7 papers
From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment
Hao Chen, Qi Zhang, Liyao Li +7
Adapting Large Language Models (LLMs) to specialized domains typically incurs high data and computational overhead. While prior efficiency efforts have largely treated data selecti…
Can LLMs Act as Historians? Evaluating Historical Research Capabilities of LLMs via the Chinese Imperial Examination
Lirong Gao, Zeqing Wang, Yuyan Cai +6
While Large Language Models (LLMs) have increasingly assisted in historical tasks such as text processing, their capacity for professional-level historical reasoning remains undere…
Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty
Zewei Yu, Lirong Gao, Yuke Zhu +4
Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex reasoning tasks by employing test-time scaling. However, they often generate over-long chains-of-t…
ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models
Hao Chen, Haoze Li, Zhiqing Xiao +6
Aligning general-purpose large language models (LLMs) to downstream tasks often incurs significant training adjustment costs. Prior research has explored various avenues to enhance…
FLoE: Fisher-Based Layer Selection for Efficient Sparse Adaptation of Low-Rank Experts
Xinyi Wang, Lirong Gao, Haobo Wang +2
Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a widely adopted strategy for adapting pre-trained Large Language Models (LLMs) to downstream tasks, significantly re…
LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization
Qi Zhang, Shouqing Yang, Lirong Gao +8
Large language models (LLMs) have demonstrated impressive capabilities in reasoning with the emergence of reasoning models like OpenAI-o1 and DeepSeek-R1. Recent research focuses o…