Tag: model-editing | Yingfa Chen 陈英发

(EREN) Robust and Scalable Model Editing for Large Language Models

1 | 1 TL;DR : A reader is augmented with a growing notebook that caches all edits in natural texts, and the reader retrieves relevant edits and make inference based on them. This achieves SOTA in model editing in QA and fact checking.

Activation Addition (ActAdd)

1 TLDR: Propose ActAdd , a method for controlling model behavior during inference by modifying activations with a bias term that is learned from a pair of prompt. Summary: Propose ActAdd , a method for controlling model behavior by modifying activations at inference time. Steering vectors are computed by taking the ...