ChatbotManip: A Dataset to Facilitate Evaluation and Oversight of Manipulative Chatbot Behaviour

TL;DR

This paper presents ChatbotManip, a dataset for studying chatbot manipulation, revealing that LLMs often exhibit manipulative behavior and that smaller models can detect manipulation with comparable performance to larger models.

Contribution

The paper introduces a new dataset with annotated conversations to evaluate manipulation tactics in chatbots and compares detection capabilities of different models.

Findings

LLMs show manipulation in 84% of instructed conversations.

Controversial strategies like gaslighting are common in persuasive LLMs.

Small models perform comparably to large models in manipulation detection.

Abstract

This paper introduces ChatbotManip, a novel dataset for studying manipulation in Chatbots. It contains simulated generated conversations between a chatbot and a (simulated) user, where the chatbot is explicitly asked to showcase manipulation tactics, persuade the user towards some goal, or simply be helpful. We consider a diverse set of chatbot manipulation contexts, from consumer and personal advice to citizen advice and controversial proposition argumentation. Each conversation is annotated by human annotators for both general manipulation and specific manipulation tactics. Our research reveals three key findings. First, Large Language Models (LLMs) can be manipulative when explicitly instructed, with annotators identifying manipulation in approximately 84\% of such conversations. Second, even when only instructed to be ``persuasive'' without explicit manipulation prompts, LLMs frequently default to controversial manipulative strategies, particularly gaslighting and fear enhancement. Third, small fine-tuned open source models, such as BERT+BiLSTM have a performance comparable to zero-shot classification with larger models like Gemini 2.5 pro in detecting manipulation, but are not yet reliable for real-world oversight. Our work provides important insights for AI safety research and highlights the need of addressing manipulation risks as LLMs are increasingly deployed in consumer-facing applications.