Abstract
Despite the striking advances in recent language generation performance, model-generated responses have suffered from the chronic problem of hallucinations that are either untrue or unfaithful to a given source. Especially in the task of knowledge grounded conversation, the models are required to generate informative responses, but hallucinated utterances lead to miscommunication. In particular, entity-level hallucination that causes critical misinformation and undesirable conversation is one of the major concerns. To address this issue, we propose a post-hoc refinement method called REM. It aims to enhance the quality and faithfulness of hallucinated utterances by refining them based on the source knowledge. If the generated utterance has a low source-faithfulness score with the given knowledge, REM mines the key entities in the knowledge and implicitly uses them for refining the utterances. We verify that our method reduces entity hallucination in the utterance. Also, we show the adaptability and efficacy of REM with extensive experiments and generative results. Our code is available at https://github.com/YOONNAJANG/REM.
Original language | English |
---|---|
Title of host publication | EMNLP 2023 - 2023 Conference on Empirical Methods in Natural Language Processing, Proceedings |
Editors | Houda Bouamor, Juan Pino, Kalika Bali |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 4844-4861 |
Number of pages | 18 |
ISBN (Electronic) | 9798891760608 |
Publication status | Published - 2023 |
Event | 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023 - Hybrid, Singapore, Singapore Duration: 2023 Dec 6 → 2023 Dec 10 |
Publication series
Name | EMNLP 2023 - 2023 Conference on Empirical Methods in Natural Language Processing, Proceedings |
---|
Conference
Conference | 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023 |
---|---|
Country/Territory | Singapore |
City | Hybrid, Singapore |
Period | 23/12/6 → 23/12/10 |
Bibliographical note
Publisher Copyright:©2023 Association for Computational Linguistics.
ASJC Scopus subject areas
- Computational Theory and Mathematics
- Computer Science Applications
- Information Systems
- Linguistics and Language