# Reinforcement Learning from Human Feedback

arXiv: https://arxiv.org/abs/2504.12501 · HTML: https://mlsanity.com/paper/2504.12501/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 110 of its 417 references that are in the map.
- First posted on arXiv 16 Apr 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## Builds on (most cited first, 30 of 110)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)

## Built on by (most cited first, 30 of 58)

- [SAM 3D: 3Dfy Anything in Images](https://mlsanity.com/paper/2511.16624/) (2025)
- [Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy](https://mlsanity.com/paper/2507.01352/) (2025)
- [RewardBench 2: Advancing Reward Model Evaluation](https://mlsanity.com/paper/2506.01937/) (2025)
- [Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI](https://mlsanity.com/paper/2511.01689/) (2025)
- [Guiding Generative Models to Uncover Diverse and Novel Crystals via Reinforcement Learning](https://mlsanity.com/paper/2511.07158/) (2025)
- [Text2Grad: Reinforcement Learning from Natural Language Feedback](https://mlsanity.com/paper/2505.22338/) (2025)
- [A Comedy of Estimators: On KL Regularization in RL Training of LLMs](https://mlsanity.com/paper/2512.21852/) (2025)
- [Pairwise Calibrated Rewards for Pluralistic Alignment](https://mlsanity.com/paper/2506.06298/) (2025)
- [Agent-in-the-Loop: A Data Flywheel for Continuous Improvement in LLM-based Customer Support](https://mlsanity.com/paper/2510.06674/) (2025)
- [Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants](https://mlsanity.com/paper/2605.09808/) (2026)
- [Using Reinforcement Learning to Train Large Language Models to Explain Human Decisions](https://mlsanity.com/paper/2505.11614/) (2025)
- [ReDit: Reward Dithering for Improved LLM Policy Optimization](https://mlsanity.com/paper/2506.18631/) (2025)
- [Survey: Multi-Armed Bandits Meet Large Language Models](https://mlsanity.com/paper/2505.13355/) (2025)
- [Pharmacist: Safety Alignment Data Curation for Large Language Models against Harmful Fine-tuning](https://mlsanity.com/paper/2510.10085/) (2025)
- [Generative AI collective behavior needs an interactionist paradigm](https://mlsanity.com/paper/2601.10567/) (2026)
- [Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models](https://mlsanity.com/paper/2510.21978/) (2025)
- [SycoEval-EM: Sycophancy Evaluation of Large Language Models in Simulated Clinical Encounters for Emergency Care](https://mlsanity.com/paper/2601.16529/) (2026)
- [Why GRPO Needs Normalization: A Local-Curvature Perspective on Adaptive Gradients](https://mlsanity.com/paper/2601.23135/) (2026)
- [Personalization Increases Affective Alignment but Has Role-Dependent Effects on Epistemic Independence in LLMs](https://mlsanity.com/paper/2603.00024/) (2026)
- [Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security](https://mlsanity.com/paper/2605.23989/) (2026)
- [RoleRMBench & RoleRM: Towards Reward Modeling for Profile-Based Role Play in Dialogue Systems](https://mlsanity.com/paper/2512.10575/) (2025)
- [Operationalising the Superficial Alignment Hypothesis via Task Complexity](https://mlsanity.com/paper/2602.15829/) (2026)
- [Steering LLMs for Culturally Localized Generation](https://mlsanity.com/paper/2603.23301/) (2026)
- [Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs](https://mlsanity.com/paper/2606.32032/) (2026)
- [Physics of Learning: A Lagrangian perspective to different learning paradigms](https://mlsanity.com/paper/2509.21049/) (2025)
- [DSCD: Large Language Model Detoxification with Self-Constrained Decoding](https://mlsanity.com/paper/2510.13183/) (2025)
- [Sophia: A Persistent Agent Framework of Artificial Life](https://mlsanity.com/paper/2512.18202/) (2025)
- [Object Hallucination-Free Reinforcement Unlearning for Vision-Language Models](https://mlsanity.com/paper/2605.08031/) (2026)
- [DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification](https://mlsanity.com/paper/2605.09269/) (2026)
- [Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure](https://mlsanity.com/paper/2605.27996/) (2026)

## Abstract (arXiv)

Reinforcement learning from human feedback (RLHF) has become a crucial tool to build the latest machine learning systems at scale. The field grew around the core methods of RLHF into today's broader suite of post-training techniques. In this book, we give a comprehensive introduction to the core methods for post-training models for people with some level of quantitative background, organized around the canonical RLHF recipe. The book starts with what RLHF does and why it was created, with seminal technical milestones in its young history and a primer on reinforcement learning context needed to understand the book. The core of the book details every optimization stage in using RLHF, from starting with instruction tuning to training a reward model and finally all of rejection sampling, reinforcement learning, on-policy distillation, and direct alignment algorithms. The book also discusses broader topics, such as the origins of RLHF -- both in recent literature and in a convergence of disparate fields of science in economics, philosophy, and optimal control. The book concludes with advanced topics -- understudied or emerging research questions in synthetic data, tool-use, character training, and evaluation -- and open questions for the field. The book is released with a variety of companion resources, including a codebase, a library to compare model completions from within post-training stages, and an educational course, to be a one-stop shop for learning all foundational concepts for post-training language models.