Don't Believe Everything You Read: Enhancing Summarization Interpretability through Automatic Identification of Hallucinations in Large Language Models (2312.14346v2)
Abstract: LLMs are adept at text manipulation -- tasks such as machine translation and text summarization. However, these models can also be prone to hallucination, which can be detrimental to the faithfulness of any answers that the model provides. Recent works in combating hallucinations in LLMs deal with identifying hallucinated sentences and categorizing the different ways in which models hallucinate. This paper takes a deep dive into LLM behavior with respect to hallucinations, defines a token-level approach to identifying different kinds of hallucinations, and further utilizes this token-level tagging to improve the interpretability and faithfulness of LLMs in dialogue summarization tasks. Through this, the paper presents a new, enhanced dataset and a new training paradigm.
- e-snli: Natural language inference with natural language explanations.
- SAMSum corpus: A human-annotated dialogue dataset for abstractive summarization. In Proceedings of the 2nd Workshop on New Frontiers in Summarization, pages 70–79, Hong Kong, China. Association for Computational Linguistics.
- Alon Jacovi and Yoav Goldberg. 2020. Towards faithfully interpretable nlp systems: How should we define and evaluate faithfulness?
- Survey of hallucination in natural language generation. ACM Computing Surveys, 55(12):1–38.
- Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension.
- Chin-Yew Lin. 2004a. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74–81, Barcelona, Spain. Association for Computational Linguistics.
- Chin-Yew Lin. 2004b. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out, pages 74–81.
- Towards faithful model explanation in nlp: A survey.
- On faithfulness and factuality in abstractive summarization. arXiv preprint arXiv:2005.00661.
- Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318.
- CONFIT: Toward faithful dialogue summarization with linguistically-informed contrastive fine-tuning. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics.
- Attention is all you need.
- Big bird: Transformers for longer sequences. Advances in neural information processing systems, 33:17283–17297.
- Using “annotator rationales” to improve machine learning for text categorization. In Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference, pages 260–267, Rochester, New York. Association for Computational Linguistics.
- Xiaodong Zhang and Houfeng Wang. 2016. A joint model of intent determination and slot filling for spoken language understanding. In IJCAI, volume 16, pages 2993–2999.
- Detecting hallucinated content in conditional neural sequence generation. arXiv preprint arXiv:2011.02593.
- Detecting hallucinated content in conditional neural sequence generation.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.