Making Document-Level Information Extraction Right for the Right Reasons
원문 초록
Document-level models for information extraction tasks like slot-filling are flexible: they can be applied to settings where information is not necessarily localized in a single sentence. For example, key features of a diagnosis in a radiology report may not be explicitly stated in one place, but nevertheless can be inferred from parts of the report's text. However, these models can easily learn spurious correlations between labels and irrelevant information. This work studies how to ensure that these models make correct inferences from complex text and make those inferences in an auditable way: beyond just being right, are these models "right for the right reasons?" We experiment with post-hoc evidence extraction in a predict-select-verify framework using feature attribution techniques. We show that regularization with small amounts of evidence supervision during training can substantially improve the quality of extracted evidence. We evaluate on two domains: a small-scale labeled dataset of brain MRI reports and a large-scale modified version of DocRED (Yao et al., 2019) and show that models' plausibility can be improved with no loss in accuracy.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs
Invocable APIs derived from NL2SQL datasets for LLM Tool-Calling Evaluation
Interpretable and Robust Dialogue State Tracking via Natural Language Summarization with LLMs
A physics-informed Bayesian optimization method for rapid development of electrical machines
Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression
Mitigating Object Hallucinations via Sentence-Level Early Intervention
토론
이 논문과 연결된 포럼 글이 아직 없습니다.