FIZZ: Factual Inconsistency Detection by Zoom-in Summary and Zoom-out Document
This work addresses limitations in interpretability and refinement for factual inconsistency detection in abstractive summarization, offering a more effective and interpretable metric for researchers and practitioners in natural language processing.
The paper tackles the problem of evaluating factual consistency in abstractive summarization systems by proposing FIZZ, a method based on fine-grained atomic facts decomposition and adaptive granularity expansion, which significantly outperforms existing systems in experiments.
Through the advent of pre-trained language models, there have been notable advancements in abstractive summarization systems. Simultaneously, a considerable number of novel methods for evaluating factual consistency in abstractive summarization systems has been developed. But these evaluation approaches incorporate substantial limitations, especially on refinement and interpretability. In this work, we propose highly effective and interpretable factual inconsistency detection method metric Factual Inconsistency Detection by Zoom-in Summary and Zoom-out Document for abstractive summarization systems that is based on fine-grained atomic facts decomposition. Moreover, we align atomic facts decomposed from the summary with the source document through adaptive granularity expansion. These atomic facts represent a more fine-grained unit of information, facilitating detailed understanding and interpretability of the summary's factual inconsistency. Experimental results demonstrate that our proposed factual consistency checking system significantly outperforms existing systems.