Decoupling Understanding from Reasoning via Problem Space Mapping for Small-scale Model Reasoning

• URL: http://arxiv.org/abs/2508.10019v1
• Date: Thu, 07 Aug 2025 01:13:30 GMT
• Title: Decoupling Understanding from Reasoning via Problem Space Mapping for Small-scale Model Reasoning
• Authors: Li Wang, Changhao Zhang, Zengqi Xiu, Kai Lu, Xin Yu, Kui Zhang, Wenjun Wu,
• Abstract summary: We propose a new framework that decouples understanding from reasoning by mapping natural language problems into a canonical problem space.<n>Within this framework, we introduce DURIT, a three-step algorithm that iteratively aligns reasoning trajectories through self-distillation.<n>Experiments show that DURIT substantially improves SLMs' performance on both in-domain and out-of-domain mathematical and logical reasoning tasks.
• Score: 22.582715282848795
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite recent advances in the reasoning capabilities of Large Language Models (LLMs), improving the reasoning ability of Small Language Models (SLMs, e.g., $\leq$ 1.5B) remains challenging. A key obstacle lies in the complexity and variability of natural language: essentially equivalent problems often appear in diverse surface forms, often obscured by redundant or distracting details. This imposes a dual burden on SLMs: they must first extract the core problem from complex linguistic input, and then perform reasoning based on that understanding. The resulting vast and noisy problem space hinders optimization, particularly for models with limited capacity. To address this, we propose a new framework that decouples understanding from reasoning by mapping natural language problems into a canonical problem space-a semantically simplified yet expressive domain. This enables SLMs to focus on reasoning over standardized inputs, free from linguistic variability. Within this framework, we introduce DURIT (Decoupled Understanding from Reasoning via Iterative Training), a three-step algorithm that iteratively: (1) mapping natural language problems via reinforcement learning, (2) aligns reasoning trajectories through self-distillation, and (3) trains reasoning policies in the problem space. The mapper and reasoner are co-trained in an alternating loop throughout this process. Experiments show that DURIT substantially improves SLMs' performance on both in-domain and out-of-domain mathematical and logical reasoning tasks. Beyond improving reasoning capabilities, DURIT also improves the robustness of reasoning, validating decoupling understanding from reasoning as an effective strategy for strengthening SLMs.

Related papers

• Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction [57.67217258741752]
  Thinker is a hierarchical thinking model for deep search through multi-turn interaction.<n>It decomposes complex problems into independently solvable sub-problems.<n> dependencies between sub-problems are passed as parameters via these logical functions.
  arXiv  Detail & Related papers  (2025-11-11T07:48:45Z)
• ReaLM: Reflection-Enhanced Autonomous Reasoning with Small Language Models [76.28894983518164]
  Small Language Models (SLMs) are a cost-effective alternative to Large Language Models (LLMs)<n>They often struggle with complex reasoning due to their limited capacity and a tendency to produce mistakes or inconsistent answers.<n>We introduce ReaLM, a reinforcement learning framework for robust and self-sufficient reasoning in vertical domains.
  arXiv  Detail & Related papers  (2025-08-17T14:50:23Z)
• Learning to Reason via Mixture-of-Thought for Logical Reasoning [56.24256916896427]
  Mixture-of-Thought (MoT) is a framework that enables LLMs to reason across three complementary modalities: natural language, code, and truth-table.<n>MoT adopts a two-phase design: (1) self-evolving MoT training, which jointly learns from filtered, self-generated rationales across modalities; and (2) MoT inference, which fully leverages the synergy of three modalities to produce better predictions.
  arXiv  Detail & Related papers  (2025-05-21T17:59:54Z)
• LINGOLY-TOO: Disentangling Reasoning from Knowledge with Templatised Orthographic Obfuscation [1.2576388595811496]
  We introduce LINGOLY-TOO, a challenging reasoning benchmark grounded in natural language.<n>We permute reasoning problems written in real languages to generate numerous question variations.<n>Experiments and analyses show that models can circumvent reasoning and answer from prior knowledge.
  arXiv  Detail & Related papers  (2025-03-04T19:57:47Z)
• General Intelligence Requires Reward-based Pretraining [19.90997698310839]
  Large Language Models (LLMs) have demonstrated impressive real-world utility.<n>But their ability to reason adaptively and robustly remains fragile.<n>We propose disangling knowledge and reasoning through three key directions.
  arXiv  Detail & Related papers  (2025-02-26T18:51:12Z)
• Large Language Models and Mathematical Reasoning Failures [1.6114012813668932]
  This paper investigates the mathematical reasoning capabilities of large language models (LLMs) using 50 newly constructed high-school-level word problems.<n>We rigorously analyze both final answers and solution steps to identify reasoning failures.<n>We find that while newer models (e.g., o3-mini, deepseek-r1) achieve higher accuracy, all models exhibit errors in spatial reasoning, strategic planning, and arithmetic.
  arXiv  Detail & Related papers  (2025-02-17T09:07:32Z)
• Language Models can be Logical Solvers [99.40649402395725]
  We introduce LoGiPT, a novel language model that directly emulates the reasoning processes of logical solvers. LoGiPT is fine-tuned on a newly constructed instruction-tuning dataset derived from revealing and refining the invisible reasoning process of deductive solvers.
  arXiv  Detail & Related papers  (2023-11-10T16:23:50Z)
• From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning [66.98861219674039]
  Heuristic-Analytic Reasoning (HAR) strategies drastically improve the coherence of rationalizations for model decisions. Our findings suggest that human-like reasoning strategies can effectively improve the coherence and reliability of PLM reasoning.
  arXiv  Detail & Related papers  (2023-10-24T19:46:04Z)
• Re-Reading Improves Reasoning in Large Language Models [87.46256176508376]
  We introduce a simple, yet general and effective prompting method, Re2, to enhance the reasoning capabilities of off-the-shelf Large Language Models (LLMs) Unlike most thought-eliciting prompting methods, such as Chain-of-Thought (CoT), Re2 shifts the focus to the input by processing questions twice, thereby enhancing the understanding process. We evaluate Re2 on extensive reasoning benchmarks across 14 datasets, spanning 112 experiments, to validate its effectiveness and generality.
  arXiv  Detail & Related papers  (2023-09-12T14:36:23Z)
• ChatABL: Abductive Learning via Natural Language Interaction with ChatGPT [72.83383437501577]
  Large language models (LLMs) have recently demonstrated significant potential in mathematical abilities. LLMs currently have difficulty in bridging perception, language understanding and reasoning capabilities. This paper presents a novel method for integrating LLMs into the abductive learning framework.
  arXiv  Detail & Related papers  (2023-04-21T16:23:47Z)
• Faithful Reasoning Using Large Language Models [12.132449274592668]
  We show how LMs can be made to perform faithful multi-step reasoning via a process whose causal structure mirrors the underlying logical structure of the problem. Our approach works by chaining together reasoning steps, where each step results from calls to two fine-tuned LMs. We demonstrate the effectiveness of our model on multi-step logical deduction and scientific question-answering, showing that it outperforms baselines on final answer accuracy.
  arXiv  Detail & Related papers  (2022-08-30T13:44:41Z)

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.