cd /news/large-language-models/mitigating-llm-based-p-hacking-by-pr… · home topics large-language-models article
[ARTICLE · art-42913] src=arxiv.org ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Mitigating LLM-based p-Hacking by Preregistering for the Next LLM

Researchers propose a protocol to mitigate p-hacking in LLM-based research by preregistering experiments and running them on the first eligible model released after registration. Across 20 models and 11 configurations, the protocol blocked p-hack transfer in over 70% of cases. The preregistered experiment confirmed the protocol's effectiveness, with hacking failing to carry over in 6 out of 7 configurations.

read1 min views1 publishedJun 29, 2026

arXiv:2606.27687v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to generate, classify, and annotate data whose outputs feed downstream hypothesis tests. However, LLM-based research is easy to p-hack: a researcher can tune the prompts, decoding parameters, or output format until a desired result is reached. We propose a protocol to mitigate p-hacking in LLM-based research: preregistering the experiment and eligible models, and then running it on the first eligible LLM that is released after the preregistration. The researcher finalizes the procedure on current models, preregisters the analysis plan together with a set of eligible future models, and runs the confirmatory analysis on the first eligible model released afterward. Because this model does not exist at commitment time, it cannot be hacked against; furthermore, configurations that hack one model frequently do not transfer to the next. We evaluate the protocol on two tasks whose true values are known. Across 20 models from four providers and 11 LLM-analysis configurations, the protocol would have blocked successful transfer of the p-hack in 73.9% and 72.7% of cases in the two tasks. Additional analyses reveal that mitigation remains substantial under several stress tests. Finally, putting money where our mouth is, we followed our own protocol and preregistered our experiment. The preregistered experiment confirmed the protocol's effectiveness: out of the 7 configurations that hacked the prior model, the hacking failed to carry over in 6 configurations on the first eligible model released afterward.

── more in #large-language-models 4 stories · sorted by recency
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/mitigating-llm-based…] indexed:0 read:1min 2026-06-29 ·