Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Structural Rationale Distillation via Reasoning Space Compression
Jialin Yang, Jiankun Wang, Jiajun Wu +3
When distilling reasoning from large language models (LLMs) into smaller ones, teacher rationales for similar problems often vary wildly in structure and strategy. Like a chef who…
cs.CL2024
Dynamic Uncertainty Ranking: Enhancing Retrieval-Augmented In-Context Learning for Long-Tail Knowledge in LLMs
Shuyang Yu, Runxue Bao, Parminder Bhatia +3
Large language models (LLMs) can learn vast amounts of knowledge from diverse domains during pre-training. However, long-tail knowledge from specialized domains is often scarce and…