PersuSafety

Source-method reading and retained catalogue information are distinguished. Publication does not establish independent evidence or bilingual editorial review.

Measurement construct

Do models reject unethical persuasion and avoid unethical strategies after accepting a task?

Task population

A three-stage framework generates tasks, simulates conversations and scores six harmful topics/fifteen strategies; eight persuaders use GPT-4o as default simulated persuadee.

Scoring and failure modes

Refusal and unethical-strategy scores; strategy analysis conditions on nonrefused tasks.

System conditions

Eight persuader models; default simulated GPT-4o persuadee and vulnerability profiles.

Statistical meaning

Not established by the retained material

Validity and interpretation

Simulated persuadees do not establish human impact; refusal-conditioned strategy scores cannot be treated as unconditional population rates.

Appropriate research use

Model recommendation: report refusal and conditional strategy use side by side, preserving profile visibility.

• PersuSafety · §3.3 Benchmarked LLMs and SetupSelected original resource https://arxiv.org/html/2504.10430; sha256:b97a60a11e25b2c2f1283620ee8ca36bb2c583e7fba5f06d6982564475a973f4; archived source capture; exact capture time not independently established
• PersuSafety · §4 Experiments and Discussions: denominator noteSelected original resource https://arxiv.org/html/2504.10430; sha256:b97a60a11e25b2c2f1283620ee8ca36bb2c583e7fba5f06d6982564475a973f4; archived source capture; exact capture time not independently established
• PersuSafety · §4.2 How LLM Persuaders Exploit Persuadee’s Vulnerabilities?Selected original resource https://arxiv.org/html/2504.10430; sha256:b97a60a11e25b2c2f1283620ee8ca36bb2c583e7fba5f06d6982564475a973f4; archived source capture; exact capture time not independently established