Skip to main content
Benchmark / dataset Authoritative

MentalManip: A Dataset for Fine-grained Analysis of Mental Manipulation in Conversations

A dataset of 4,000 annotated multi-turn dialogues (drawn from movie scripts) labelled for the presence of manipulation, the technique used, and the targeted vulnerability. Evaluates how well models detect and classify manipulative content.

Publisher

Association for Computational Linguistics (ACL 2024)

Published

26 May 2024

Added

today

DOI

Key Findings

  • State-of-the-art models struggle to detect and classify mental manipulation in dialogue
  • Fine-tuning on existing mental-health or toxicity datasets does not close the gap
  • Provides a fine-grained taxonomy of manipulation techniques and targeted vulnerabilities

Methodology Notes

Peer-reviewed dataset paper, ACL 2024 (arXiv 2405.16584, 26 May 2024). Source dialogues are fictional (movie scripts) — a stated ecological-validity caveat.

Sources

arXiv abstract (primary)

ACL Anthology

Archived snapshot (Wayback Machine) — preserved against link rot

Authors

Yuxin Wang, Ivory Yang, Saeed Hassanpour, Soroush Vosoughi

Tags

acl-2024manipulationdatasetconversation

Cite This

APA

Yuxin Wang et al. (2024). MentalManip: A Dataset for Fine-grained Analysis of Mental Manipulation in Conversations. Association for Computational Linguistics (ACL 2024). https://arxiv.org/abs/2405.16584