https://scholars.lib.ntu.edu.tw/handle/123456789/640563
標題: | Fidelity-Enriched Contrastive Search: Reconciling the Faithfulness-Diversity Trade-Off in Text Generation | 作者: | Chen, Wei Lin Wu, Cheng Kuang HSIN-HSI CHEN Chen, Chung Chi |
公開日期: | 1-一月-2023 | 來源出版物: | EMNLP 2023 - 2023 Conference on Empirical Methods in Natural Language Processing, Proceedings | 摘要: | In this paper, we address the hallucination problem commonly found in natural language generation tasks. Language models often generate fluent and convincing content but lack consistency with the provided source, resulting in potential inaccuracies. We propose a new decoding method called Fidelity-Enriched Contrastive Search (FECS), which augments the Contrastive Search framework with context-aware regularization terms. FECS promotes tokens that are semantically similar to the provided source while penalizing repetitiveness in the generated text. We demonstrate its effectiveness across two tasks prone to hallucination: abstractive summarization and dialogue generation. Results show that FECS consistently enhances faithfulness across various language model sizes while maintaining output diversity comparable to well-performing decoding algorithms. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/640563 | ISBN: | 9798891760608 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。