6 papers
TEXAS: Task-Expert-Aware Supervision for Downstream Mixture-of-Experts LLM Adaptation
Guanzhi Deng, Haibo Wang, Kuan Wu +5
Mixture-of-Experts (MoE) language models route each token through a small subset of experts, making routing patterns useful for identifying task-relevant experts during downstream…
Routing-Aligned Fine-Tuning for Multilingual Downstream Tasks in Mixture-of-Experts Models
Guanzhi Deng, Kuan Wu, Haibo Wang +3
Mixture-of-Experts (MoE) models have emerged as a dominant paradigm for efficient LLM scaling, yet adapting them to non-English downstream tasks remains challenging. Existing fine-…
Integrating Large Language Models into Recommendation via Mutual Augmentation and Adaptive Aggregation
Sichun Luo, Yuxuan Yao, Bowei He +9
Conventional recommendation methods have achieved notable advancements by harnessing collaborative or sequential information from user behavior. Recently, large language models (LL…
Reasoning Meets Personalization: Unleashing the Potential of Large Reasoning Model for Personalized Generation
Sichun Luo, Guanzhi Deng, Jian Xu +3
Personalization is a critical task in modern intelligent systems, with applications spanning diverse domains, including interactions with large language models (LLMs). Recent advan…
RALLRec+: Retrieval Augmented Large Language Model Recommendation with Reasoning
Sichun Luo, Jian Xu, Xiaojie Zhang +4
Large Language Models (LLMs) have been integrated into recommender systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further inc…
Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling
Yuxuan Yao, Han Wu, Mingyang Liu +5
Large language models (LLMs) exhibit varying strengths and weaknesses across different tasks, prompting recent studies to explore the benefits of ensembling models to leverage thei…