9 papers
When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration
Yaxin Gong, Gangyi Zhang, Chongming Gao +7
Multi-agent LLM systems rely on message passing among specialized agents to accomplish complex tasks. However, an upstream agent may provide useful information or an incorrect answ…
Beyond Verbalized Confidence: Calibrating Reasoners with Differentiable Readouts
Chenxiao Fan, Chongming Gao, Gangyi Zhang +8
Reinforcement learning with verifiable rewards (RLVR) trains reasoning models to produce correct answers, but does not ensure that their stated confidence is calibrated. The result…
Trustworthy Recommendation in the Era of Large Language Models: Opportunities and Challenges
Bohao Wang, Yu Cui, Zhenxiang Xu +13
The field of recommender systems (RS) is currently undergoing two profound paradigm shifts. From the perspective of objectives, the goal has shifted beyond mere recommendation accu…
Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation
Jiaju Chen, Chongming Gao, Chenxiao Fan +4
Large language model (LLM)-based generative list-wise recommendation has advanced rapidly, but decoding remains sequential and thus latency-prone. To accelerate inference without c…
Breaking User-Centric Agency: A Tri-Party Framework for Agent-Based Recommendation
Yaxin Gong, Chongming Gao, Chenxiao Fan +6
Large language models (LLMs) have spurred interest in agent-based recommender systems, yet most agentic approaches remain user-centric: items stay passive entities whose exposure i…
Uncertainty-aware Generative Recommendation
Chenxiao Fan, Chongming Gao, Yaxin Gong +3
Generative Recommendation has emerged as a transformative paradigm, reformulating recommendation as an end-to-end autoregressive sequence generation task. Despite its promise, exis…
Fine-grained List-wise Alignment for Generative Medication Recommendation
Chenxiao Fan, Chongming Gao, Wentao Shi +3
Accurate and safe medication recommendations are critical for effective clinical decision-making, especially in multimorbidity cases. However, existing systems rely on point-wise p…
Process-Supervised LLM Recommenders via Flow-guided Tuning
Chongming Gao, Mengyao Gao, Chenxiao Fan +3
While large language models (LLMs) are increasingly adapted for recommendation systems via supervised fine-tuning (SFT), this approach amplifies popularity bias due to its likeliho…
Fine-grained Alignment of Large Language Models for General Medication Recommendation without Overprescription
Zihao Zhao, Chenxiao Fan, Junlong Liu +5
Large language models (LLMs) holds significant promise in achieving general medication recommendation systems owing to their comprehensive interpretation of clinical notes and flex…