1 citations · 1 across the 12 of their papers we have counts for
13 papers
Cog-Rethinker: Hierarchical Metacognitive Reinforcement Learning for LLM Reasoning
Zexu Sun, Yongcheng Zeng, Erxue Min +3
Contemporary progress in large language models (LLMs) has revealed notable inferential capacities via reinforcement learning (RL) employing verifiable reward, facilitating the deve…
Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents
Heyang Gao, Zexu Sun, Erxue Min +4
Large Language Models (LLMs) as autonomous agents are increasingly tasked with solving complex, long-horizon problems. Aligning these agents via preference-based offline methods li…
CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs
Yongcheng Zeng, Zexu Sun, Bokai Ji +7
Curriculum learning plays a crucial role in enhancing the training efficiency of large language models (LLMs) on reasoning tasks. However, existing methods often fail to adequately…
Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding
Ziheng Li, Zexu Sun, Jinman Zhao +8
Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs). However, existing RLV…
A Question Answering Dataset for Temporal-Sensitive Retrieval-Augmented Generation
Ziyang Chen, Erxue Min, Xiang Zhao +7
We introduce ChronoQA, a large-scale benchmark dataset for Chinese question answering, specifically designed to evaluate temporal reasoning in Retrieval-Augmented Generation (RAG)…
CTR-Guided Generative Query Suggestion in Conversational Search
Erxue Min, Hsiu-Yuan Huang, Xihong Yang +7
Generating effective query suggestions in conversational search requires aligning model outputs with user preferences, which is challenging due to sparse and noisy click signals. W…
From Prompting to Alignment: A Generative Framework for Query Recommendation
Erxue Min, Hsiu-Yuan Huang, Xihong Yang +7
In modern search systems, search engines often suggest relevant queries to users through various panels or components, helping refine their information needs. Traditionally, these…
Hgformer: Hyperbolic Graph Transformer for Recommendation
Xin Yang, Xingrun Li, Heng Chang +8
The cold start problem is a challenging problem faced by most modern recommender systems. By leveraging knowledge from other domains, cross-domain recommendation can be an effectiv…
LLMs + Persona-Plug = Personalized LLMs
Jiongnan Liu, Yutao Zhu, Shuting Wang +6
Personalization plays a critical role in numerous language tasks and applications, since users with the same requirements may prefer diverse outputs based on their individual inter…
Selective Preference Optimization via Token-Level Reward Function Estimation
Kailai Yang, Zhiwei Liu, Qianqian Xie +3
Recent advancements in large language model alignment leverage token-level supervisions to perform fine-grained preference optimization. However, existing token-level alignment met…
DaRec: A Disentangled Alignment Framework for Large Language Model and Recommender System
Xihong Yang, Heming Jing, Zixing Zhang +10
Benefiting from the strong reasoning capabilities, Large language models (LLMs) have demonstrated remarkable performance in recommender systems. Various efforts have been made to d…
Hyperbolic Knowledge Transfer in Cross-Domain Recommendation System
Xin Yang, Heng Chang, Zhijian Lai +6
Cross-Domain Recommendation (CDR) seeks to utilize knowledge from different domains to alleviate the problem of data sparsity in the target recommendation domain, and it has been g…
Neighbour Interaction based Click-Through Rate Prediction via Graph-masked Transformer
Erxue Min, Yu Rong, Tingyang Xu +6
Click-Through Rate (CTR) prediction, which aims to estimate the probability that a user will click an item, is an essential component of online advertising. Existing methods mainly…