SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations
Paper • 2606.05563 • Published • 56
Seunghwan Bang
Breadbang
·
AI & ML interests
Recommender System, Large Language Models
Organizations
upvoted 4
papers 3 months ago
ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback
Paper • 2503.21332 • Published • 25
Rethinking RAG in Long Videos: What to Retrieve and How to Use It?
Paper • 2606.13141 • Published • 36
What Makes a Sale? Rethinking End-to-End Seller--Buyer Retail Dynamics with LLM Agents
Paper • 2604.04468 • Published • 9
upvoted a paper over 1 year ago