6 papers
Reliability-Aware LLM Alignment from Inconsistent Human Feedback
Jingyi Huang, Ruohan Zong, Yujun Feng +3
Reinforcement Learning from Human Feedback (RLHF) is critical for aligning Large Language Models (LLMs) with human preferences. However, its efficacy is often compromised by the in…
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…
MASH: A Multiplatform and Multimodal Annotated Dataset for Societal Impact of Hurricane
Ruichen Yao, Aslanbek Murzakhmetov, Raaghav Pillai +9
Natural disasters cause multidimensional threats to human societies, with hurricanes exemplifying one of the most disruptive events that not only caused severe physical damage but…
Hybrid Latent Reasoning via Reinforcement Learning
Zhenrui Yue, Bowen Jin, Huimin Zeng +6
Recent advances in large language models (LLMs) have introduced latent reasoning as a promising alternative to autoregressive reasoning. By performing internal computation with hid…
Designing Effective AI Explanations for Misinformation Detection: A Comparative Study of Content, Social, and Combined Explanations
Yeaeun Gong, Yifan Liu, Lanyu Shang +2
In this paper, we study the problem of AI explanation of misinformation, where the goal is to identify explanation designs that help improve users' misinformation detection abiliti…
SIDE: Socially Informed Drought Estimation Toward Understanding Societal Impact Dynamics of Environmental Crisis
Lanyu Shang, Bozhang Chen, Shiwei Liu +6
Drought has become a critical global threat with significant societal impact. Existing drought monitoring solutions primarily focus on assessing drought severity using quantitative…