Haoyu Wang

LLMs Can Generate a Better Answer by Aggregating Their Own Responses

AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play

Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration

Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing

Towards Federated RLHF with Aggregated Client Preference for LLMs

Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning

Neat: Nonlinear Parameter-efficient Adaptation of Pre-trained Models