SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

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 the

Read original source ↗ Open in workspace

recordType

paper

region

Global