NASA’s new dark energy space telescope can also detect killer asteroids
technologyreview.com·1h ago
AI Research
arXiv CS.AI·Jun 9·5 min read
"I understand your perspective": LLM Persuasion and Sycophancy through the Lens of Communicative Action Theory
TL;DR
Large Language Models (LLMs) have shown potential in generating arguments, but their persuasive capabilities are not well understood. This research applies Jürgen Habermas' Theory of Communicative Action to analyze LLMs' illocutionary intent, which refers to the intended meaning behind statements.
✦ Why It Matters
Engineers can leverage insights on LLM persuasion to enhance user interactions in applications requiring effective communication.
Key Takeaways
- Explore LLMs' capabilities in persuasive communication.
- Apply communicative action theory to evaluate LLM interactions.
- Enhance LLM design for trust-building and knowledge sharing.
- Investigate illocutionary intent in LLM responses.
Full Summary
Large Language Models (LLMs) are increasingly used for generating text, yet their ability to engage in persuasive communication remains underexplored. This study utilizes Jürgen Habermas' Theory of Communicative Action, which focuses on the social aspects of communication, to evaluate whether LLMs can express illocutionary intent—meaning the intended effect of a statement beyond its literal meaning.
Through qualitative analysis, the research examines how LLMs convey knowledge, build trust, and signal similarity in their responses. Results indicate that LLMs can mimic human-like persuasive strategies, suggesting they can effectively engage in nuanced communicative actions.
These findings have implications for improving human-LLM interactions, particularly in applications requiring persuasion or trust-building. Understanding these capabilities can guide engineers in developing more sophisticated conversational agents.