Skip to content
Launchpad Library logo

rlhf

3 free resources on this topic. Everything here is free and hand-picked. You can also search within this topic.

arxiv.org
Free
Research Paper
AI Models & Benchmarks

Towards Understanding Sycophancy in Language Models

Authors
Mrinank Sharma, Meg Tong, Tomasz Korbak, David Duvenaud, Amanda Askell, Samuel R. Bowman, Newton Cheng, Esin Durmus, Zac Hatfield-Dodds, Scott R. Johnston, Shauna Kravec, Timothy Maxwell, Sam McCandlish, Kamal Ndousse, Oliver Rausch, Nicholas Schiefer, Da Yan, Miranda Zhang, Ethan Perez
Venue
arXiv preprint
Published
2023-10-20
ID
arXiv:2310.13548

Research paper investigating why AI assistants fine-tuned with human feedback tend to produce responses that match user beliefs rather than truthful ones. Analyzes five state-of-the-art AI assistants across text-generation tasks and the role of human preference data in driving this sycophantic behavior.

#llm#sycophancy#rlhf#ai-safety#arxiv
arxiv.orgAdded Oct 6, 20260 opens
Medium
Free
Article
Technology & Ethics

What Is RLCD? Reinforcement Learning from Contrast Distillation

A plain-language explainer on RLCD, a way of aligning language models by learning from contrasting outputs rather than human ratings alone.

From the site: RLCD is a method developed to adjust language models to human preferences without using human feedback data. This approach aims to address…

Why I recommend it: Good background reading if you want to understand how the models you use are actually steered.

#ai#ai ethics#ai-alignment#ai-safety#explainers#llm#machine-learning#model-training#reinforcement-learning#research#rlhf
MediumAdded Sep 17, 20260 opens
Weights & Biases
Free
Document
AI & Assistive Tools

Reinforcement Learning ebook (Weights & Biases)

A free ebook walking through reinforcement learning from the basics to RLHF, written for practitioners rather than researchers.

From the site: Reinforcement learning (RL) is transforming how reliable AI agents are trained and deployed. Discover real-world use cases, efficiency techniques like LoRA, and practical patterns you can apply today.

Why I recommend it: Free download in exchange for an email address. Solid grounding if you keep seeing "RLHF" and nodding along.

#ai#ai ethics#ebook#free-training#learning#llm#machine-learning#model-training#reinforcement-learning#research#rlhf
Weights & BiasesAdded Sep 17, 20260 opens