2 citations · 2 across the 10 of their papers we have counts for
5 papers · 1 filter
Continual Memorization of Factoids in Language Models
Howard Chen, Jiayi Geng, Adithya Bhaskar +2
As new knowledge rapidly accumulates, language models (LMs) with pretrained knowledge quickly become obsolete. A common approach to updating LMs is fine-tuning them directly on new…
Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
Noam Razin, Sadhika Malladi, Adithya Bhaskar +3
Direct Preference Optimization (DPO) and its variants are increasingly used for aligning language models with human preferences. Although these methods are designed to teach a mode…
Finding Transformer Circuits with Edge Pruning
Adithya Bhaskar, Alexander Wettig, Dan Friedman +1
The path to interpreting a language model often proceeds via analysis of circuits -- sparse computational subgraphs of the model that capture specific aspects of its behavior. Rece…
The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models
Adithya Bhaskar, Dan Friedman, Danqi Chen
Prior work has found that pretrained language models (LMs) fine-tuned with different random seeds can achieve similar in-domain performance but generalize differently on tests of s…
Improving Language Understanding from Screenshots
Tianyu Gao, Zirui Wang, Adithya Bhaskar +1
An emerging family of language models (LMs), capable of processing both text and images within a single visual view, has the promise to unlock complex tasks such as chart understan…