2023-05-01から1ヶ月間の記事一覧
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models arxiv.org Wei, Jason, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed Chi, Quoc Le, and Denny Zhou. "Chain of thought prompting elicits reasoning in large language model…
Controlled Hallucinations: Learning to Generate Faithfully from Noisy Data aclanthology.org Katja Filippova. 2020. Controlled Hallucinations: Learning to Generate Faithfully from Noisy Data. In Findings of the Association for Computational…
Retrieval Augmentation Reduces Hallucination in Conversation aclanthology.org Kurt Shuster, Spencer Poff, Moya Chen, Douwe Kiela, and Jason Weston. 2021. Retrieval Augmentation Reduces Hallucination in Conversation. In Findings of the Asso…
On the Origin of Hallucinations in Conversational Models:Is it the Datasets or the Models? aclanthology.org ©2022 Association for Computational Linguistics License: Creative Commons Attribution 4.0 International License(CC-BY) 本記事は、原…
Diving Deep into Modes of Fact Hallucinations in Dialogue Systems aclanthology.org ©2022 Association for Computational Linguistics License: Creative Commons Attribution 4.0 International License(CC-BY) 本記事は、原著の内容に基づき筆者が要…
The Curious Case of Hallucinations in Neural Machine Translation aclanthology.org ©2022 Association for Computational Linguistics License: Creative Commons Attribution 4.0 International License(CC-BY) 本記事は、原著の内容に基づき筆者が要約…
A Distributional Lens for Multi-Aspect Controllable Text Generation aclanthology.org ©2022 Association for Computational Linguistics License: Creative Commons Attribution 4.0 International License(CC-BY) 本記事は、原著の内容に基づき筆者が…
AttentionViz: A Global View of Transformer Attention arxiv.org Yeh, Catherine, Yida Chen, Aoyu Wu, Cynthia Chen, Fernanda Viégas, and Martin Wattenberg. "AttentionViz: A Global View of Transformer Attention." arXiv preprint arXiv:2305.0321…
CIKQA: Learning Commonsense Inference with a Unified Knowledge-in-the-loop QA Paradigm aclanthology.org ©2022 Association for Computational Linguistics License: Creative Commons Attribution 4.0 International License(CC-BY) 本記事は、原著の…
Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents aclanthology.org Eric Smith, Orion Hsu, Rebecca Qian, Stephen Roller, Y-Lan Boureau, and Jason Weston. 2022. …
Long-term Control for Dialogue Generation: Methods and Evaluation aclanthology.org Ramya Ramakrishnan, Hashan Narangodage, Mauro Schilman, Kilian Weinberger, and Ryan McDonald. 2022. Long-term Control for Dialogue Generation: Methods and E…
SKILL: Structured Knowledge Infusion for Large Language Models. aclanthology.org Fedor Moiseev, Zhe Dong, Enrique Alfonseca, and Martin Jaggi. 2022. SKILL: Structured Knowledge Infusion for Large Language Models. In Proceedings of the 2022…
Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space aclanthology.org Mor Geva, Avi Caciularu, Kevin Wang, and Yoav Goldberg. 2022. Transformer Feed-Forward Layers Build Predictions by Promoting C…