2 papers
cs.LG2025
The Alignment Game: A Theory of Long-Horizon Alignment Through Recursive Curation
Ali Falahati, Mohammad Mohammadi Amiri, Kate Larson +1
In self-consuming generative models that train on their own outputs, alignment with user preferences becomes a recursive rather than one-time process. We provide the first formal f…
cs.SE2025
NL in the Middle: Code Translation with LLMs and Intermediate Representations
Chi-en Amy Tai, Pengyu Nie, Lukasz Golab +1
Studies show that large language models (LLMs) produce buggy code translations. One promising avenue to improve translation accuracy is through intermediate representations, which…