3 papers
cs.CL2025
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
Angelica Chen, Ravid Shwartz-Ziv, Kyunghyun Cho +2
Most interpretability research in NLP focuses on understanding the behavior and features of a fully trained model. However, certain insights into model behavior may only be accessi…
cs.LG2024
Preference Learning Algorithms Do Not Learn Preference Rankings
Angelica Chen, Sadhika Malladi, Lily H. Zhang +4
Preference learning algorithms (e.g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner…
cs.GT2024
Playing Large Games with Oracles and AI Debate
Xinyi Chen, Angelica Chen, Dean Foster +1
We consider regret minimization in repeated games with a very large number of actions. Such games are inherent in the setting of AI Safety via Debate \cite{irving2018ai}, and more…