Search Results for author: Qinan Yu

Found 4 papers, 2 papers with code

Grokking Group Multiplication with Cosets

no code implementations11 Dec 2023 Dashiell Stander, Qinan Yu, Honglu Fan, Stella Biderman

We use the group Fourier transform over the symmetric group $S_n$ to reverse engineer a 1-layer feedforward network that has "grokked" the multiplication of $S_5$ and $S_6$.

Characterizing Mechanisms for Factual Recall in Language Models

no code implementations24 Oct 2023 Qinan Yu, Jack Merullo, Ellie Pavlick

By scaling up or down the value vector of these heads, we can control the likelihood of using the in-context answer on new data.


Are Language Models Worse than Humans at Following Prompts? It's Complicated

1 code implementation17 Jan 2023 Albert Webson, Alyssa Marie Loo, Qinan Yu, Ellie Pavlick

However, recent work finds that models can perform surprisingly well when given intentionally irrelevant or misleading prompts.

Does CLIP Bind Concepts? Probing Compositionality in Large Image Models

1 code implementation20 Dec 2022 Martha Lewis, Nihal V. Nayak, Peilin Yu, Qinan Yu, Jack Merullo, Stephen H. Bach, Ellie Pavlick

In this work, we focus on the ability of a large pretrained vision and language model (CLIP) to encode compositional concepts and to bind variables in a structure-sensitive way (e. g., differentiating ''cube behind sphere'' from ''sphere behind cube'').

Language Modelling Open-Ended Question Answering

Cannot find the paper you are looking for? You can Submit a new open access paper.