83 citations · 190 across the 20 of their papers we have counts for
21 papers
When History Misleads: Asymmetric Margin Supervision for Instruction-Guided LLM Generative Recommendation
Ming Yin, Yuhan Yang, Chen Chen +10
In instruction-guided generative recommendation, LLM-based recommenders need to balance two goals: responding to the user's current request and aligning with the preferences in the…
EvoHarness-RL: Learning Runtime Harness Coordination for Self-Evolving Agents
Xuying Ning, Dongqi Fu, Tianxin Wei +17
Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, recover from failures, and reuse experience across extended interactions.…
Intuition-Guided Latent Reasoning for LLM-Based Recommendation
Chang Liu, Yimeng Bai, Xiaoyan Zhao +4
Large Language Models (LLMs) have demonstrated impressive reasoning capabilities in complex problem-solving tasks, motivating their use for preference reasoning in recommender syst…
Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning
Tianyuan Shi, Canbin Huang, Bei Li +4
Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferring what to answer rather th…
When Model Merging Breaks Routing: Training-Free Calibration for MoE
Canbin Huang, Tianyuan Shi, Xiaojun Quan +3
Model merging has emerged as a cost-effective approach for consolidating the capabilities of multiple LLMs without retraining. However, existing merging techniques, largely based o…
SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems
Yangbo Wei, Zhen Huang, Shaoqiang Lu +4
LLM agents increasingly store capabilities in external skill and tool libraries. Libraries can grow, but execution must fit a finite context window and improvement consumes a finit…
DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts
Jiarui Feng, Hanqing Zeng, Karish Grover +11
Mixture-of-Experts (MoE) models have become a leading approach for decoupling parameter count from computational cost in large language models, yet effectively scaling MoE performa…
Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders
Wentao Shi, Qifan Wang, Chen Chen +7
Reinforcement learning (RL) effectively optimizes Large Language Model (LLM)-based recommenders by contrasting positive and negative items. Empirically, training with beam-search n…
Bringing Reasoning to Generative Recommendation Through the Lens of Cascaded Ranking
Xinyu Lin, Pengyuan Liu, Wenjie Wang +5
Generative Recommendation (GR) has become a promising end-to-end approach with high FLOPS utilization for resource-efficient recommendation. Despite the effectiveness, we show that…
TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards
Xiqiao Xiong, Ouxiang Li, Zhuo Liu +5
Large language models have seen widespread adoption, yet they remain vulnerable to multi-turn jailbreak attacks, threatening their safe deployment. This has led to the task of trai…
K-order Ranking Preference Optimization for Large Language Models
Shihao Cai, Chongming Gao, Yang Zhang +5
To adapt large language models (LLMs) to ranking tasks, existing list-wise methods, represented by list-wise Direct Preference Optimization (DPO), focus on optimizing partial-order…
Assistant-Guided Mitigation of Teacher Preference Bias in LLM-as-a-Judge
Zhuo Liu, Moxin Li, Xun Deng +2
LLM-as-a-Judge employs large language models (LLMs), such as GPT-4, to evaluate the quality of LLM-generated responses, gaining popularity for its cost-effectiveness and strong ali…
Reason4Rec: Deliberative User Preference Alignment of Large Language Models for Recommendation
Yi Fang, Wenjie Wang, Yang Zhang +4
Aligning Large Language Models (LLMs) with recommendation tasks represents an emerging paradigm in recommendation domain, exhibiting promising performance overall. However, these a…
Agentic Feedback Loop Modeling Improves Recommendation and User Simulation
Shihao Cai, Jizhi Zhang, Keqin Bao +4
Large language model-based agents are increasingly applied in the recommendation field due to their extensive knowledge and strong planning capabilities. While prior research has p…
Direct Multi-Turn Preference Optimization for Language Agents
Wentao Shi, Mengqi Yuan, Junkang Wu +2
Adapting Large Language Models (LLMs) for agent tasks is critical in developing language agents. Direct Preference Optimization (DPO) is a promising technique for this adaptation w…
CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG
Boyi Deng, Wenjie Wang, Fengbin Zhu +2
Retrieval-Augmented Generation (RAG) can alleviate hallucinations of Large Language Models (LLMs) by referencing external documents. However, the misinformation in external documen…
Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection
Moxin Li, Wenjie Wang, Fuli Feng +3
Self-detection for Large Language Models (LLMs) seeks to evaluate the trustworthiness of the LLM's output by leveraging its own capabilities, thereby alleviating the issue of outpu…
Attack Prompt Generation for Red Teaming and Defending Large Language Models
Boyi Deng, Wenjie Wang, Fuli Feng +3
Large language models (LLMs) are susceptible to red teaming attacks, which can induce LLMs to generate harmful content. Previous research constructs attack prompts via manual or au…
Should Graph Convolution Trust Neighbors? A Simple Causal Inference Method
Fuli Feng, Weiran Huang, Xiangnan He +3
Graph Convolutional Network (GCN) is an emerging technique for information retrieval (IR) applications. While GCN assumes the homophily property of a graph, real-world graphs are n…
CatGCN: Graph Convolutional Networks with Categorical Node Features
Weijian Chen, Fuli Feng, Qifan Wang +4
Recent studies on Graph Convolutional Networks (GCNs) reveal that the initial node representations (i.e., the node representations before the first-time graph convolution) largely…
Graph Convolution Machine for Context-aware Recommender System
Jiancan Wu, Xiangnan He, Xiang Wang +4
The latest advance in recommendation shows that better user and item representations can be learned via performing graph convolutions on the user-item interaction graph. However, s…