HH-RLHF

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

08:51

2026-08-20

marktechpost.com

machine-learning

Auditing Preference Biases and Fine-Tuning Language Models with Direct Preference Optimization on Anthropic HH-RLHF Using TRL and LoRA

MarkTechPost published a tutorial on August 20, 2026, detailing an end-to-end workflow for fine-tuning language models with Direct Preference Optimization (DPO), including auditing the Anthropic HH-RL…

04:00

2026-07-28

arxiv.org

artificial-intelligence

Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluation

A new arXiv paper introduces a scalable, inference-only data valuation pipeline that approximates the Shapley value to audit LLM alignment datasets, reducing manual audit search space by 99.1% on Help…

// co-occurs with top 7 entities

Anthropic 2 arXiv 1 HelpSteer2 1 MarkTechPost 1 Direct Preference Optimization 1 TRL 1 LoRA 1

// topics top 6 topics

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