Helpfulness
llama-3.1-8b-oracle-rm-hh-rlhf-helpfulnessdsp_roberta_base_dapt_reviews_tapt_amazon_helpfulness_115Kdsp_roberta_base_tapt_amazon_helpfulness_115Kparaphrase-multilingual-MiniLM-L12-v2-helpfulnessSmolLM-360M-Helpsteer2-Helpfulness-merged-fp16Llama-3.1-8B-SafeRLHF-HTMNPO-helpfulnessairbnb-reviews-helpfulness-classifier-roberta-base20260228-helpfulness-Qwen3-0.6B_grpo_baseline_seed_42_wo_warmup
