1 citations · 2 across the 12 of their papers we have counts for
10 papers · 1 filter
Beyond Imitation: Reflective On-Policy Self-Distillation for LLM Reasoning
Ziqi Zhao, Xinyu Ma, Liu Yang +6
On-policy self-distillation (OPSD) improves the reasoning capabilities of large language models (LLMs) by providing dense token-level supervision for on-policy rollouts. However, e…
Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models
Yujie Feng, Jian Li, Zhihan Zhou +7
Large Language Models (LLMs) achieve impressive performance across many tasks but remain prone to hallucination, especially in long-form generation where redundant retrieved contex…
AIMMerging: Adaptive Iterative Model Merging Using Training Trajectories for Language Model Continual Learning
Yujie Feng, Jian Li, Xiaoyu Dong +8
Continual learning (CL) is essential for deploying large language models (LLMs) in dynamic real-world environments without the need for costly retraining. Recent model merging-base…
GeoEdit: Geometric Knowledge Editing for Large Language Models
Yujie Feng, Liming Zhan, Zexin Lu +6
Regular updates are essential for maintaining up-to-date knowledge in large language models (LLMs). Consequently, various model editing methods have been developed to update specif…
Understanding Layer Significance in LLM Alignment
Guangyuan Shi, Zexin Lu, Xiaoyu Dong +4
Aligning large language models (LLMs) through supervised fine-tuning is essential for tailoring them to specific applications. Recent studies suggest that alignment primarily adjus…
Diversity-grounded Channel Prototypical Learning for Out-of-Distribution Intent Detection
Bo Liu, Liming Zhan, Yujie Feng +5
In the realm of task-oriented dialogue systems, a robust intent detection mechanism must effectively handle malformed utterances encountered in real-world scenarios. This study pre…
TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation
Yujie Feng, Xu Chu, Yongxin Xu +3
A practical dialogue system requires the capacity for ongoing skill acquisition and adaptability to new tasks while preserving prior knowledge. However, current methods for Continu…
Continual Dialogue State Tracking via Reason-of-Select Distillation
Yujie Feng, Bo Liu, Xiaoyu Dong +4
An ideal dialogue system requires continuous skill acquisition and adaptation to new tasks while retaining prior knowledge. Dialogue State Tracking (DST), vital in these systems, o…
KIF: Knowledge Identification and Fusion for Language Model Continual Learning
Yujie Feng, Xu Chu, Yongxin Xu +4
Language model continual learning (CL) has recently attracted significant interest for its ability to adapt large language models (LLMs) to dynamic real-world scenarios without ret…
Towards LLM-driven Dialogue State Tracking
Yujie Feng, Zexin Lu, Bo Liu +2
Dialogue State Tracking (DST) is of paramount importance in ensuring accurate tracking of user goals and system actions within task-oriented dialogue systems. The emergence of larg…