31 citations · 40 across the 18 of their papers we have counts for
18 papers
Normalized Rewards for Preference Optimization
Shawn Im, Federico Danieli, Skyler Seto +2
Direct Alignment Algorithms (DAAs) such as DPO have become a common way to post-train and align LLMs with human preferences. However, DAAs have been observed to over-optimize their…
Closing the Gap Between Text and Speech Understanding in LLMs
Santiago Cuervo, Skyler Seto, Maureen de Seyssel +5
Large Language Models (LLMs) can be adapted to extend their text capabilities to speech inputs. However, these speech-adapted LLMs consistently underperform their text-based counte…
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
Chen Huang, Skyler Seto, Hadi Pouransari +6
Vision foundation models pre-trained on massive data encode rich representations of real-world concepts, which can be adapted to downstream tasks by fine-tuning. However, fine-tuni…
Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models
Anirudh Sundar, Sinead Williamson, Katherine Metcalf +3
Aligned representations across languages is a desired property in multilingual large language models (mLLMs), as alignment can improve performance in cross-lingual tasks. Typically…
ExpertLens: Activation steering features are highly interpretable
Masha Fedzechkina, Eleonora Gualdoni, Sinead Williamson +3
Activation steering methods in large language models (LLMs) have emerged as an effective way to perform targeted updates to enhance generated language without requiring large amoun…
On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization
Yong Lin, Skyler Seto, Maartje ter Hoeve +6
Reinforcement Learning from Human Feedback (RLHF) is an effective approach for aligning language models to human preferences. Central to RLHF is learning a reward function for scor…