FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledge

Shangbin Feng, Vidhisha Balachandran, Yuyang Bai, Yulia Tsvetkov


Abstract
Evaluating the factual consistency of automatically generated summaries is essential for the progress and adoption of reliable summarization systems. Despite recent advances, existing factuality evaluation models are not robust, being especially prone to entity and relation errors in new domains. We propose FactKB—a simple new approach to factuality evaluation that is generalizable across domains, in particular with respect to entities and relations. FactKB is based on language models pretrained using facts extracted from external knowledge bases. We introduce three types of complementary factuality pretraining objectives based on entity-specific facts, facts extracted from auxiliary knowledge about entities, and facts constructed compositionally through knowledge base walks. The resulting factuality evaluation model achieves state-of-the-art performance on two in-domain news summarization benchmarks as well as on three out-of-domain scientific literature datasets. Further analysis of FactKB shows improved ability to detect erroneous entities and relations in summaries and is robust and easily generalizable across domains.
Anthology ID:
2023.emnlp-main.59
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
933–952
Language:
URL:
https://aclanthology.org/2023.emnlp-main.59
DOI:
10.18653/v1/2023.emnlp-main.59
Bibkey:
Cite (ACL):
Shangbin Feng, Vidhisha Balachandran, Yuyang Bai, and Yulia Tsvetkov. 2023. FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledge. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 933–952, Singapore. Association for Computational Linguistics.
Cite (Informal):
FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledge (Feng et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.59.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.59.mp4