THE IMPACT OF PREFERENCE LEARNING

Our latest blog entry discusses the impact of #PreferenceLearning in #LLMs, wraps up #MPREF2025, and gives an outlook on this year’s #PreferenceHandling events #DA2PL2026 and #ADT2026. ADT will be held in Paris on Nov. 16-18. Abstracts are due by May 4, papers by May 11.
mpref.org/the-impact-o...

Problem Solving Through Human–AI Preference-based Cooperation Abstract. While there is a widespread belief that artificial general intelligence—or even superhuman AI—is imminent, complex problems in expert domains are far from being solved. We argue that such pr...

💻 Project page:
ukplab.github.io/arxiv2025-ex...

🔁 Both papers build on HAI-Co2 described in this position paper:
direct.mit.edu/coli/article...

#NLP #NLProc #LLMs #Evaluation #PreferenceLearning #ScientificWriting #HumanAI #HaiCo2 @tuda.bsky.social @cs-tudarmstadt.bsky.social

CS329H: Machine Learning from Human Preferences Machine Learning from Human Preferences

7/ Materials:
Course website / syllabus / notes: web.stanford.edu/class/cs329h/
Living Textbook: mlhp.stanford.edu
#AIAlignment #MachineLearning #ResponsibleAI #Stanford #PreferenceLearning

Algorithm Finds Best Policies with Trajectory Preference Feedback

PSPL merges offline preference data with online exploration, using Thompson sampling to give Bayesian simple‑regret bounds for RL. Read more: getnews.me/algorithm-finds-best-pol... #preferencelearning #reinforcementlearning