Unraveling SITT: Social Influence Technique Taxonomy and Detection with LLMs

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Mieleszczenko-Kowszewicz, Wiktoria, Bajcar, Beata, Szczęsny, Aleksander, Markiewicz, Maciej, Babiak, Jolanta, Dyczek, Berenika, Kazienko, Przemysław
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910977563295744
author Mieleszczenko-Kowszewicz, Wiktoria
Bajcar, Beata
Szczęsny, Aleksander
Markiewicz, Maciej
Babiak, Jolanta
Dyczek, Berenika
Kazienko, Przemysław
author_facet Mieleszczenko-Kowszewicz, Wiktoria
Bajcar, Beata
Szczęsny, Aleksander
Markiewicz, Maciej
Babiak, Jolanta
Dyczek, Berenika
Kazienko, Przemysław
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00061
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unraveling SITT: Social Influence Technique Taxonomy and Detection with LLMs
Mieleszczenko-Kowszewicz, Wiktoria
Bajcar, Beata
Szczęsny, Aleksander
Markiewicz, Maciej
Babiak, Jolanta
Dyczek, Berenika
Kazienko, Przemysław
Computation and Language
Artificial Intelligence
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.
title Unraveling SITT: Social Influence Technique Taxonomy and Detection with LLMs
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2506.00061