PaulR11/training-runs-multi-target

GRPO Training Runs — Multi-Target (5-Model Pool) Part of the data release for "Training Alignment Auditors via Reinforcement Learning" (ICLR 2026). Four GRPO runs using a 5-model target pool (Gemini 3 Flash, Grok 4.1 Fast, Seed 2.0 Lite, Llama 3.3 70B, GPT-4.1-mini) with target-identity anonymization. All targets present as "PRISM-4 by Nexus Research" to prevent the auditor from identifying target family. mt3_2f_grpo_mt_v3_2fp/ — PV2 intragroup pairwise, 2/8 FP… See the full description on the dataset page: https://huggingface.co/datasets/PaulR11/training-runs-multi-target.

<iframe src="https://silytics.si/embed/item/df065760-ecc3-426d-a0a9-41250ec12a96" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Silytics shows public metadata from Hugging Face and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.