← Search

Harsh Kumar

2 accepted papers

2026

Position: We Need Large Language Models Optimized For Our Well-Being

ICML 2026poster

Contemporary large language models are predominantly trained using reinforcement learning from human feedback (RLHF), optimizing for immediate user approval rather than long-term well-being. This position paper argues that as AI systems increasingly serve socioemotional functions, this optimization …

Cited by 0SourceScholar
2024

Using Adaptive Bandit Experiments to Increase and Investigate Engagement in Mental Health

AAAI 2024technical

Digital mental health (DMH) interventions, such as text-message-based lessons and activities, offer immense potential for accessible mental health support. While these interventions can be effective, real-world experimental testing can further enhance their design and impact. Adaptive experimentatio…