7 papers · 1 filter
PropUQ-MAS: Propagation-Aware Uncertainty Quantification for LLM Multi-Agent Systems
Yaokun Liu, Yifan Liu, Daniel Yue Zhang +3
LLM-based multi-agent systems (MAS) solve complex tasks through communication among role-specialized agents. However, inter-agent dependencies introduce reliability risks beyond is…
Beyond Truth Discovery: A Two-Stage Framework to Assess the Severity of False Claim during Disasters
Ruichen Yao, Tejna Dasari, Gulshat Baispay +5
False information spreads rapidly on social media during disasters and can undermine emergency response efforts, public trust, and crisis communication. Existing research primarily…
SCoRD: Semantic-Assisted Continual Retriever-Reranker Distillation for LLM-Based Recommendation
Seunghyun Baek, Gyuseok Lee, Seunghan Lee +3
Recommendation systems increasingly adopt a two-stage pipeline, where an ID-based retriever retrieves candidates and an LLM-based reranker refines their rankings. To improve retrie…
Topology-Aware Tokenization for Generative Recommendation
Yaokun Liu, Yifan Liu, Zhenrui Yue +4
Generative recommendation reformulates sequential recommendation as an autoregressive generation task, yet a critical issue in this paradigm remains overlooked: topology distortion…
Harsher on Male? Evaluating LLMs on Gender-Asymmetric Moral Framing Across Diverse Conflict Scenarios
Guangzong Si, Dong Wang, Zhenhao Li +3
Existing studies on gender bias in LLMs have largely focused on stereotypes, occupational associations, or explicit harmful outputs. In this work, we ask whether LLMs apply consist…
DisImpact: Quantifying the Physi-Social Impact of Natural Disasters Through Social Media
Ruichen Yao, Tejna Dasari, Xuanyu Meng +6
Natural disasters not only cause large-scale physical destruction, but also cascading social consequences that are difficult to quantify with traditional surveys and reports. Socia…
Mind the Ambiguity: Aleatoric Uncertainty Quantification in LLMs for Safe Medical Question Answering
Yaokun Liu, Yifan Liu, Phoebe Mbuvi +4
The deployment of Large Language Models in Medical Question Answering is severely hampered by ambiguous user queries, a significant safety risk that demonstrably reduces answer acc…