Optimizing Retrieval-augmented Reader Models via Token Elimination

Moshe Berchansky, Peter Izsak, Avi Caciularu, Ido Dagan, Moshe Wasserblat

Submission Type: Regular Long Paper

Submission Track: Efficient Methods for NLP

Submission Track 2: Question Answering

Keywords: fusion in decoder, efficiency, long-form question answering

TL;DR: We introduce a method for eliminating irrelevant tokens from retrieved information in long form question answering systems during decoding time.

Abstract:

Fusion-in-Decoder (FiD) is an effective retrieval-augmented language model applied across a variety of open-domain tasks, such as
question answering, fact checking, etc. In FiD, supporting passages are first retrieved and then processed using a generative model (Reader),
which can cause a significant bottleneck in decoding time, particularly with long outputs. In this work, we analyze the contribution and necessity of all the retrieved passages to the performance of reader models, and propose eliminating some of the retrieved information, at the
token level, that might not contribute essential information to the answer generation process. We demonstrate that our method can reduce
run-time by up to 62.2%, with only a 2% reduction in performance, and in some cases, even improve the performance results.

Submission Number: 3740