Leveraging Machine-Generated Rationales to Facilitate Social Meaning Detection in Conversations
This work addresses the challenge of understanding subtle social cues in conversations for NLP applications, though it appears incremental as it builds on existing LLM capabilities.
The researchers tackled the problem of detecting implicitly encoded social meaning in conversations by using LLM-generated rationales as augmentations, achieving significant positive impact across 2,340 experimental settings including in-domain, zero-shot, and few-shot scenarios.
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.