CORE: Concept-Oriented Reinforcement for Bridging the Definition-Application Gap in Mathematical Reasoning

• URL: http://arxiv.org/abs/2512.18857v1
• Date: Sun, 21 Dec 2025 19:01:35 GMT
• Title: CORE: Concept-Oriented Reinforcement for Bridging the Definition-Application Gap in Mathematical Reasoning
• Authors: Zijun Gao, Zhikun Xu, Xiao Ye, Ben Zhou,
• Abstract summary: Large language models (LLMs) often solve challenging math exercises yet fail to apply the concept right when the problem requires genuine understanding.<n>We introduce CORE (Concept-Oriented REinforcement), an RL training framework that turns explicit concepts into a controllable supervision signal.
• Score: 11.332501212320194
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) often solve challenging math exercises yet fail to apply the concept right when the problem requires genuine understanding. Popular Reinforcement Learning with Verifiable Rewards (RLVR) pipelines reinforce final answers but provide little fine-grained conceptual signal, so models improve at pattern reuse rather than conceptual applications. We introduce CORE (Concept-Oriented REinforcement), an RL training framework that turns explicit concepts into a controllable supervision signal. Starting from a high-quality, low-contamination textbook resource that links verifiable exercises to concise concept descriptions, we run a sanity probe showing LLMs can restate definitions but fail concept-linked quizzes, quantifying the conceptual reasoning gap. CORE then (i) synthesizes concept-aligned quizzes, (ii) injects brief concept snippets during rollouts to elicit concept-primed trajectories, and (iii) reinforces conceptual reasoning via trajectory replacement after group failures, a lightweight forward-KL constraint that aligns unguided with concept-primed policies, or standard GRPO directly on concept-aligned quizzes. Across several models, CORE delivers consistent gains over vanilla and SFT baselines on both in-domain concept-exercise suites and diverse out-of-domain math benchmarks. CORE unifies direct training on concept-aligned quizzes and concept-injected rollouts under outcome regularization. It provides fine-grained conceptual supervision that bridges problem-solving competence and genuine conceptual reasoning, while remaining algorithm- and verifier-agnostic.

Related papers

• Concept Component Analysis: A Principled Approach for Concept Extraction in LLMs [51.378834857406325]
  Mechanistic interpretability seeks to mitigate the issues through extracts from large language models.<n>Sparse autoencoders (SAEs) have emerged as a popular approach for extracting interpretable and monosemantic concepts.<n>We show that SAEs suffer from a fundamental theoretical ambiguity: the well-defined correspondence between LLM representations and human-interpretable concepts remains unclear.
  arXiv  Detail & Related papers  (2026-01-28T09:27:05Z)
• FaCT: Faithful Concept Traces for Explaining Neural Network Decisions [56.796533084868884]
  Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge.<n>We put emphasis on the faithfulness of concept-based explanations and propose a new model with model-inherent mechanistic concept-explanations.<n>Our concepts are shared across classes and, from any layer, their contribution to the logit and their input-visualization can be faithfully traced.
  arXiv  Detail & Related papers  (2025-10-29T13:35:46Z)
• Latent Chain-of-Thought for Visual Reasoning [53.541579327424046]
  Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs)<n>We reformulate reasoning in LVLMs as posterior inference and propose a scalable training algorithm based on amortized variational inference.<n>We empirically demonstrate that the proposed method enhances the state-of-the-art LVLMs on seven reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-10-27T23:10:06Z)
• FACE: Faithful Automatic Concept Extraction [4.417419748257645]
  FACE (Faithful Automatic Concept Extraction) is a novel framework that augments Non-negative Matrix Factorization (NMF) with a Kullback-Leibler (KL) divergence regularization term to ensure alignment between the model's original and concept-based predictions.<n>We provide theoretical guarantees showing that minimizing the KL divergence bounds the deviation in predictive distributions, thereby promoting faithful local linearity in the learned concept space.
  arXiv  Detail & Related papers  (2025-10-13T17:44:45Z)
• Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space [62.54887038032942]
  We introduce Soft Thinking, a training-free method that emulates human-like "soft" reasoning by generating soft, abstract concept tokens.<n>These concept tokens are created by the probability-weighted mixture of token embeddings, which form the continuous concept space.<n>In essence, each generated concept token encapsulates multiple meanings from related discrete tokens, implicitly exploring various reasoning paths to converge.
  arXiv  Detail & Related papers  (2025-05-21T17:29:15Z)
• Zero-shot Concept Bottleneck Models [17.70684428339905]
  Concept bottleneck models (CBMs) are inherently interpretable and intervenable neural network models.<n>We present textitzero-shot concept bottleneck models (Z-CBMs), which predict concepts and labels in a fully zero-shot manner without training neural networks.
  arXiv  Detail & Related papers  (2025-02-13T07:11:07Z)
• On the Diagram of Thought [20.805936414171892]
  Large Language Models (LLMs) excel at many tasks but often falter on complex problems that require structured, multi-step reasoning.<n>We introduce the Diagram of Thought (DoT), a new framework that enables a single LLM to build and navigate a mental map of its reasoning.
  arXiv  Detail & Related papers  (2024-09-16T07:01:41Z)
• Incorporating Expert Rules into Neural Networks in the Framework of Concept-Based Learning [2.9370710299422598]
  It is proposed how to combine logical rules and neural networks predicting the concept probabilities. We provide several approaches for solving the stated problem and for training neural networks. The code of proposed algorithms is publicly available.
  arXiv  Detail & Related papers  (2024-02-22T17:33:49Z)
• Deep Concept Removal [29.65899467379793]
  We address the problem of concept removal in deep neural networks. We propose a novel method based on adversarial linear classifiers trained on a concept dataset. We also introduce an implicit gradient-based technique to tackle the challenges associated with adversarial training.
  arXiv  Detail & Related papers  (2023-10-09T14:31:03Z)
• Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problems [54.26307134687171]
  Raven's Progressive Matrix (RPM) is a classic test to realize such ability in machine intelligence by selecting from candidates. Recent studies suggest that solving RPM in an answer-generation way boosts a more in-depth understanding of rules. We propose a deep latent variable model for Concept-changing Rule ABstraction (CRAB) by learning interpretable concepts and parsing concept-changing rules in the latent space.
  arXiv  Detail & Related papers  (2023-07-15T07:16:38Z)
• Interpretable Neural-Symbolic Concept Reasoning [7.1904050674791185]
  Concept-based models aim to address this issue by learning tasks based on a set of human-understandable concepts. We propose the Deep Concept Reasoner (DCR), the first interpretable concept-based model that builds upon concept embeddings.
  arXiv  Detail & Related papers  (2023-04-27T09:58:15Z)
• Concept Gradient: Concept-based Interpretation Without Linear Assumption [77.96338722483226]
  Concept Activation Vector (CAV) relies on learning a linear relation between some latent representation of a given model and concepts. We proposed Concept Gradient (CG), extending concept-based interpretation beyond linear concept functions. We demonstrated CG outperforms CAV in both toy examples and real world datasets.
  arXiv  Detail & Related papers  (2022-08-31T17:06:46Z)

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.