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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publicationNLP+CSS 2024 - 6thWorkshop on Natural Language Processing and Computational Social Science, Proceedings of the Workshop
EditorsDallas Card, Anjalie Field, Dirk Hovy, Katherine Keith
PublisherAssociation for Computational Linguistics (ACL)
Pages68-85
Number of pages18
ISBN (Electronic)9798891761124
StatePublished - 2024
Event6thWorkshop on Natural Language Processing and Computational Social Science, NLP+CSS 2024 - Mexico City, Mexico
Duration: Jun 21 2024 → …

Publication series

NameNLP+CSS 2024 - 6thWorkshop on Natural Language Processing and Computational Social Science, Proceedings of the Workshop

Conference

Conference6thWorkshop on Natural Language Processing and Computational Social Science, NLP+CSS 2024
Country/TerritoryMexico
CityMexico City
Period6/21/24 → …

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Networks and Communications
  • Hardware and Architecture
  • Information Systems
  • Software

Fingerprint

Dive into the research topics of 'Retrieval Augmented Generation of Subjective Explanations for Socioeconomic Scenarios'. Together they form a unique fingerprint.

Cite this