. We introduce a general framework for distilling expert system reasoning into natural language chain-of-thought explanations, enabling compact models to acquire domain expertise and the ability to generate faithful, grounded explanations. Rather than distilling only final outputs, we capture the full reasoning process, transforming opaque expert computations into transparent, step-by-step explanations. We demonstrate this approach in chess, a canonical reasoning domain where language models continue to underperform. Our 4B parameter model, C1, advances from a near-zero baseline to 48.1% accuracy, outperforming all open-source models and most frontier proprietary systems. Notably, C1 surpasses its distillation teacher and generates solutions in two orders of magnitude fewer tokens than baselines. Unlike prior neural chess approaches that predict only best moves, C1 generates explainable solutions revealing strategic reasoning. Our pipeline combines supervised fine-tuning and reinforcement learning with theme-balanced data sampling for comprehensive tactical coverage. Master Distillation demonstrates how to inject expert-level knowledge into compact models for under-optimized domains, offering a recipe for unlocking RLVR where LLMs lack sufficient base capabilities.

Related papers

• The Regularizing Power of Language-Training Deepfake Detectors [57.529452351298495]
  Deepfake detection generally suffers from overfitting to low-level domain-specific artifacts.<n>We use a dual-encoder architecture, pairing a frozen specialist detector with a LoRA-tuned MLLM encoder.<n>We employ a reinforcement learning stage that encourages the model to generate descriptive reasoning before classifying.
  arXiv  Detail & Related papers  (2026-05-29T12:01:17Z)
• AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution [61.593935260052795]
  Post-training viaSupervised Fine-Tuning (SFT) and Reinforcement Learning (RL) is crucial for enhancing reasoning in Multimodal Large Language Models (MLLMs)<n>Existing paradigms often reach a performance bottleneck due to the limitations of static data.<n>We propose Anchor Evolution (AnE), a new paradigm that integrates truth-anchored data curation and model evolution.
  arXiv  Detail & Related papers  (2026-05-25T08:26:34Z)
• Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion [84.20493238687187]
  We introduce a novel framework that moves beyond simple mimicry to instill a deeper conceptual understanding.<n>underlinetextitFirst, to address pattern memorization, Explanatory Inversion (EI) generates targeted explanatory probes''<n>underlinetextitSecond, to improve generalization, Explanatory GRPO (texttEXGRPO) uses a reinforcement learning algorithm with a novel Dialogue Structure Utility Bonus.
  arXiv  Detail & Related papers  (2026-02-26T23:01:46Z)
• On-Policy Context Distillation for Language Models [92.82835176360864]
  We propose On-Policy Context Distillation (OPCD), a framework that bridges on-policy distillation with context distillation.<n>We demonstrate the effectiveness of OPCD on two important applications: experiential knowledge distillation and system prompt distillation.
  arXiv  Detail & Related papers  (2026-02-12T18:58:28Z)
• Large Language Model enabled Mathematical Modeling [2.132096006921049]
  This research investigates the potential of Large Language Models (LLMs) to bridge the formulation gap using natural language understanding and code generation.<n>DeepSeek-R1 is a cost-efficient and high-performing model trained with reinforcement learning.<n>Our methodology includes baseline assessments, the development of a hallucination taxonomy, and the application of mitigation strategies.
  arXiv  Detail & Related papers  (2025-10-22T17:41:42Z)
• Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning [51.92313556418432]
  Supervised fine-tuning (SFT) plays a critical role for pretrained large language models (LLMs)<n>We suggest categorizing tokens within each corpus into two parts -- positive and negative tokens -- based on whether they are useful to improve model performance.<n>We conduct experiments on well-established benchmarks, finding that this forgetting mechanism not only improves overall model performance and also facilitate more diverse model responses.
  arXiv  Detail & Related papers  (2025-08-06T11:22:23Z)
• ReasonBridge: Efficient Reasoning Transfer from Closed to Open-Source Language Models [1.125423117145132]
  This paper introduces ReasonBridge, a methodology that efficiently transfers reasoning capabilities from powerful closed-source to open-source models.<n>We develop a tailored dataset Reason1K with only 1,000 carefully curated reasoning traces emphasizing difficulty, diversity, and quality.<n> Comprehensive evaluations demonstrate that ReasonBridge improves reasoning capabilities in open-source models by up to 23% on benchmark tasks.
  arXiv  Detail & Related papers  (2025-06-28T12:22:55Z)
• I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders [8.1201445044499]
  Internal mechanisms behind reasoning in LLMs remain unexplored.<n>We employ Sparse Autoencoders to test our hypothesis.<n>Our work provides the first step towards a mechanistic understanding of reasoning in LLMs.
  arXiv  Detail & Related papers  (2025-03-24T16:54:26Z)
• Bayesian Prompt Learning for Image-Language Model Generalization [64.50204877434878]
  We use the regularization ability of Bayesian methods to frame prompt learning as a variational inference problem. Our approach regularizes the prompt space, reduces overfitting to the seen prompts and improves the prompt generalization on unseen prompts. We demonstrate empirically on 15 benchmarks that Bayesian prompt learning provides an appropriate coverage of the prompt space.
  arXiv  Detail & Related papers  (2022-10-05T17:05:56Z)
• Explaining a Series of Models by Propagating Local Feature Attributions [9.66840768820136]
  Pipelines involving several machine learning models improve performance in many domains but are difficult to understand. We introduce a framework to propagate local feature attributions through complex pipelines of models based on a connection to the Shapley value. Our framework enables us to draw higher-level conclusions based on groups of gene expression features for Alzheimer's and breast cancer histologic grade prediction.
  arXiv  Detail & Related papers  (2021-04-30T22:20:58Z)
• Self-Feature Regularization: Self-Feature Distillation Without Teacher Models [0.0]
  Self-Feature Regularization(SFR) is proposed, which uses features in the deep layers to supervise feature learning in the shallow layers. We firstly use generalization-l2 loss to match local features and a many-to-one approach to distill more intensively in the channel dimension.
  arXiv  Detail & Related papers  (2021-03-12T15:29:00Z)
• Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge [96.92252296244233]
  Large pre-trained language models (LMs) acquire some reasoning capacity, but this ability is difficult to control. We show that LMs can be trained to reliably perform systematic reasoning combining both implicit, pre-trained knowledge and explicit natural language statements. Our work paves a path towards open-domain systems that constantly improve by interacting with users who can instantly correct a model by adding simple natural language statements.
  arXiv  Detail & Related papers  (2020-06-11T17:02:20Z)

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.