Unsupervised Improvement of Factual Knowledge in Language Models

[2304.01597] Unsupervised Improvement of Factual Knowledge in Language Models Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2304.01597 (cs) [Submitted on 4 Apr 2023] Title: Unsupervised Improvement of Factual Knowledge in Language Models Authors: Nafis Sadeq , Byungkyu Kang , Prarit Lamba , Julian McAuley View a PDF of the paper titled Unsupervised Improvement of Factual Knowledge in Language Models, by Nafis Sadeq and 3 other authors View PDF HTML (experimental) Abstract: Masked language modeling (MLM) plays a key role in pretraining large language models. But the MLM objective is often dominated by high-frequency words that are sub-optimal for learning factual knowledge. In this work, we propose an approach for influencing MLM pretraining in a way that can improve language model performance on a variety of knowledge-intensive tasks. We force the language model to prioritize informative words in a fully unsupervised way. Experiments demonstrate that the proposed approach can significantly improve the performance of pretrained language models on tasks such as factual recall, question answering, sentiment analysis, and natural language inference in a closed-book setting. Subjects: Computation and Language (cs.CL) Cite as: arXiv:2304.01597 [cs.CL] (or arXiv:2304.01597v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2304.01597 Focus to learn more arXiv-issued DOI via DataCite Journal reference: Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023) Related DOI : https://doi.org/10.18653/v1/2023.eacl-main.215 Focus to learn more DOI(s) linking to related resources Submission history From: Nafis Sadeq [ view email ] [v1] Tue, 4 Apr 2023 07:37:06 UTC (288 KB) Full-text links: Access Paper: View a PDF of the paper titled Unsupervised Improvement of Factual Knowledge in Language Models, by Nafis Sadeq and 3 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2023-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Falsehood and Entailment#711668
• InComeS: Integrating Compression and Selection Mechanisms into LLMs for Efficient Model Editing#820206
• The Semantics of Entailment#774398
• The Semantics of Entailment#764262
• Data and evidence in linguistics#341429