SALA: Semantic-Aware Logical Alignment for Complex Reasoning in In-Context Learning

• URL: http://arxiv.org/abs/2609.02336v1
• Date: Wed, 02 Sep 2026 09:12:03 GMT
• Title: SALA: Semantic-Aware Logical Alignment for Complex Reasoning in In-Context Learning
• Abstract summary: We propose SALA, a Semantic-Aware Logical Alignment framework.<n>Instead of relying on a fixed inventory, SALA automatically learns task-specific reasoning operations.<n>It then embeds these operations into a continuous semantic space and uses dynamic time warping to align the reasoning sequences.
• Score: 61.13104919370034
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Effective in-context learning (ICL) for complex reasoning relies on selecting the right demonstrations. Traditional retrieval methods based on surface similarity fail to capture the underlying problem-solving logic. Recent logic-based methods address this by matching predefined reasoning steps, but the rigid rules and exact-match criteria is improper to handle flexible or diverse reasoning processes. To address the problem, we propose SALA, a Semantic-Aware Logical Alignment framework. Instead of relying on a fixed inventory, SALA automatically learns task-specific reasoning operations. It then embeds these operations into a continuous semantic space and uses dynamic time warping (DTW) to align the reasoning sequences. This approach allows for soft, flexible matching of reasoning logic while remaining highly interpretable. Experiments across four reasoning benchmarks and three LLMs demonstrate that SALA outperforms existing demonstration selection methods. Further analysis confirms the roles of the operation induction and the logical semantic alignment.

Related papers

• Semiotic logical hexagon theory for LLM logical reasoning [15.42414269675365]
  We investigate how semantic organization influences logical reasoning in large language models (LLMs)<n>We propose HexLogicAgent, a framework that first organizes the meaning of natural-language statements and then guides logical reasoning through structured verification.<n> Experiments on challenging logical reasoning benchmarks demonstrate that HexLogicAgent consistently improves reasoning reliability across multiple LLMs.
  arXiv  Detail & Related papers  (2026-07-24T03:10:34Z)
• Discovering a Shared Logical Subspace: Steering LLM Logical Reasoning via Alignment of Natural-Language and Symbolic Views [16.869958532486258]
  Large Language Models (LLMs) still struggle with multi-step logical reasoning.<n>We ask whether LLMs contain a shared internal logical subspace that simultaneously aligns natural-language and symbolic-language views.
  arXiv  Detail & Related papers  (2026-04-21T17:42:54Z)
• Process In-Context Learning: Enhancing Mathematical Reasoning via Dynamic Demonstration Insertion [11.708864769915857]
  We propose Process In-Context Learning (PICL) to boost mathematical reasoning by responding to real-time inference needs.<n>PICL operates in two stages: 1)it identifies potential confusion points by analyzing semantics and entropy in the reasoning process and summarizes their core characteristics.<n>It retrieves relevant demonstrations from the demonstration pool that match the confusion context and inserts them directly into the ongoing reasoning process to guide subsequent steps.
  arXiv  Detail & Related papers  (2026-01-17T09:20:06Z)
• 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)
• Order Doesn't Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation [57.570754504160305]
  We introduce an order-centric data augmentation framework based on commutativity in logical reasoning.<n>By leveraging order-centric augmentations, models can develop a more flexible and generalized reasoning process.
  arXiv  Detail & Related papers  (2025-02-27T09:25:50Z)
• LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning [74.0242521818214]
  This paper systematically investigates the comparative dynamics of inductive (System 1) versus abductive/deductive (System 2) inference in large language models (LLMs)<n>We utilize a controlled analogical reasoning environment, varying modality (textual, visual, symbolic), difficulty, and task format (MCQ / free-text)<n>Our analysis reveals System 2 pipelines generally excel, particularly in visual/symbolic modalities and harder tasks, while System 1 is competitive for textual and easier problems.
  arXiv  Detail & Related papers  (2025-02-16T15:54:53Z)
• FSLI: An Interpretable Formal Semantic System for One-Dimensional Ordering Inference [0.9048611509540079]
  We develop a system for solving logical deduction one-dimensional ordering problems.<n>It transforms natural language premises and candidate statements into first-order logic.<n>It achieves 100% accuracy on BIGbench's logical deduction task and 88% on a syntactically simplified subset of AR-LSAT.
  arXiv  Detail & Related papers  (2025-02-12T13:58:42Z)
• H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables [56.73919743039263]
  This paper introduces a novel algorithm that integrates both symbolic and semantic (textual) approaches in a two-stage process to address limitations.<n>Our experiments demonstrate that H-STAR significantly outperforms state-of-the-art methods across three question-answering (QA) and fact-verification datasets.
  arXiv  Detail & Related papers  (2024-06-29T21:24:19Z)
• Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities [31.728976421529577]
  We investigate the contrast across abstract and contextualized logical problems from a comprehensive set of domains. We focus on standard propositional logic, specifically propositional deductive and abductive logic reasoning. Our experiments aim to provide insights into disentangling context in logical reasoning and the true reasoning capabilities of LLMs.
  arXiv  Detail & Related papers  (2024-06-04T21:25:06Z)
• Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning [74.90592233107712]
  We propose a Direct-Indirect Reasoning (DIR) method, which considers Direct Reasoning (DR) and Indirect Reasoning (IR) as multiple parallel reasoning paths that are merged to derive the final answer.<n>Our DIR method is simple yet effective and can be straightforwardly integrated with existing variants of CoT methods.
  arXiv  Detail & Related papers  (2024-02-06T03:41:12Z)
• 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)
• OPERA:Operation-Pivoted Discrete Reasoning over Text [33.36388276371693]
  OPERA is an operation-pivoted discrete reasoning framework for machine reading comprehension. It uses lightweight symbolic operations as neural modules to facilitate the reasoning ability and interpretability. Experiments on both DROP and RACENum datasets show the reasoning ability of OPERA.
  arXiv  Detail & Related papers  (2022-04-29T15:41:47Z)

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.