Leveraging Machine-Generated Rationales to Facilitate Social Meaning Detection in Conversations
Ritam Dutt, Zhen Wu, Jiaxin Shi, Divyanshu Sheth, Prakhar Gupta, Carolyn Rose
Abstract
We present a generalizable classification approach that leverages Large Language Models (LLMs) to facilitate the detection of implicitly encoded social meaning in conversations. We design a multi-faceted prompt to extract a textual explanation of the reasoning that connects visible cues to underlying social meanings. These extracted explanations or rationales serve as augmentations to the conversational text to facilitate dialogue understanding and transfer. Our empirical results over 2,340 experimental settings demonstrate the significant positive impact of adding these rationales. Our findings hold true for in-domain classification, zero-shot, and few-shot domain transfer for two different social meaning detection tasks, each spanning two different corpora.- Anthology ID:
- 2024.acl-long.373
- Volume:
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6901–6929
- Language:
- URL:
- https://aclanthology.org/2024.acl-long.373
- DOI:
- Cite (ACL):
- Ritam Dutt, Zhen Wu, Jiaxin Shi, Divyanshu Sheth, Prakhar Gupta, and Carolyn Rose. 2024. Leveraging Machine-Generated Rationales to Facilitate Social Meaning Detection in Conversations. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6901–6929, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- Leveraging Machine-Generated Rationales to Facilitate Social Meaning Detection in Conversations (Dutt et al., ACL 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.acl-long.373.pdf