3 papers
cs.AI2026
PULSE: Identifying Demonstration-Utility Features with Sparse Autoencoders
Chenduo Hao, Chuanbao Gao, Pinjun Zeng +4
In-context learning is highly sensitive to demonstration choice, yet most methods select demonstrations using external query-demonstration similarity. Such criteria can miss model-…
cs.CL2026
Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions
Boyu Shi, Chang Liu, ChuanBao Gao +2
Layer pruning efficiently reduces Large Language Model (LLM) computational costs but often triggers sudden performance collapse. Existing representation-based analyses struggle to…
cs.CL2023
Feature Representation Learning for NL2SQL Generation Based on Coupling and Decoupling
Chenduo Hao, Xu Zhang, Chuanbao Gao +1
The NL2SQL task involves parsing natural language statements into SQL queries. While most state-of-the-art methods treat NL2SQL as a slot-filling task and use feature representatio…