# Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment

arXiv: https://arxiv.org/abs/2405.17888 · HTML: https://mlsanity.com/paper/2405.17888/

## Key facts

- Cited by 32 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 40 of its 57 references that are in the map.
- First posted on arXiv 28 May 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)
- Offline RL and imitation learning from data / [Inverse reinforcement learning](https://mlsanity.com/offlinerl/inverse-reinforcement-learning/)

## Builds on (most cited first, 30 of 40)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Safe RLHF: Safe Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2310.12773/) (2023)

## Built on by (most cited first, 30 of 32)

- [Preserving Diversity in Supervised Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2408.16673/) (2024)
- [Self-Exploring Language Models: Active Preference Elicitation for Online Alignment](https://mlsanity.com/paper/2405.19332/) (2024)
- [LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling](https://mlsanity.com/paper/2511.20785/) (2025)
- [Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning](https://mlsanity.com/paper/2509.06948/) (2025)
- [Imitating Language via Scalable Inverse Reinforcement Learning](https://mlsanity.com/paper/2409.01369/) (2024)
- [Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment](https://mlsanity.com/paper/2503.18991/) (2025)
- [ShowUI-Aloha: Human-Taught GUI Agent](https://mlsanity.com/paper/2601.07181/) (2026)
- [Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models](https://mlsanity.com/paper/2507.02870/) (2025)
- [Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities](https://mlsanity.com/paper/2507.13158/) (2025)
- [Direct Post-Training Preference Alignment for Multi-Agent Motion Generation Models Using Implicit Feedback from Pre-training Demonstrations](https://mlsanity.com/paper/2503.20105/) (2025)
- [ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation](https://mlsanity.com/paper/2505.16495/) (2025)
- [RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models](https://mlsanity.com/paper/2502.09003/) (2025)
- [CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models](https://mlsanity.com/paper/2512.07890/) (2025)
- [From Demonstrations to Rewards: Alignment Without Explicit Human Preferences](https://mlsanity.com/paper/2503.13538/) (2025)
- [Automatic MILP Model Construction for Multi-Robot Task Allocation and Scheduling Based on Large Language Models](https://mlsanity.com/paper/2503.13813/) (2025)
- [We Think, Therefore We Align LLMs to Helpful, Harmless and Honest Before They Go Wrong](https://mlsanity.com/paper/2509.22510/) (2025)
- [Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive Weighting](https://mlsanity.com/paper/2603.08118/) (2026)
- [Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models](https://mlsanity.com/paper/2603.13985/) (2026)
- [Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring](https://mlsanity.com/paper/2502.05242/) (2025)
- [Multi2: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environments](https://mlsanity.com/paper/2606.03698/) (2026)
- [Enhancing Spectral Knowledge Interrogation: A Reliable Retrieval-Augmented Generative Framework on Large Language Models](https://mlsanity.com/paper/2408.11557/) (2024)
- [Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data](https://mlsanity.com/paper/2502.18679/) (2025)
- [InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes under Herd Behavior](https://mlsanity.com/paper/2507.06528/) (2025)
- [Nonconvex Decentralized Stochastic Bilevel Optimization under Heavy-Tailed Noise](https://mlsanity.com/paper/2509.15543/) (2025)
- [Beyond Imitation: Recovering Dense Rewards from Demonstrations](https://mlsanity.com/paper/2510.02493/) (2025)
- [Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only](https://mlsanity.com/paper/2510.21090/) (2025)
- [DMRL: Data- and Model-aware Reward Learning for Data Extraction](https://mlsanity.com/paper/2505.06284/) (2025)
- [Datarus-R1: An Adaptive Multi-Step Reasoning LLM for Automated Data Analysis](https://mlsanity.com/paper/2508.13382/) (2025)
- [Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs](https://mlsanity.com/paper/2606.03489/) (2026)
- [SCOUT: Self-Checking and Recovery-Aware Tool-Thought Agents for Ultra-Long Egocentric Video Reasoning](https://mlsanity.com/paper/2608.07959/) (2026)

## Abstract (arXiv)

Aligning human preference and value is an important requirement for contemporary foundation models. State-of-the-art techniques such as Reinforcement Learning from Human Feedback (RLHF) often consist of two stages: 1) supervised fine-tuning (SFT), where the model is fine-tuned by learning from human demonstration data; 2) Preference learning, where preference data is used to learn a reward model, which is in turn used by a reinforcement learning (RL) step to fine-tune the model. Such reward model serves as a proxy to human preference, and it is critical to guide the RL step towards improving the model quality. In this work, we argue that the SFT stage significantly benefits from learning a reward model as well. Instead of using the human demonstration data directly via supervised learning, we propose to leverage an Inverse Reinforcement Learning (IRL) technique to simultaneously build an reward model and a policy model. This approach leads to new SFT algorithms that are not only efficient to implement, but are robust to the presence of low-quality supervised learning data. Moreover, we discover a connection between the proposed IRL based approach, and a recent line of works called Self-Play Fine-tune (SPIN). Theoretically, we show that the proposed algorithms converge to the stationary solutions of the IRL problem. Empirically, we align 1B and 7B models using proposed methods and evaluate them on a reward benchmark model and the HuggingFace Open LLM Leaderboard. The proposed methods show significant performance improvement over existing SFT approaches. Our results indicate that it is beneficial to leverage reward learning throughout the entire alignment process.