2 citations · 3 across the 5 of their papers we have counts for
5 papers
Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior
Daniel Aarao Reis Arturi, Eric Zhang, Andrew Ansah +3
Recent work has discovered that large language models can develop broadly misaligned behaviors after being fine-tuned on narrowly harmful datasets, a phenomenon known as emergent m…
Can Gradient Descent Simulate Prompting?
Eric Zhang, Leshem Choshen, Jacob Andreas
There are two primary ways of incorporating new information into a language model (LM): changing its prompt or changing its parameters, e.g. via fine-tuning. Parameter updates incu…
Unforgettable Generalization in Language Models
Eric Zhang, Leshem Choshen, Jacob Andreas
When language models (LMs) are trained to forget (or "unlearn'') a skill, how precisely does their behavior change? We study the behavior of transformer LMs in which tasks have bee…
Ragnarök: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Track
Ronak Pradeep, Nandan Thakur, Sahel Sharifymoghaddam +5
Did you try out the new Bing Search? Or maybe you fiddled around with Google AI~Overviews? These might sound familiar because the modern-day search stack has recently evolved to in…
Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models
Yiwen Tang, Ray Zhang, Zoey Guo +4
The popularity of pre-trained large models has revolutionized downstream tasks across diverse fields, such as language, vision, and multi-modality. To minimize the adaption cost fo…