Publications (28)
Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models
Chao Xue, Yao Wang, Mengqiao Liu +11
Supervised Fine-Tuning (SFT) is the standard approach for adapting large language models (LLMs) to downstream tasks. However, we observe a persistent failure mode: even after conve…
TRACE: Discovering Task-Specific Parameter via Adaptation-Aware Probing for Continual Fine-Tuning
Xiaosong Han, Ke Chen, Xindi Dai +7
In real-world deployment, LLMs are often adapted continually across tasks to keep LLMs up-to-date in production, where new fine-tuning should preserve previously learned skills. Ho…
RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction
Jun Zhao, Wenyu Zhan, Xin Zhao +6
Semantic matching is a mainstream paradigm of zero-shot relation extraction, which matches a given input with a corresponding label description. The entities in the input should ex…
Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance
Yao Wang, Di Liang, Minlong Peng
Supervised fine-tuning (SFT) is a pivotal approach to adapting large language models (LLMs) for downstream tasks; however, performance often suffers from the ``seesaw phenomenon'',…
Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis
Xinhao Yao, Yuanzhuo Liu, Changhao Wang +6
Deep search is becoming a core capability of modern agent systems, yet it is typically evaluated solely based on end-to-end answer accuracy. This coupled evaluation paradigm entang…
Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis
Minlong Peng, Qi Zhang, Xuanjing Huang
Cross-domain sentiment analysis is currently a hot topic in the research and engineering areas. One of the most popular frameworks in this field is the domain-invariant representat…