most citedMedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs

2 citations · 2 across the 7 of their papers we have counts for

collaborators

11 papers

cs.CL2026

RATE: Reviewer Profiling and Annotation-free Training for Expertise Ranking in Peer Review Systems

Weicong Liu, Zixuan Yang, Yibo Zhao +1

Reviewer assignment is increasingly critical yet challenging in the LLM era, where rapid topic shifts render many pre-2023 benchmarks outdated and where proxy signals poorly reflec…

cs.CV2025

ChartAgent: A Chart Understanding Framework with Tool Integrated Reasoning

Boran Wang, Xinming Wang, Yi Chen +4

With their high information density and intuitive readability, charts have become the de facto medium for data analysis and communication across disciplines. Recent multimodal larg…

cs.CL2025

Think Globally, Group Locally: Evaluating LLMs Using Multi-Lingual Word Grouping Games

César Guerra-Solano, Zhuochun Li, Xiang Lorraine Li

Large language models (LLMs) can exhibit biases in reasoning capabilities due to linguistic modality, performing better on tasks in one language versus another, even with similar c…

cs.AI2025

RoRecomp: Enhancing Reasoning Efficiency via Rollout Response Recomposition in Reinforcement Learning

Gang Li, Yulei Qin, Xiaoyu Tan +6

Reinforcement learning with verifiable rewards (RLVR) has proven effective in eliciting complex reasoning in large language models (LLMs). However, standard RLVR training often lea…

cs.CL2025

MMBERT: Scaled Mixture-of-Experts Multimodal BERT for Robust Chinese Hate Speech Detection under Cloaking Perturbations

Qiyao Xue, Yuchen Dou, Ryan Shi +2

Hate speech detection on Chinese social networks presents distinct challenges, particularly due to the widespread use of cloaking techniques designed to evade conventional text-bas…

cs.CV2025

VideoMultiAgents: A Multi-Agent Framework for Video Question Answering

Noriyuki Kugo, Xiang Li, Zixin Li +9

Video Question Answering (VQA) inherently relies on multimodal reasoning, integrating visual, temporal, and linguistic cues to achieve a deeper understanding of video content. Howe…