LLM Response Distortion Across Dark Triad Traits
A study examines how seven state-of-the-art Large Language Models (LLMs) modulate the expression of Machiavellianism, narcissism, and psychopathy under fake-good and fake-bad conditions. The research found that models generally reduce these traits when presented with socially desirable scenarios but increase them in fake-bad contexts. Contextual framing influenced responses more than explicit…
1 source primary source
Key points
- LLMs modulate Dark Triad traits under fake-good/fake-bad conditions
- Machiavellianism and narcissism show strongest response shifts
- Explicit instructions generate stronger distortions than contextual framing
Read the original at arXiv cs.CL · by Victoria Popa, Guglielmo Cola, Caterina Senette, Maurizio Tesconi primary source Open source ↗
Topics · follow one to build your own front page
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us.
More in Generative AI & Models
All →- FairCompressAgent: An Agentic Framework for Fairness-Aware Model Compression · 1 src
- CADWorld: A New Benchmark for Long-Horizon Computer-Aided Design · 1 src
- LLMs outperform traditional Chinese medicine physicians in case evaluations · 1 src
- Non-Standard English Queries Routinely Sent to Lower-Capacity LLMs, Study Finds · 1 src
- SAGE: Streamlines Enterprise Document Conversion · 1 src
Comments
via GitHub Discussions