Showing cs.CLShow all
2 papers · 1 filter
cs.CL2025
Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO
Kaiyang Guo, Yinchuan Li, Zhitang Chen
Direct alignment methods typically train large language models (LLMs) by contrasting the likelihoods of preferred and dispreferred responses. While effective at capturing relative…
cs.CL2025
Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents
Yihong Tang, Kehai Chen, Liang Yue +11
With the rise of large language models (LLMs), LLM agents capable of autonomous reasoning, planning, and executing complex tasks have become a frontier in artificial intelligence.…