Language Modeling with Editable External Knowledge
Abstract: When the world changes, so does the text that people write about it. How do we build language models that can be easily updated to reflect these changes? One popular approach is retrieval-augmented generation, in which new documents are inserted into a knowledge base and retrieved during prediction for downstream tasks.
Most prior work on these systems have focused on improving behavior during *prediction* through better retrieval or reasoning.
This paper introduces ERASE, which instead improves model behavior *when new documents are created*, by incrementally deleting or rewriting other entries in the knowledge base each time a new document is encountered.
In two new benchmark datasets evaluating models' ability to answer questions about a stream of news articles or conversations, ERASE improves accuracy relative to conventional retrieval-augmented generation by 7--13\% (Mixtral-8x7B) and 6--10\% (Llama-3-8B) absolute.
Code and data will be made publicly available.
Paper Type: Long
Research Area: Language Modeling
Research Area Keywords: retrieval-augmented models, continual learning
Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources
Languages Studied: English
Submission Number: 3509
Loading