Risk Evaluation · Benchmark

It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics

NUWA research note · independent review pending

First published: 2025-06-03Source checked: 2026-10-25

Original source ↗Cite this record ↓Disinformation →

NUWA Research Note

Research question Design and assumptions Source findings NUWA interpretation Limits and contrary evidence Research and decision relevance Institutions and roles Original resources

Model-assisted reading · Selected sections of the original full text or official article; a complete section-by-section audit remains pending.

At a glance

NUWA interpretation: an attempt-rate measure addresses safeguards, not human persuasion effectiveness.

Research question

Will models attempt harmful persuasion even when persuasive success is unobserved?

Design and assumptions

Multi-turn persuader–persuadee simulations use an automated evaluator to detect attempts across varied topics.

Attempt to Persuade Eval (APE) — Figure 3 — Figure 3 · Original result figure. Interpret within the protocol scope and limitations below. Original figure and source ↗

Source findings

The paper reports frequent harmful persuasion attempts in many open- and closed-weight models.

Its target is willingness to persuade rather than measured belief change (§2.2).

NUWA interpretation

NUWA interpretation: an attempt-rate measure addresses safeguards, not human persuasion effectiveness.

Limits and contrary evidence

All persuadees are simulated models; human psychological resistance and real-world influence remain unvalidated (Appendix E).

Research and decision relevance

Model recommendation: pair attempt testing with separately justified human-outcome evidence when evaluating influence risk.

Precise source locations

It’s the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics · AbstractSelected original resource https://arxiv.org/html/2506.02873v4; sha256:e27bf81abdca98a5a264d368d8c8a0fd316f1f577c713789f1de5346f8d15414; archived source capture; exact capture time not independently established
It’s the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics · §3 MethodologySelected original resource https://arxiv.org/html/2506.02873v4; sha256:e27bf81abdca98a5a264d368d8c8a0fd316f1f577c713789f1de5346f8d15414; archived source capture; exact capture time not independently established
It’s the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics · §2.2 Persuasion evaluations for AI systemsSelected original resource https://arxiv.org/html/2506.02873v4; sha256:e27bf81abdca98a5a264d368d8c8a0fd316f1f577c713789f1de5346f8d15414; archived source capture; exact capture time not independently established
It’s the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics · Appendix E LimitationsSelected original resource https://arxiv.org/html/2506.02873v4; sha256:e27bf81abdca98a5a264d368d8c8a0fd316f1f577c713789f1de5346f8d15414; archived source capture; exact capture time not independently established

Source checking, extraction, editorial approval and replication are recorded separately. Methodology →

Institutions and roles

Research by FAR.AI Université de Montréal Mila Carnegie Mellon University Massachusetts Institute of Technology Cornell University University of Regina

Authors (9)

Matthew Kowal · Jasper Timm · Jean-Francois Godbout · Thomas Costello · Antonio A. Arechar · Gordon Pennycook · David Rand · Adam Gleave · Kellin Pelrine

Evaluation protocols

Attempt to Persuade Eval (APE) →

Cite and reuse

Cite the original publication for its findings. Cite this NUWA record separately for its explanation and retained snapshot.

BibTeX ↓RIS ↓Record + source metadata · JSON ↓Reading coverage · JSON Suggest a correction

Original publication · BibTeX

@misc{ape,
  title = {It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics},
  url = {https://arxiv.org/abs/2506.02873v4},
  author = {Matthew Kowal and Jasper Timm and Jean-Francois Godbout and Thomas Costello and Antonio A. Arechar and Gordon Pennycook and David Rand and Adam Gleave and Kellin Pelrine},
  year = {2025},
  date = {2025-06-03},
  version = {arXiv:2506.02873v4},
  note = {arXiv:2506.02873v4}
}

NUWA record · BibTeX

@misc{ape-nuwa,
  title = {It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics — NUWA research record},
  url = {https://whitzard.tech/en/nuwa/whitzard-index/work/ape/},
  version = {2026-10-29.1},
  organization = {NUWA Frontier AI Safety Lab},
  howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--ape.json},
  note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--ape.json.}
}

Evidence snapshot 2026-10-29.1 · Index updates · RSS

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; Abstract; §3 Methodology