Pith. sign in

REVIEW 3 cited by

Enhanced Detection of Conversational Mental Manipulation Through Advanced Prompting Techniques

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2408.07676 v1 pith:3N4ZHVFX submitted 2024-08-14 cs.CL

Ivory Yang , Xiaobo Guo , Sean Xie , Soroush Vosoughi This is my paper · ORCID
classification cs.CL
keywords promptingmanipulationmentaltechniquesdetectionadvancedzero-shotbinary
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This study presents a comprehensive, long-term project to explore the effectiveness of various prompting techniques in detecting dialogical mental manipulation. We implement Chain-of-Thought prompting with Zero-Shot and Few-Shot settings on a binary mental manipulation detection task, building upon existing work conducted with Zero-Shot and Few- Shot prompting. Our primary objective is to decipher why certain prompting techniques display superior performance, so as to craft a novel framework tailored for detection of mental manipulation. Preliminary findings suggest that advanced prompting techniques may not be suitable for more complex models, if they are not trained through example-based learning.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Communication is All You Need: Persuasion Dataset Construction via Multi-LLM Communication

    cs.CL 2025-02 conditional novelty 6.0 of 10

    A six-role multi-LLM communication framework generates persuasive dialogue data that human judges find nearly indistinguishable from human-written rewrites.

  2. Detecting Conversational Mental Manipulation with Intent-Aware Prompting

    cs.CL 2024-12 conditional novelty 6.0 of 10

    Adding per-speaker intent summaries to an LLM prompt reduces false negatives in mental manipulation detection by 30.5% versus zero-shot prompting on the MentalManip dataset.

  3. Explainable Detection of Implicit Influential Patterns in Conversations via Data Augmentation

    cs.CL 2025-06 conditional novelty 4.0 of 10

    A two-phase LoRA fine-tuning pipeline, trained on line-level labels generated by a reasoning language model, improves detection of implicit mental manipulation in the MentalManip conversation benchmark.

Pith tools