Instructed Language Models with Retrievers Are Powerful Entity Linkers

Zilin Xiao, Ming Gong, Jie Wu, Xingyao Zhang, Linjun Shou, Daxin Jiang


Abstract
Generative approaches powered by large language models (LLMs) have demonstrated emergent abilities in tasks that require complex reasoning abilities. Yet the generative nature still makes the generated content suffer from hallucinations, thus unsuitable for entity-centric tasks like entity linking (EL) requiring precise entity predictions over a large knowledge base. We present Instructed Generative Entity Linker (INSGENEL), the first approach that enables casual language models to perform entity linking over knowledge bases. Several methods of equipping language models with EL ability were proposed in this work, including (i) a sequence-to-sequence training EL objective with instruction-tuning, (ii) a novel generative EL framework based on a light-weight potential mention retriever that frees the model from heavy and non-parallelizable decoding, achieving 4× speedup without compromise on linking metrics. INSGENEL outperforms previous generative alternatives with +6.8 F1 points gain on average, also with a huge advantage in training data efficiency and training compute consumption. In addition, our skillfully-engineered in-context learning (ICL) framework for EL still lags behind INSGENEL significantly, reaffirming that the EL task remains a persistent hurdle for general LLMs.
Anthology ID:
2023.emnlp-main.139
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:
2267–2282
Language:
URL:
https://aclanthology.org/2023.emnlp-main.139
DOI:
10.18653/v1/2023.emnlp-main.139
Bibkey:
Cite (ACL):
Zilin Xiao, Ming Gong, Jie Wu, Xingyao Zhang, Linjun Shou, and Daxin Jiang. 2023. Instructed Language Models with Retrievers Are Powerful Entity Linkers. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 2267–2282, Singapore. Association for Computational Linguistics.
Cite (Informal):
Instructed Language Models with Retrievers Are Powerful Entity Linkers (Xiao et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.139.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.139.mp4