Showing 2024Show all
3 papers · 1 filter
cs.CL2024
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…
cs.LG2024
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…
cs.CL2024
Representing Rule-based Chatbots with Transformers
Dan Friedman, Abhishek Panigrahi, Danqi Chen
What kind of internal mechanisms might Transformers use to conduct fluid, natural-sounding conversations? Prior work has illustrated by construction how Transformers can solve vari…