5 papers
C-Cite: Contextual-Aware Citation Generation for Attributed Large Language Models
Yue Yu, Ting Bai, HengZhi Lan +6
The attribution technique enhances the credibility of LLMs by adding citations to the generated sentences, enabling users to trace back to the original sources and verify the relia…
GMoE: Empowering LLMs Fine-Tuning via MoE Graph Collaboration
Ting Bai, Yue Yu, Le Huang +2
The sparse Mixture-of-Experts (MoE) architecture of large language models (LLMs) confronts an inherent issue of load imbalance arising from the simplistic linear router strategy, w…
KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models
Weijie Chen, Ting Bai, Jinbo Su +3
Large language models with retrieval-augmented generation encounter a pivotal challenge in intricate retrieval tasks, e.g., multi-hop question answering, which requires the model t…
Invariant debiasing learning for recommendation via biased imputation
Ting Bai, Weijie Chen, Cheng Yang +1
Previous debiasing studies utilize unbiased data to make supervision of model training. They suffer from the high trial risks and experimental costs to obtain unbiased data. Recent…
Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrieval
Le Huang, Hengzhi Lan, Zijun Sun +2
As LLMs exhibit a high degree of human-like capability, increasing attention has been paid to role-playing research areas in which responses generated by LLMs are expected to mimic…