3 papers
cs.LG2026
MixFormer: Linear Transformer with Mixture of Memory Experts
Yu Guo, Lei Duan
State Space Models (SSMs), as a mainstream research direction of linear Transformers, aim to achieve higher efficiency than standard Transformers in long-context modeling. However,…
cs.CL2025
Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs
Shuyuan Lin, Lei Duan, Philip Hughes +1
Conversational Information Retrieval (CIR) systems, while offering intuitive access to information, face a significant challenge: reliably handling unanswerable questions to preven…
cs.CL2025
DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism
Dengchun Li, Naizheng Wang, Zihao Zhang +4
Instruction-based fine-tuning of large language models (LLMs) has achieved remarkable success in various natural language processing (NLP) tasks. Parameter-efficient fine-tuning (P…