Toward LLM Self-Play Under Data Scarcity: Effectiveness, Generalizability, and Trustworthiness
The rapid development of large language models (LLMs) has been driven largely by scaling model size and human-curated training data, yet this paradigm is increasingly constrained by data scarcity and diminishing returns from human supervision.
By Zhiyin Yu, Yuchen Mou, Bingzhe Wu, Zhonghai Wu, Shiyang Feng, Xiao LuoarXiv - cs.AI
Read the full story
Originally published by arXiv - cs.AI on Nov 9, 2026.
Comments
Sign in to join the discussion.