arXiv Machine Learning By Jacek Karwowski, Younesse Kaddar, Zihuiwen Ye, Esmeralda S. Whitammer, Sam Staton

Likelihood Hacking in Probabilistic Program Synthesis

Read the original on arXiv Machine Learning →

arXiv:2603. 24126v2 Announce Type: replace Abstract: When language models are trained by reinforcement learning (RL) to write probabilistic programs, they can artificially inflate their marginal-likelihood reward by producing programs whose data distribution fails to normalise instead of fitting the data better.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers
Jul 2

Safety Targeted Embedding Exploit via Refinement

Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching. We show that this creates an epistemic gap in which models confidently generate harmful responses for inputs that fall outside the distribution of their safety training.