7 papers
From Images to Words: Efficient Cross-Modal Knowledge Distillation to Language Models from Black-box Teachers
Ayan Sengupta, Shantanu Dixit, Md Shad Akhtar +1
Knowledge distillation (KD) methods are pivotal in compressing large pre-trained language models into smaller models, ensuring computational efficiency without significantly droppi…
HateMirage: An Explainable Multi-Dimensional Dataset for Decoding Faux Hate and Subtle Online Abuse
Sai Kartheek Reddy Kasu, Shankar Biradar, Sunil Saumya +1
Subtle and indirect hate speech remains an underexplored challenge in online safety research, particularly when harmful intent is embedded within misleading or manipulative narrati…
Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation
Zuhair Hasan Shaik, Abdullah Mazhar, Aseem Srivastava +1
Large Language Models have demonstrated impressive fluency across diverse tasks, yet their tendency to produce toxic content remains a critical challenge for AI safety and public t…
Assess and Prompt: A Generative RL Framework for Improving Engagement in Online Mental Health Communities
Bhagesh Gaur, Karan Gupta, Aseem Srivastava +2
Online Mental Health Communities (OMHCs) provide crucial peer and expert support, yet many posts remain unanswered due to missing support attributes that signal the need for help.…
Sentiment-guided Commonsense-aware Response Generation for Mental Health Counseling
Aseem Srivastava, Gauri Naik, Alison Cerezo +2
The crisis of mental health issues is escalating. Effective counseling serves as a critical lifeline for individuals suffering from conditions like PTSD, stress, etc. Therapists fo…
Trust Modeling in Counseling Conversations: A Benchmark Study
Aseem Srivastava, Zuhair Hasan Shaik, Tanmoy Chakraborty +1
In mental health counseling, a variety of earlier studies have focused on dialogue modeling. However, most of these studies give limited to no emphasis on the quality of interactio…