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.
Analyzing x’s web of influence: Dis- secting news sharing dynamics through credibility and popularity with transfer entropy and multiplex network measures
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Explainable Detection of Implicit Influential Patterns in Conversations via Data Augmentation
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.