{"schemaVersion":"nuwa-current-record-1","version":"2026-10-29.1","publication":"published","work":{"id":"neo-glm52-report","title":"Early Results on Evaluating GLM 5.2 for Behavioral and Persuasion Risks","aliases":[],"authors":[],"primaryFunction":"evaluation","secondaryFunctions":[],"kind":"technical-report","sourceId":"neo-glm52-source","attributionSourceId":"neo-glm52-source","originalUrl":"https://neoresearch.ai/research/glm-5-2-behavioral-persuasion-evaluation/","publicationDate":"2026-07-03","updatedOn":"2026-10-25","areas":["autonomy","deception","cybersecurity","cbrn","disinformation"],"scopeNote":{"en":"Reported results retain their original evaluator, configuration and measurement scope. NUWA organizes and interprets the evidence; it has not independently reproduced these experiments.","zh":"结果保留原始执行方、配置与测量范围。NUWA 整理和解读证据，未独立复现这些实验。"},"protocolIds":["mask","deceptionbench","ape","persusafety","agentic-misalignment"],"contributions":[{"organizationId":"neo","role":"research","sourceId":"neo-glm52-source","locator":"Report masthead and stated evaluation methodology"}],"summary":{"en":"The note reports scenario-dependent behavior and an uncertain decline in verbalized evaluation awareness; silence is not evidence of absent awareness.","zh":"报告记录随情境变化的行为和不确定的显式评测感知下降；不表达不代表没有感知。"},"note":{"question":{"en":"How does GLM-5.2 respond to pressure, persuasion requests and evaluation cues?","zh":"GLM-5.2 如何应对压力、说服请求和评测线索？"},"method":{"en":"MASK, DeceptionBench, Gram, APE, modified PersuSafety judging and verbalized-awareness analyses. Claude comparisons use different releases across tests.","zh":"采用 MASK、DeceptionBench、Gram、APE、改造 PersuSafety 判别和显式感知分析；各测试的 Claude 对照版本不同。"},"finding":{"en":"The note reports scenario-dependent behavior and an uncertain decline in verbalized evaluation awareness; silence is not evidence of absent awareness.","zh":"报告记录随情境变化的行为和不确定的显式评测感知下降；不表达不代表没有感知。"},"supports":null,"limits":{"en":"Controlled tasks, elicitation, benchmark familiarity and configuration differences constrain generalization to deployment.","zh":"受控任务、诱发方式、基准熟悉程度和配置差异限制对部署的外推。"},"connections":null},"resources":[],"tags":[]},"reading":{"id":"neo-glm52-report","title":"Early Results on Evaluating GLM 5.2 for Behavioral and Persuasion Risks","en":{"question":"How does GLM-5.2 behave on pressured honesty, harmful persuasion and evaluation-awareness probes?","design":"The note combines MASK, DeceptionBench, four Gram seeds, persuasion tests and a familiar-scenario awareness measurement.","findings":["MASK honesty was 55%; single-/multi-turn DeceptionBench rates were 11.3%/16.7%.","Awareness dropped from GLM-5.1’s 39% to 5.2’s 32% in this setup; the cause is unresolved."],"interpretation":"NUWA interpretation: lower verbalized awareness cannot be assumed to mean lower underlying awareness.","limits":"Claude reference models vary by benchmark; some comparisons reuse prior/public results, so there is no single matched reference model throughout.","decisionRelevance":"Model recommendation: cite benchmark-specific comparator identity and distinguish measured signals from speculative explanations.","takeaway":"NUWA interpretation: lower verbalized awareness cannot be assumed to mean lower underlying awareness.","connections":[],"scoring":null,"conditions":null,"statistics":"MASK honesty was 55%; single-/multi-turn DeceptionBench rates were 11.3%/16.7%. Awareness dropped from GLM-5.1’s 39% to 5.2’s 32% in this setup; the cause is unresolved.","usage":"Model recommendation: cite benchmark-specific comparator identity and distinguish measured signals from speculative explanations."