Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarization
원문 초록
Detecting factual inconsistency for long document summarization remains challenging, given the complex structure of the source article and long summary length. In this work, we study factual inconsistency errors and connect them with a line of discourse analysis. We find that errors are more common in complex sentences and are associated with several discourse features. We propose a framework that decomposes long texts into discourse-inspired chunks and utilizes discourse information to better aggregate sentence-level scores predicted by natural language inference models. Our approach shows improved performance on top of different model baselines over several evaluation benchmarks, covering rich domains of texts, focusing on long document summarization. This underscores the significance of incorporating discourse features in developing models for scoring summaries for long document factual inconsistency.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
A MISMATCHED Benchmark for Scientific Natural Language Inference
Parameter-Efficient Transformer Embeddings
Thunder-NUBench: A Benchmark for LLMs' Sentence-Level Negation Understanding
Document Attribution: Examining Citation Relationships using Large Language Models
SALAD: Improving Robustness and Generalization through Contrastive Learning with Structure-Aware and LLM-Driven Augmented Data
Negation: A Pink Elephant in the Large Language Models' Room?
토론
이 논문과 연결된 포럼 글이 아직 없습니다.