hallucination detection

SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models EMNLP 2023 When Do Pre-Training Biases Propagate to Downstream Tasks? A Case Study in Text Summarization EACL 2023 A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation ACL 2022 ‘Beach’ to ‘Bitch’: Inadvertent Unsafe Transcription of Kids’ Content on YouTube AAAI 2022 Chart-to-Text: A Large-Scale Benchmark for Chart Summarization ACL 2022 Diving Deep into Modes of Fact Hallucinations in Dialogue Systems EMNLP 2022 Don’t Say What You Don’t Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Search EMNLP 2022 Generation of Patient After-Visit Summaries to Support Physicians COLING 2022 Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization ACL 2022 HaRiM+: Evaluating Summary Quality with Hallucination Risk AACL 2022 Human Ratings Do Not Reflect Downstream Utility: A Study of Free-Text Explanations for Model Predictions EMNLP 2022 Improving Faithfulness by Augmenting Negative Summaries from Fake Documents EMNLP 2022 Mutual Information Alleviates Hallucinations in Abstractive Summarization EMNLP 2022 On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models? NAACL 2022 Unsupervised Token-level Hallucination Detection from Summary Generation By-products EMNLP 2022 MiRANews: Dataset and Benchmarks for Multi-Resource-Assisted News Summarization EMNLP 2021 Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View AAAI 2021 Trainable Ranking Models to Evaluate the Semantic Accuracy of Data-to-Text Neural Generator EMNLP 2021 Controlled Hallucinations: Learning to Generate Faithfully from Noisy Data EMNLP 2020 On Faithfulness and Factuality in Abstractive Summarization ACL 2020 Reducing Quantity Hallucinations in Abstractive Summarization EMNLP 2020 Slot-consistent NLG for Task-oriented Dialogue Systems with Iterative Rectification Network ACL 2020 ToTTo: A Controlled Table-To-Text Generation Dataset EMNLP 2020