AkihikoWatanabe / paper_notes

たまに追加される論文メモ
https://AkihikoWatanabe.github.io/paper_notes
14 stars 0 forks source link

On Improving Summarization Factual Consistency from Natural Language Feedback, ACL'23 #841

Open AkihikoWatanabe opened 12 months ago

AkihikoWatanabe commented 12 months ago

https://virtual2023.aclweb.org/paper_P4192.html

AkihikoWatanabe commented 11 months ago

Despite the recent progress in language generation models, their outputs may not always meet user expectations. In this work, we study whether informational feedback in natural language can be leveraged to improve generation quality and user preference alignment. To this end, we consider factual consistency in summarization, the quality that the summary should only contain information supported by the input documents, as the user-expected preference. We collect a high-quality dataset, DeFacto, containing human demonstrations and informational natural language feedback consisting of corrective instructions, edited summaries, and explanations with respect to the factual consistency of the summary. Using our dataset, we study three natural language generation tasks: (1) editing a summary by following the human feedback, (2) generating human feedback for editing the original summary, and (3) revising the initial summary to correct factual errors by generating both the human feedback and edited summary. We show that DeFacto can provide factually consistent human-edited summaries and further insights into summarization factual consistency thanks to its informational natural language feedback. We further demonstrate that fine-tuned language models can leverage our dataset to improve the summary factual consistency, while large language models lack the zero-shot learning ability in our proposed tasks that require controllable text generation.

Translation (by gpt-3.5-turbo)