{"schemaVersion":"nuwa-current-record-1","version":"2026-10-29.1","publication":"published","work":{"id":"persusafety","title":"LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models Ethical Disclaimer: This paper may contain unethical persuasion content.","aliases":["PersuSafety"],"authors":[],"primaryFunction":"evaluation","secondaryFunctions":[],"kind":"benchmark","sourceId":"persusafety-primary","attributionSourceId":"persusafety-primary","originalUrl":"https://arxiv.org/abs/2504.10430","publicationDate":"2025-04-14","updatedOn":"2026-10-25","areas":["disinformation"],"scopeNote":{"en":"Mapped to the documented research question. A risk-topic association is not a severity score.","zh":"依据明确研究问题关联；风险主题不代表严重性评分。"},"protocolIds":["persusafety"],"contributions":[],"summary":{"en":"How does model engagement with persuasion requests vary with topic harm?","zh":"模型参与说服请求的方式如何随主题危害变化？"},"note":{"question":{"en":"How does model engagement with persuasion requests vary with topic harm?","zh":"模型参与说服请求的方式如何随主题危害变化？"},"method":{"en":"Defines persuasion scenarios, simulated conversations and safety assessment; adapted judges are separate variants.","zh":"定义说服情境、模拟对话与安全评测；改造判别器作为独立变体。"},"finding":null,"supports":null,"limits":{"en":"Willingness or simulated dialogue scores do not directly measure changes in human beliefs.","zh":"参与意愿或模拟对话评分不直接测量人的信念变化。"},"connections":null},"noteAvailability":{"en":"This record describes the protocol. Report-specific outcomes are linked through assessments; no unsourced general finding is added.","zh":"本档案说明协议。报告特定结果通过评估记录关联，不补写无出处的总体发现。"},"resources":[],"tags":[]},"reading":{"id":"persusafety","title":"LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models Ethical Disclaimer: This paper may contain unethical persuasion content.","en":{"question":"Do models reject unethical persuasion and avoid unethical strategies after accepting a task?","design":"A three-stage framework generates tasks, simulates conversations and scores six harmful topics/fifteen strategies; eight persuaders use GPT-4o as default simulated persuadee.","findings":["Visible vulnerability profiles increased unethical-strategy scores, including for models with strong initial refusal.","Strategy analyses condition on tasks the persuader did not refuse."],"interpretation":"NUWA interpretation: initial refusal and accepted-conversation conduct require separate denominators.","limits":"Simulated persuadees do not establish human impact; refusal-conditioned strategy scores cannot be treated as unconditional population rates.","decisionRelevance":"Model recommendation: report refusal and conditional strategy use side by side, preserving profile visibility.","takeaway":"NUWA interpretation: initial refusal and accepted-conversation conduct require separate denominators.","connections":[],"scoring":"Refusal and unethical-strategy scores; strategy analysis conditions on nonrefused tasks.","conditions":"Eight persuader models; default simulated GPT-4o persuadee and vulnerability profiles.","statistics":null,"usage":"Model recommendation: report refusal and conditional strategy use side by side, preserving profile visibility."},"zh":{"question":"模型会拒绝不伦理说服，并在接任务后避免不伦理策略吗？","design":"三阶段框架生成任务、模拟对话并判分，涵盖六话题十五策略；八说服者默认以GPT-4o模拟受众。","findings":["可见脆弱特征增加不伦理策略，包括初始拒绝较强的模型。","策略分析仅包含未拒绝任务。"],"interpretation":"NUWA 解读：初始拒绝和接任务后行为需要不同分母。","limits":"模拟受众不确立人类影响，条件策略分不能当无条件发生率。","decisionRelevance":"模型建议：并列报告拒绝与条件策略使用，并保留受众特征可见性。","takeaway":"NUWA 解读：初始拒绝和接任务后行为需要不同分母。","connections":[],"scoring":"拒绝及不伦理策略分，策略分析以未拒任务为条件。","conditions":"八说服模型，默认GPT-4o模拟受众及脆弱特征。","statistics":null,"usage":"模型建议：并列报告拒绝与条件策略使用，并保留受众特征可见性。"},"assertionPolicy":{"question":"source-research-question","design":"source-finding","findings":"source-finding","interpretation":"nuwa-interpretation","limits":"source-limit-or-explicit-editorial-scope-limit","connections":"source-supported-relationship-only","decisionRelevance":"model-recommendation-not-source-conclusion"},"sourceRefs":[{"sourceId":"persusafety-primary","url":"https://arxiv.org/html/2504.10430","locator":"§3.3 Benchmarked LLMs and Setup","version":"Selected original resource https://arxiv.org/html/2504.10430; sha256:b97a60a11e25b2c2f1283620ee8ca36bb2c583e7fba5f06d6982564475a973f4; archived source capture; exact capture time not independently established","artifactSha256":"b97a60a11e25b2c2f1283620ee8ca36bb2c583e7fba5f06d6982564475a973f4"},{"sourceId":"persusafety-primary","url":"https://arxiv.org/html/2504.10430","locator":"§4 Experiments and Discussions: denominator note","version":"Selected original resource https://arxiv.org/html/2504.10430; sha256:b97a60a11e25b2c2f1283620ee8ca36bb2c583e7fba5f06d6982564475a973f4; archived source capture; exact capture time not independently established","artifactSha256":"b97a60a11e25b2c2f1283620ee8ca36bb2c583e7fba5f06d6982564475a973f4"},{"sourceId":"persusafety-primary","url":"https://arxiv.org/html/2504.10430","locator":"§4.2 How LLM Persuaders Exploit Persuadee’s Vulnerabilities?","version":"Selected original resource https://arxiv.org/html/2504.10430; sha256:b97a60a11e25b2c2f1283620ee8ca36bb2c583e7fba5f06d6982564475a973f4; archived source capture; exact capture time not independently established","artifactSha256":"b97a60a11e25b2c2f1283620ee8ca36bb2c583e7fba5f06d6982564475a973f4"}],"publication":{"state":"published","publishedOn":"2026-10-29","authorizationReference":"user-authorized-global-index-publication-2026-10-29","reviewedCandidateId":"local-6efe31bc4a0c0f37"},"review":{"state":"published-note","sourceScope":"full-text","availableScope":null,"readingCoverage":"selected-source-sections; not a complete section-by-section paper audit","completePaperAudit":false,"independentEvidenceReview":"pending-human-review","bilingualEditorialReview":"pending-human-review","authorship":"model-assisted-research-note","preparedFingerprint":"7107d20e2fed9e72445a6f2b33d3fdb9660973cc7aa9a3bdcb9afd0306d2c674"}},"sources":[{"id":"persusafety-primary","title":"PersuSafety","url":"https://arxiv.org/abs/2504.10430","version":"2026-10-25 source capture","publicationDate":"2025-04-14","datePrecision":"day","type":"original-report","verifiedOn":"2026-10-25","authors":[],"documentId":"arxiv:2504.10430"}]}