3 papers
cs.CL2026
Why Are Some Emotions Harder for LLMs? Uncovering the Causal Mechanisms of Emotion Inference via Sparse Autoencoders
Bangzhao Shu, Arinjay Singh, Mai ElSherief
Large language models (LLMs) are increasingly used in emotionally sensitive human-AI applications, where reliable emotion detection is essential. However, their emotion recognition…
cs.SI2026
"He gets to be the fun parent": Understanding and Supporting Burnt-Out Mothers in Online Communities
Nazanin Sabri, Ananya Malik, Bangzhao Shu +3
Maternal burnout is a psychological phenomena with documented harms to both mother and child, requiring prompt attention. Mothers experiencing burnout might choose to turn to onlin…
cs.CL2025
Fluent but Unfeeling: The Emotional Blind Spots of Language Models
Bangzhao Shu, Isha Joshi, Melissa Karnaze +5
The versatility of Large Language Models (LLMs) in natural language understanding has made them increasingly popular in mental health research. While many studies explore LLMs' cap…