2 papers
cs.CL2024
Model-based Preference Optimization in Abstractive Summarization without Human Feedback
Jaepill Choi, Kyubyung Chae, Jiwoo Song +2
In abstractive summarization, the challenge of producing concise and accurate summaries arises from the vast amount of information contained in the source document. Consequently, a…
cs.CL2024
Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information
Kyubyung Chae, Jaepill Choi, Yohan Jo +1
A primary challenge in abstractive summarization is hallucination -- the phenomenon where a model generates plausible text that is absent in the source text. We hypothesize that th…