Unsupervised Pretraining for Fact Verification by Language Model Distillation
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Unsupervised Learning, Self-supervised Learning, Deep Features, Contrastive Learning, Large Language Models, Knowledge Distillation, Multimodality, Fact Verification
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: We propose a new framework for performing unsupervised pretraining for fact verification by distilling large language models knowledge for claim-evidence matching
Abstract: Fact verification aims to verify a claim using evidence from a trustworthy knowledge base. To address this challenge, algorithms must produce features for every claim that are both semantically meaningful, and compact enough to find a semantic alignment with the source information. In contrast to previous work, which tackled the alignment problem by learning over annotated corpora of claims and their corresponding labels, we propose SFAVEL ($\underline{S}$elf-supervised $\underline{Fa}$ct $\underline{Ve}$rification via $\underline{L}$anguage Model Distillation), a novel unsupervised pretraining framework that leverages pre-trained language models to distil self-supervised features into high-quality claim-fact alignments without the need for annotations. This is enabled by a novel contrastive loss function that encourages features to attain high-quality claim and evidence alignments whilst preserving the semantic relationships across the corpora. Notably, we present results that achieve a new state-of-the-art on FB15k-237 (+5.3\% Hits@1) and FEVER (+8\% accuracy) with linear evaluation.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Primary Area: representation learning for computer vision, audio, language, and other modalities
Submission Number: 6308
Loading