Retrieval Augmented Generation of Subjective Explanations for Socioeconomic Scenarios

Razvan-Gabriel Dumitru, Maria Alexeeva, Keith Alcock, Nargiza Ludgate, Cheonkam Jeong, Zara Fatima Abdurahaman, Prateek Puri, Brian Kirchhoff, Santadarshan Sadhu, Mihai Surdeanu


Abstract
We introduce a novel retrieval augmented generation approach that explicitly models causality and subjectivity. We use it to generate explanations for socioeconomic scenarios that capture beliefs of local populations. Through intrinsic and extrinsic evaluation, we show that our explanations, contextualized using causal and subjective information retrieved from local news sources, are rated higher than those produced by other large language models both in terms of mimicking the real population and the explanations quality. We also provide a discussion of the role subjectivity plays in evaluation of this natural language generation task.
Anthology ID:
2024.nlpcss-1.6
Volume:
Proceedings of the Sixth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS 2024)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Dallas Card, Anjalie Field, Dirk Hovy, Katherine Keith
Venues:
NLP+CSS | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
68–85
Language:
URL:
https://aclanthology.org/2024.nlpcss-1.6
DOI:
10.18653/v1/2024.nlpcss-1.6
Bibkey:
Cite (ACL):
Razvan-Gabriel Dumitru, Maria Alexeeva, Keith Alcock, Nargiza Ludgate, Cheonkam Jeong, Zara Fatima Abdurahaman, Prateek Puri, Brian Kirchhoff, Santadarshan Sadhu, and Mihai Surdeanu. 2024. Retrieval Augmented Generation of Subjective Explanations for Socioeconomic Scenarios. In Proceedings of the Sixth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS 2024), pages 68–85, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Retrieval Augmented Generation of Subjective Explanations for Socioeconomic Scenarios (Dumitru et al., NLP+CSS-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.nlpcss-1.6.pdf