一作ACL 2026Findings· Findings of ACL
Beyond Templates: Dynamic Adaptation of Reasoning Demonstrations via Feasibility-Aware Exploration
Yong Wu · Weihang Pan · Ke Li · Chen Binhui · Ping Li · Binbin Lin
摘要
Large language models (LLMs) have shown remarkable reasoning capabilities, yet aligning such abilities to small language models (SLMs) remains a challenge due to distributional mismatches and limited model capacity. Existing reasoning datasets, typically designed for powerful LLMs, often lead to...