Zero-shot Factual Consistency Evaluation Across Domains
This addresses the problem of ensuring factual accuracy in AI-generated text for applications like summarization and verification, representing a strong incremental advance.
The paper tackled the challenge of evaluating factual consistency in text generation by unifying multiple tasks to train models for cross-domain assessment, achieving state-of-the-art performance on a benchmark of 22 datasets.
This work addresses the challenge of factual consistency in text generation systems. We unify the tasks of Natural Language Inference, Summarization Evaluation, Factuality Verification and Factual Consistency Evaluation to train models capable of evaluating the factual consistency of source-target pairs across diverse domains. We rigorously evaluate these against eight baselines on a comprehensive benchmark suite comprising 22 datasets that span various tasks, domains, and document lengths. Results demonstrate that our method achieves state-of-the-art performance on this heterogeneous benchmark while addressing efficiency concerns and attaining cross-domain generalization.