9 papers
Investigating and Alleviating Harm Amplification in LLM Interactions
Ruohao Guo, Wei Xu, Alan Ritter
Large language models (LLMs) can serve as helpful assistants, yet they can equally function as harm amplifiers that enable malicious users to achieve harmful outcomes beyond their…
Synthetic Data Alone is Enough? Rethinking Data Scarcity in Pediatric Rare Disease Recognition
Ganlin Feng, Yuxi Long, Erin Lou +4
Children with rare genetic diseases often exhibit distinctive facial phenotypes, yet developing computer vision systems for early diagnosis remains challenging due to extreme data…
Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression
Jungsoo Park, Hyungjoo Chae, Ethan Mendes +4
Large language models can predict real-valued quantities from heterogeneous inputs such as text, code, and molecular strings, but most training objectives score each decoded floati…
GeoRC: A Benchmark for Geolocation Reasoning Chains
Mohit Talreja, Joshua Diao, Jim Thannikary James +6
Vision Language Models (VLMs) are good at recognizing the global location of a photograph -- their geolocation prediction accuracy rivals the best human experts. But many VLMs are…
Do Vision-Language Models Respect Contextual Integrity in Location Disclosure?
Ruixin Yang, Ethan Mendes, Arthur Wang +4
Vision-language models (VLMs) have demonstrated strong performance in image geolocation, a capability further sharpened by frontier multimodal large reasoning models (MLRMs). This…
Supporting Informed Self-Disclosure: Design Recommendations for Presenting AI-Estimates of Privacy Risks to Users
Isadora Krsek, Meryl Ye, Wei Xu +3
People candidly discuss sensitive topics online under the perceived safety of anonymity; yet, for many, this perceived safety is tenuous, as miscalibrated risk perceptions can lead…