},"zh":{"question":"GLM-5.2在压力诚实、有害说服和评测意识测试表现如何？","design":"研究札记结合MASK、DeceptionBench、四个Gram种子、说服测试与熟悉场景意识测量。","findings":["MASK诚实55%，单多轮DeceptionBench为11.3%、16.7%。","此设置意识从GLM-5.1的39%降至5.2的32%，原因未明。"],"interpretation":"NUWA 解读：较少说出意识不能假定潜在意识降低。","limits":"Claude参考随基准变化，部分重用旧或公开结果，未统一匹配同一参考模型。","decisionRelevance":"模型建议：逐基准注明比较身份，区分测得信号与猜测解释。","takeaway":"NUWA 解读：较少说出意识不能假定潜在意识降低。","connections":[],"scoring":null,"conditions":null,"statistics":"MASK诚实55%，单多轮DeceptionBench为11.3%、16.7%。 此设置意识从GLM-5.1的39%降至5.2的32%，原因未明。","usage":"模型建议：逐基准注明比较身份，区分测得信号与猜测解释。"},"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":"neo-glm52-source","url":"https://neoresearch.ai/research/glm-5-2-behavioral-persuasion-evaluation/","locator":"§1 Behavioral","version":"Selected original resource https://neoresearch.ai/research/glm-5-2-behavioral-persuasion-evaluation/; sha256:275116beeb47908130d9fca47e1fab8315a6d1a0b018305f771021302c3f1e42; archived source capture; exact capture time not independently established","artifactSha256":"275116beeb47908130d9fca47e1fab8315a6d1a0b018305f771021302c3f1e42"},{"sourceId":"neo-glm52-source","url":"https://neoresearch.ai/research/glm-5-2-behavioral-persuasion-evaluation/","locator":"§2 Persuasion benchmarks","version":"Selected original resource https://neoresearch.ai/research/glm-5-2-behavioral-persuasion-evaluation/; sha256:275116beeb47908130d9fca47e1fab8315a6d1a0b018305f771021302c3f1e42; archived source capture; exact capture time not independently established","artifactSha256":"275116beeb47908130d9fca47e1fab8315a6d1a0b018305f771021302c3f1e42"},{"sourceId":"neo-glm52-source","url":"https://neoresearch.ai/research/glm-5-2-behavioral-persuasion-evaluation/","locator":"§3 Evaluation awareness","version":"Selected original resource https://neoresearch.ai/research/glm-5-2-behavioral-persuasion-evaluation/; sha256:275116beeb47908130d9fca47e1fab8315a6d1a0b018305f771021302c3f1e42; archived source capture; exact capture time not independently established","artifactSha256":"275116beeb47908130d9fca47e1fab8315a6d1a0b018305f771021302c3f1e42"},{"sourceId":"neo-glm52-source","url":"https://neoresearch.ai/research/glm-5-2-behavioral-persuasion-evaluation/","locator":"§4 Conclusion","version":"Selected original resource https://neoresearch.ai/research/glm-5-2-behavioral-persuasion-evaluation/; sha256:275116beeb47908130d9fca47e1fab8315a6d1a0b018305f771021302c3f1e42; archived source capture; exact capture time not independently established","artifactSha256":"275116beeb47908130d9fca47e1fab8315a6d1a0b018305f771021302c3f1e42"}],"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":"0b4dcba92aa4ebe8c2c7995a380e1ed2bfe1f67ba205c5d02246409ecc74fe75"}},"sources":[{"id":"neo-glm52-source","title":"Early Results on Evaluating GLM 5.2 for Behavioral and Persuasion Risks","url":"https://neoresearch.ai/research/glm-5-2-behavioral-persuasion-evaluation/","version":"3 July 2026","publicationDate":"2026-07-03","datePrecision":"day","type":"original-report","verifiedOn":"2026-10-25","authors":[],"documentId":"https://neoresearch.ai/research/glm-5-2-behavioral-persuasion-evaluation"}]}