Papers
arxiv:2305.16765

Backpack Language Models

Published on May 26, 2023
· Submitted by akhaliq on May 29, 2023

Abstract

We present Backpacks: a new neural architecture that marries strong modeling performance with an interface for interpretability and control. Backpacks learn multiple non-contextual sense vectors for each word in a vocabulary, and represent a word in a sequence as a context-dependent, non-negative linear combination of sense vectors in this sequence. We find that, after training, sense vectors specialize, each encoding a different aspect of a word. We can interpret a sense vector by inspecting its (non-contextual, linear) projection onto the output space, and intervene on these interpretable hooks to change the model's behavior in predictable ways. We train a 170M-parameter Backpack language model on OpenWebText, matching the loss of a GPT-2 small (124Mparameter) Transformer. On lexical similarity evaluations, we find that Backpack sense vectors outperform even a 6B-parameter Transformer LM's word embeddings. Finally, we present simple algorithms that intervene on sense vectors to perform controllable text generation and debiasing. For example, we can edit the sense vocabulary to tend more towards a topic, or localize a source of gender bias to a sense vector and globally suppress that sense.

Community

Paper author

A gif I made of the Backpack language modeling process :)

backpack-process.gif

Sign up or log in to comment

Models citing this paper 2

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2305.16765 in a dataset README.md to link it from this page.

Spaces citing this paper 2

Collections including this paper 1