Inspecting and Editing Knowledge Representations in Language Models
Research Area: LMs and the world
Keywords: representation editing, knowledge, factuality, interpretability, world models
TL;DR: Introduces representation editing for LMs and applies it to controlled generation, knowledge editing, and failure detection
Abstract: Neural language models (LMs) represent facts about the world described by text. Sometimes these facts derive from training data (in most LMs, a representation of the word *banana* encodes the fact that bananas are fruits). Sometimes facts derive from input text itself (a representation of the sentence *I poured out the bottle* encodes the fact that the bottle became empty). We describe REMEDI, a method for learning to map statements in natural language to fact encodings in an LM's internal representation system. REMEDI encodings can be used as *knowledge editors*: when added to LM hidden representations, they modify downstream generation to be consistent with new facts. REMEDI encodings may also be used as *probes*: when compared to LM representations, they reveal which properties LMs already attribute to mentioned entities, in some cases making it possible to predict when LMs will generate outputs that conflict with background knowledge or input text. REMEDI thus links work on probing, prompting, and LM editing, and offers steps toward general tools for fine-grained inspection and control of knowledge in LMs.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html
Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html
Submission Number: 921
Loading