5 citations · 6 across the 12 of their papers we have counts for
13 papers
Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning
Tian Xu, Zexuan Chen, Zhilong Zhang +4
Adversarial imitation learning (AIL) achieves high-quality imitation compared to behavioral cloning (BC), but demands substantial online environment interaction. Recent empirical w…
CECOR: Correction-oriented synthetic data construction for factual error correction
Lei Zhu, Xiaobao Wang, Jianbiao Yang +4
Factual Error Correction (FEC) aims to revise inaccurate text into statements that are factually consistent with external evidence. Although recent methods perform well on single-h…
Graph-GRPO: Dependency-Aware Credit Assignment for Generative E-commerce Search Relevance
Jiarui Che, Yifei Chen, Zhixing Tian +2
Search relevance modeling is a core task in e-commerce search systems, assessing how well a user query matches candidate products. Rather than relying on a single holistic matching…
K-CARE: Knowledge-driven Symmetrical Contextual Anchoring and Analogical Prototype Reasoning for E-commerce Relevance
Chen Yifei, Tian Zhixing, Wang Chenyang +1
This paper targets e-commerce search relevance. While Large Language Models (LLMs) have demonstrated significant potential in this field, they often encounter performance bottlenec…
Off-Policy Value-Based Reinforcement Learning for Large Language Models
Peng-Yuan Wang, Ziniu Li, Tian Xu +8
Improving data utilization efficiency is critical for scaling reinforcement learning (RL) for long-horizon tasks where generating trajectories is expensive. However, the dominant R…
Non-Adversarial Imitation Learning Provably Free of Compounding Errors: The Value Flow Mechanism
Tian Xu, Chenyang Wang, Xiaochen Zhai +3
Adversarial imitation learning (AIL) achieves high-quality imitation by mitigating compounding errors inherent to behavioral cloning (BC), yet its adversarial optimization frequent…
Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following
Chenyang Wang, Liang Wen, Shousheng Jia +2
While advancements in the reasoning abilities of LLMs have significantly enhanced their performance in solving mathematical problems, coding tasks, and general puzzles, their effec…
Integration of Old and New Knowledge for Generalized Intent Discovery: A Consistency-driven Prototype-Prompting Framework
Xiao Wei, Xiaobao Wang, Ning Zhuang +3
Intent detection aims to identify user intents from natural language inputs, where supervised methods rely heavily on labeled in-domain (IND) data and struggle with out-of-domain (…
A Survey on Large Language Models for Mathematical Reasoning
Peng-Yuan Wang, Tian-Shuo Liu, Chenyang Wang +8
Mathematical reasoning has long represented one of the most fundamental and challenging frontiers in artificial intelligence research. In recent years, large language models (LLMs)…
SeedBench: A Multi-task Benchmark for Evaluating Large Language Models in Seed Science
Jie Ying, Zihong Chen, Zhefan Wang +7
Seed science is essential for modern agriculture, directly influencing crop yields and global food security. However, challenges such as interdisciplinary complexity and high costs…
PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models
Shi Qiu, Shaoyang Guo, Zhuo-Yang Song +51
Current benchmarks for evaluating the reasoning capabilities of Large Language Models (LLMs) face significant limitations: task oversimplification, data contamination, and flawed e…
LREF: A Novel LLM-based Relevance Framework for E-commerce
Tian Tang, Zhixing Tian, Zhenyu Zhu +5
Query and product relevance prediction is a critical component for ensuring a smooth user experience in e-commerce search. Traditional studies mainly focus on BERT-based models to…
Consistency of Responses and Continuations Generated by Large Language Models on Social Media
Wentao Xu, Wenlu Fan, Yuqi Zhu +1
Large Language Models (LLMs) demonstrate remarkable capabilities in text generation, yet their emotional consistency and semantic coherence in social media contexts remain insuffic…