ACL 2023findings3 citations
Triggering Multi-Hop Reasoning for Question Answering in Language Models using Soft Prompts and Random Walks
Kanishka Misra, Cicero Nogueira dos Santos, Siamak Shakeri
Abstract
Despite readily memorizing world knowledge about entities, pre-trained language models (LMs) struggle to compose together two or more facts to perform multi-hop reasoning in question-answering tasks. In this work, we propose techniques that improve upon this limitation by relying on random-walks over structured knowledge graphs. Specifically, we use soft-prompts to guide LMs to chain together their encoded knowledge by learning to map multi-hop questions to random-walk paths that lead to the answer. Applying our methods on two T5 LMs shows substantial improvements over standard tuning approaches in answering questions that require multi-hop reasoning.
BibTeX
@inproceedings{misra-etal-2023-triggering,
title = "Triggering Multi-Hop Reasoning for Question Answering in Language Models using Soft Prompts and Random Walks",
author = "Misra, Kanishka and
Nogueira dos Santos, Cicero and
Shakeri, Siamak",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.62/",
doi = "10.18653/v1/2023.findings-acl.62",
pages = "972--985"
}