A two-stage introspection prompt, SELF-PERCEPT, modestly improves LLM detection of mental manipulation in multi-party dialogues on a new 220-dialogue dataset.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SELF-PERCEPT: Introspection Improves Large Language Models' Detection of Multi-Person Mental Manipulation in Conversations
A two-stage introspection prompt, SELF-PERCEPT, modestly improves LLM detection of mental manipulation in multi-party dialogues on a new 220-dialogue dataset.