8 papers
Towards Fast Domain Adaptation and Fine-Grained User Simulation for Evaluating Conversational Recommender Systems
Yuanzi Li, Quanyu Dai, Xueyang Feng +5
Conversational Recommender Systems (CRSs) enhance user experience through multi-turn interactions, yet evaluating their performance remains challenging. While Large Language Model…
ARCO: Adaptive Rubrics with Co-Evolution for Multi-Step LLM-Based Agents
Zihang Tian, Jingsen Zhang, Rui Li +3
Reinforcement learning for multi-step LLM agents often relies on scalar rewards that indicate success but cannot explain why a trajectory is good or bad. Rubric-based rewards impro…
Divergence Meets Consensus: A Multi-Source Negative Sampling Framework for Sequential Recommendation
Yuanzi Li, Lingjie Wang, Jingyu Zhao +4
Negative sampling is significant for training sequential recommendation models under implicit feedback. The predominant strategy, self-guided hard negative sampling, selects negati…
Prompt and Parameter Co-Optimization for Large Language Models
Xiaohe Bo, Rui Li, Zexu Sun +5
Prompt optimization and fine-tuning are two major approaches to improve the performance of Large Language Models (LLMs). They enhance the capabilities of LLMs from complementary pe…
HAPS: Hierarchical LLM Routing with Joint Architecture and Parameter Search
Zihang Tian, Rui Li, Jingsen Zhang +3
Large language model (LLM) routing aims to exploit the specialized strengths of different LLMs for diverse tasks. However, existing approaches typically focus on selecting LLM arch…
CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension
Rui Li, Zeyu Zhang, Xiaohe Bo +5
Current Large Language Models (LLMs) are confronted with overwhelming information volume when comprehending long-form documents. This challenge raises the imperative of a cohesive…