Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks

Anonymous

Paper Link: https://openreview.net/forum?id=8cwJDZ1VezG

Paper Type: Long paper (up to eight pages of content + unlimited references and appendices)

Abstract:

Retrieval-augmented generation models have shown state-of-the-art performance across many knowledge-intensive NLP tasks such as open-domain question answering and fact verification. These models are trained to generate a final output given retrieved passages that can be irrelevant to an input query, leading to learning spurious cues or memorization.
This work introduces a method to incorporate {\it evidentiality} of passages---whether a passage contains correct evidence to support the output---into training the generator.
We introduce a multi-task learning framework to jointly generate the final output and predict the {\it evidentiality} of each passage. Furthermore, we introduce a new task-agnostic method for obtaining high-quality {\it silver} evidentiality labels, addressing the issues of gold evidentiality labels being unavailable in most domains. Our experiments on five datasets across three knowledge-intensive tasks show that our new evidentiality-guided generator significantly outperforms its direct counterpart on all of them, and advances the state of the art on three of them. Our analysis shows that multi-task learning and silver evidentiality mining play key roles. Our code is available at https://github.com/AkariAsai/evidentiality_qa

Presentation Mode: This paper will be presented in person in Seattle

Copyright Consent Signature (type Name Or NA If Not Transferrable): Akari Asai

Copyright Consent Name And Address: Paul G. Allen School of Computer Science & Engineering University of Washington, 185 E Stevens Way NE Seattle, WA 98195-2350