SALA：面向上下文学习中复杂推理的语义感知逻辑对齐框架
SALA: Semantic-Aware Logical Alignment for Complex Reasoning in In-Context Learning
浏览论文内容
中文总结 AI 辅助
针对上下文学习中传统示例选择方法无法捕捉推理逻辑、刚性逻辑方法适配性差的问题，提出SALA框架，通过自动学习任务特定推理操作并结合动态时间规整实现灵活可解释的逻辑对齐，在多基准和多LLM上性能优于现有方法。
中文摘要 AI 辅助
面向复杂推理的有效上下文学习（ICL）依赖于合适示例的选择。传统基于表面相似度的检索方法无法捕捉底层解题逻辑；近期基于逻辑的方法通过匹配预定义推理步骤解决该问题，但刚性规则与精确匹配标准难以处理灵活或多样的推理过程。为解决此问题，本文提出SALA，即语义感知逻辑对齐框架。SALA不依赖固定库存，而是自动学习任务特定的推理操作，随后将这些操作嵌入连续语义空间，并使用动态时间规整（DTW）对推理序列进行对齐。该方法可实现推理逻辑的软、灵活匹配，同时保持高可解释性。在四个推理基准和三个大语言模型（LLM）上开展的实验表明，SALA的性能优于现有示例选择方法；进一步分析证实了操作归纳和逻辑语义对齐的作用。
英文摘要
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.
发表机构
- School of Software Engineering, Sun Yat-sen University（中山大学软件工程学院）
- School of Artificial Intelligence, Sun Yat-sen University（中山大学人工智能学院）
- Merchants Union Consumer Finance Company Limited（招商局联融消费金融股份有限公司）
机构由 AI 辅助整理，请以论文原文为准。
