Log In Sign Up

FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation

by   Sebastian Hofstätter, et al.

Retrieval-augmented generation models offer many benefits over standalone language models: besides a textual answer to a given query they provide provenance items retrieved from an updateable knowledge base. However, they are also more complex systems and need to handle long inputs. In this work, we introduce FiD-Light to strongly increase the efficiency of the state-of-the-art retrieval-augmented FiD model, while maintaining the same level of effectiveness. Our FiD-Light model constrains the information flow from the encoder (which encodes passages separately) to the decoder (using concatenated encoded representations). Furthermore, we adapt FiD-Light with re-ranking capabilities through textual source pointers, to improve the top-ranked provenance precision. Our experiments on a diverse set of seven knowledge intensive tasks (KILT) show FiD-Light consistently improves the Pareto frontier between query latency and effectiveness. FiD-Light with source pointing sets substantial new state-of-the-art results on six KILT tasks for combined text generation and provenance retrieval evaluation, while maintaining reasonable efficiency.


page 1

page 2

page 3

page 4


Multi-Task Retrieval-Augmented Text Generation with Relevance Sampling

This paper studies multi-task training of retrieval-augmented generation...

A Survey on Retrieval-Augmented Text Generation

Recently, retrieval-augmented text generation attracted increasing atten...

Generation-Augmented Query Expansion For Code Retrieval

Pre-trained language models have achieved promising success in code retr...

ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models

Automatic construction of relevant Knowledge Bases (KBs) from text, and ...

Does Structure Matter? Leveraging Data-to-Text Generation for Answering Complex Information Needs

In this work, our aim is to provide a structured answer in natural langu...

Retrieval-Augmented Multimodal Language Modeling

Recent multimodal models such as DALL-E and CM3 have achieved remarkable...

FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference

Fusion-in-Decoder (FiD) is a powerful retrieval-augmented language model...