# Unraveling SITT: Social Influence Technique Taxonomy and Detection with LLMs

arXiv: https://arxiv.org/abs/2506.00061 · HTML: https://mlsanity.com/paper/2506.00061/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 36 references that are in the map.
- First posted on arXiv 29 May 2025.

## Builds on (most cited first, 10 of 10)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good](https://mlsanity.com/paper/1906.06725/) (2019)
- [A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI](https://mlsanity.com/paper/2404.15058/) (2024)
- [MentalManip: A Dataset For Fine-grained Analysis of Mental Manipulation in Conversations](https://mlsanity.com/paper/2405.16584/) (2024)
- [Measuring and Improving Persuasiveness of Large Language Models](https://mlsanity.com/paper/2410.02653/) (2024)
- [Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models](https://mlsanity.com/paper/2412.17128/) (2024)
- [Persuasion Should be Double-Blind: A Multi-Domain Dialogue Dataset With Faithfulness Based on Causal Theory of Mind](https://mlsanity.com/paper/2502.21297/) (2025)
- [Communication is All You Need: Persuasion Dataset Construction via Multi-LLM Communication](https://mlsanity.com/paper/2502.08896/) (2025)

## Built on by (most cited first, 2 of 2)

- [From Emotion to Expression: Theoretical Foundations and Resources for Fear Speech](https://mlsanity.com/paper/2601.17132/) (2026)
- [IMPACTeen: Intentions, Manipulation, Persuasion, Annotations, and Consequences in Teen Communication Dataset](https://mlsanity.com/paper/2606.16910/) (2026)

## Abstract (arXiv)

In this work we present the Social Influence Technique Taxonomy (SITT), a comprehensive framework of 58 empirically grounded techniques organized into nine categories, designed to detect subtle forms of social influence in textual content. We also investigate the LLMs ability to identify various forms of social influence. Building on interdisciplinary foundations, we construct the SITT dataset -- a 746-dialogue corpus annotated by 11 experts in Polish and translated into English -- to evaluate the ability of LLMs to identify these techniques. Using a hierarchical multi-label classification setup, we benchmark five LLMs, including GPT-4o, Claude 3.5, Llama-3.1, Mixtral, and PLLuM. Our results show that while some models, notably Claude 3.5, achieved moderate success (F1 score = 0.45 for categories), overall performance of models remains limited, particularly for context-sensitive techniques. The findings demonstrate key limitations in current LLMs' sensitivity to nuanced linguistic cues and underscore the importance of domain-specific fine-tuning. This work contributes a novel resource and evaluation example for understanding how LLMs detect, classify, and potentially replicate strategies of social influence in natural dialogues.