The exact text we saved

This is the version exactly as it was saved, character for character. The SHA-256 hash below is a 64-character code worked out from that text. Run the same text through SHA-256 and you get the same code; change a single letter and the code comes out completely different. Each version also stores the previous version’s hash, which chains them together so no version can be swapped out quietly.

TRUVACE RECORD VERSION
record: TRV-2026-2706
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-11-12T17:12:10.382214Z
status: published
lens: g_space
sector: science
headline: A meta-analysis of the persuasive power of large language models
dek: Large language models (LLMs) are increasingly used for persuasion, such as in political communication and marketing, where they affect how people think, choose, and act. Yet, empirical findings on the effectiveness of LLMs in persuasion compared to humans remain inconsistent. The aim of this study was to systematically review and meta-analytically assess whether LLMs differ from humans in persuasive effectiveness, and under which contextual conditions LLMs are particularly effective. We identified 7 studies with…
gain_title: A meta-analysis of 7 studies with 17,422 participants found no significant overall difference in persuasiveness between LLM-generated and human-written messages, so the models matched human persuaders on average.
problem_title: (none)
trace_subject: (none)
gain_reading: A meta-analysis of 7 studies with 17,422 participants found no significant overall difference in persuasiveness between LLM-generated and human-written messages, so the models matched human persuaders on average.
gain_evidence: The results show no significant overall difference in persuasive performance between LLMs and humans
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers pooled 12 effect sizes from 7 experiments, covering 17,422 participants, that directly compared persuasion by large language models with persuasion by human communicators. On average they found no significant difference between the two.

The pooled result hides wide variation between studies. The authors say how persuasive a model is seems to depend on the model, on whether the exchange is a single message or an interactive conversation, and on the topic, though no single factor was significant on its own.

The evidence base is small and narrow. Participants came mainly from English-speaking countries and online panels, and the authors treat the combined-factor findings as possibly overfitted.
limitation: Only 7 studies with 12 effect sizes were eligible, which limits the subgroup analyses. All studies recruited from online convenience panels, so the findings may not generalize beyond U.S.-centric Western samples, and several included studies are not peer reviewed.
tag: Evidence-backed gain
key_points: The review searched Web of Science, ACM Digital Library, arXiv, SSRN and OSF for English-language studies published after December 2022, up to May 22, 2025. | Seven studies with 12 independent effect sizes met the strict criteria; four papers were dropped because their authors did not supply missing statistics. | The pooled difference in persuasiveness between LLMs and humans was very small and not statistically significant, and the result held when only peer-reviewed studies were analysed. | Heterogeneity between studies was substantial, which the authors read as persuasiveness depending on context. | Across the 12 estimates, 7 used one-shot messages and 5 used interactive dialogue; models ranged from GPT-3 and GPT-3.5 to GPT-4 and Claude Sonnet. | In a combined model, interactive setups beat one-shot messages, Claude 3.x trailed GPT-4.x, and political topics were less persuasive than health topics. | Early studies from 2021 and 2022 leaned toward LLMs being somewhat less persuasive than humans, but adding 2024 and 2025 studies moved the cumulative estimate toward zero and slightly positive.
rundown: The authors followed PRISMA 2020 guidelines and required a direct between-subjects comparison of LLM-generated and human-generated content. None of the included studies reported standardized effect sizes, so the authors computed Hedges' g from means, standard deviations and test statistics. They used a random-effects model with a restricted maximum-likelihood estimator.

In single-factor analyses, no moderator reached significance: not the model (GPT-3.x with 5 effect sizes, GPT-4.x with 4, Claude 3.x with 3), not the format, and not the domain. Politics and health were almost equally effective, while a catch-all category of propaganda, quiz and mixed tasks looked slightly weaker. The authors say small subgroups may have left these tests underpowered.

When all factors were entered together, the model explained a large share of between-study variance and residual heterogeneity became low. GPT-3.x then outperformed GPT-4.x once domain and interaction type were controlled for, which suggests the apparent GPT-4 advantage in the single-factor analysis reflected study design. The authors warn the drop in heterogeneity may reflect overfitting.

Across the reviewed studies, human messages tended to be more emotionally vivid and personally engaging, while LLM messages leaned on analytical reasoning and coherence. Only one included study tested personalization, and it showed a notably high positive effect. Leave-one-out checks left the non-significant pooled result unchanged, and trim-and-fill added no missing studies.
sources:
- peer_reviewed | Scientific Reports | https://doi.org/10.1038/s41598-025-30783-y | 2025-12-12
prev: 0000000000000000000000000000000000000000000000000000000000000000

SHA-256 hash

26cae46085dcc536aff043db171d3ad495fdb6f77b731c5f36c20a294486fd5c

Previous version’s hash

0000000000000000000000000000000000000000000000000000000000000000