RLHFlow

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

04:00

2026-08-11

machinebrief.com

artificial-intelligence

Quality-Diversity Stress Tests for Process Reward Models:What Archive Coverage Can and Cannot Certify

A new arXiv study (2608.08008v1) proposes quality-diversity stress testing for process reward models (PRMs) using MAP-Elites, revealing that Qwen2.5-Math-PRM-7B exhibits an aggregation-dependent vulne…

04:00

2026-06-26

arxiv.org

large-language-models

Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training

A new study on Llama 3.1 8B finds that helpfulness post-training (SFT and GRPO) significantly degrades animal compassion values compared to coding-domain post-training, with a 35.7% vs. 65.2% gap on t…

// co-occurs with top 8 entities

Llama 3.1 8B 1 Dolly-15k 1 Magicoder-110K 1 Animal Harm Benchmark 1 MORU benchmark 1 arXiv 1 Qwen2.5-Math-PRM-7B 1 MAP-Elites 1

// topics top 6 topics

ai safety 2 ai research 2 large language models 1 ai ethics 1 artificial intelligence 1 machine learning 1