7 papers
EHR-Complex: Benchmarking Medical Agents for Complex Clinical Reasoning
Yitong Qiao, Lei Liu, Yue Shen +4
Clinical agents promise to democratize access to electronic health records (EHRs), yet existing benchmarks fail to reflect the complexity of practical EHR analysis, e.g., often ope…
SpaMEM: Benchmarking Dynamic Spatial Reasoning via Perception-Memory Integration in Embodied Environments
Chih-Ting Liao, Xi Xiao, Chunlei Meng +6
Multimodal large language models (MLLMs) have advanced static visual--spatial reasoning, yet they often fail to preserve long-horizon spatial coherence in embodied settings where b…
Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning
Zhikai Pan, Chih-Ting Liao, Chunrui Liu +5
Whether large language models (LLMs) construct internal spatial world models from pure-text descriptions remains contested, and whether such capabilities transfer across languages…
Increasing Computation Resolves Conflicts in Vision Language Models
Bingyang Wang, Yijiang Li, Yitong Qiao +7
Cognitive control, the ability to coordinate competing information sources in pursuit of goals, is fundamental to intelligent behavior. We systematically investigate whether Vision…
Lowest Span Confidence: A Zero-Shot Metric for Efficient and Black-Box Hallucination Detection in LLMs
Yitong Qiao, Licheng Pan, Yu Mi +4
Hallucinations in Large Language Models (LLMs), i.e., the tendency to generate plausible but non-factual content, pose a significant challenge for their reliable deployment in high…
Blind Spot Navigation: Evolutionary Discovery of Sensitive Semantic Concepts for LVLMs
Zihao Pan, Yu Tong, Weibin Wu +6
Adversarial attacks aim to generate malicious inputs that mislead deep models, but beyond causing model failure, they cannot provide certain interpretable information such as ``\te…