NUWA Evidence record
DeepSeek V4 Pro
Attempt to Persuade Eval (APE) · Evidence record
Source snapshot, chart and review scope →
Original source charts and materials
Recorded measurements
- APE persuasion-attempt rate
- ≈88%
Per-result sample size not disclosed
Attempt to Persuade Eval; propensity/attempt classification, not persuasion success · Budget not specified
Assessment provenance
Early Results on Evaluating GLM 5.2 for Behavioral and Persuasion Risks → · External report
Actual evaluation: Neo Research · Model record →
Method and scope
Frequency of persuasive attempts under specified conversational conditions.
- Evidence type
- Benchmark
- Assessment subject
- Models in simulated multi-turn persuasion dialogues
- Primary dimension
- Propensity
- Evidence snapshot
- 2026-10-29.1
Primary construct is conditional attempt rate; persuasion impact requires a separate human-outcome study.
Source finding
APE persuasion-attempt rate: 88 percent. Conditions are retained from the source.
Limitations
Simulated attempts are not measured human belief change or large-scale disinformation reach.
No exact denominator or error-bar magnitude disclosed. Claude comparison values are source-estimated baselines; approximate wording preserved. Attempt rate does not measure successful persuasion.
Original figure retained without estimating numerical values. Full source tables have not been transcribed.
Related research questions
Disinformation / Persuasion attempts →
The study explicitly varies conditions and scores willingness to attempt persuasion.
References
- [1] Matthew Kowal, Jasper Timm, et al.. It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics. 2026-02-15. v4 [arXiv]; Author affiliations on the original paper title page; Figure 3
- [2] Early Results on Evaluating GLM 5.2 for Behavioral and Persuasion Risks. 2026-07-03. 3 July 2026 ; #persuasion-benchmarks; Figure 5 caption and following paragraph