Analysis of Plan-based Retrieval for Grounded Text Generation

Ameya Godbole, Nicholas Monath, Seungyeon Kim, Ankit Singh Rawat, Andrew McCallum, Manzil Zaheer


Abstract
In text generation, hallucinations refer to the generation of seemingly coherent text that contradicts established knowledge. One compelling hypothesis is that hallucinations occur when a language model is given a generation task outside its parametric knowledge (due to rarity, recency, domain, etc.). A common strategy to address this limitation is to infuse the language models with retrieval mechanisms, providing the model with relevant knowledge for the task. In this paper, we leverage the planning capabilities of instruction-tuned LLMs and analyze how planning can be used to guide retrieval to further reduce the frequency of hallucinations. We empirically evaluate several variations of our proposed approach on long-form text generation tasks. By improving the coverage of relevant facts, plan-guided retrieval and generation can produce more informative responses while providing a higher rate of attribution to source documents.
Anthology ID:
2024.emnlp-main.727
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13101–13119
Language:
URL:
https://aclanthology.org/2024.emnlp-main.727
DOI:
Bibkey:
Cite (ACL):
Ameya Godbole, Nicholas Monath, Seungyeon Kim, Ankit Singh Rawat, Andrew McCallum, and Manzil Zaheer. 2024. Analysis of Plan-based Retrieval for Grounded Text Generation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 13101–13119, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Analysis of Plan-based Retrieval for Grounded Text Generation (Godbole et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.727.pdf