On the Intractability to Synthesize Factual Inconsistencies in Summarization

Factual consistency detection has gotten significant attention for the task of abstractive summarization. Many existing works rely on synthetic training data, which may not accurately reflect or match the inconsistencies produced by summarization models. In this paper, we first systematically analyze the shortcomings of the current methods in synthesizing inconsistent summaries. Current synthesis methods may fail to produce inconsistencies of coreference errors and discourse errors, per our quantitative and qualitative study. Then, employing the parameter-efficient finetuning (PEFT) technique, we discover that a competitive factual consistency detector can be achieved using thousands of real model-generated summaries with human annotations. Our study demonstrates the importance of real machine-generated texts with human annotation in Natural Language Generatioon (NLG) evaluation as our model outperforms the SOTA on the CoGenSumm, FactCC, Frank, and SummEval datasets.