3 papers
cs.LG2026
Toward Robust Open-set Adaptation: Synapse Consolidation Inspired by Rac1/MAPK Pathways
Xiao Zhang, Tianyu Hu, Juntao Lyu +2
Large Language Models (LLMs) generalize across tasks through reusable representations and flexible reasoning, yet remain brittle in real deployment when faced with evolving tasks a…
cs.CL2025
Efficient Knowledge Transfer in Multi-Task Learning through Task-Adaptive Low-Rank Representation
Xiao Zhang, Kangsheng Wang, Tianyu Hu +1
Pre-trained language models (PLMs) demonstrate remarkable intelligence but struggle with emerging tasks unseen during training in real-world applications. Training separate models…
cs.CL2025
CSCE: Boosting LLM Reasoning by Simultaneous Enhancing of Causal Significance and Consistency
Kangsheng Wang, Xiao Zhang, Juntao Lyu +2
Chain-based reasoning methods like chain of thought (CoT) play a rising role in solving reasoning tasks for large language models (LLMs). However, the causal hallucinations between…