Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
BPO: Staying Close to the Behavior LLM Creates Better Online LLM Alignment
Wenda Xu, Jiachen Li, William Yang Wang +1
Direct alignment from preferences (DAP) has emerged as a promising paradigm for aligning large language models (LLMs) to human desiderata from pre-collected, offline preference dat…
cs.LG2024
Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning
Danqing Wang, Antonis Antoniades, Kha-Dinh Luong +6
Counterfactual explanations of Graph Neural Networks (GNNs) offer a powerful way to understand data that can naturally be represented by a graph structure. Furthermore, in many dom…