# Your Weak LLM is Secretly a Strong Teacher for Alignment

arXiv: https://arxiv.org/abs/2409.08813 · HTML: https://mlsanity.com/paper/2409.08813/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 45 of its 59 references that are in the map.
- First posted on arXiv 13 Sep 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 30 of 45)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [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)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [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)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (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)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (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)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision](https://mlsanity.com/paper/2312.09390/) (2023)
- [Statistical Rejection Sampling Improves Preference Optimization](https://mlsanity.com/paper/2309.06657/) (2023)
- [Direct Language Model Alignment from Online AI Feedback](https://mlsanity.com/paper/2402.04792/) (2024)
- [Knowledge distillation: A good teacher is patient and consistent](https://mlsanity.com/paper/2106.05237/) (2021)

## Built on by (most cited first, 20 of 20)

- [Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors](https://mlsanity.com/paper/2504.04785/) (2025)
- [Provable Weak-to-Strong Generalization via Benign Overfitting](https://mlsanity.com/paper/2410.04638/) (2024)
- [Weak-to-Strong Generalization Even in Random Feature Networks, Provably](https://mlsanity.com/paper/2503.02877/) (2025)
- [SPARTA ALIGNMENT: Collectively Aligning Multiple Language Models through Combat](https://mlsanity.com/paper/2506.04721/) (2025)
- [On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective](https://mlsanity.com/paper/2505.18346/) (2025)
- [Incentivizing Strong Reasoning from Weak Supervision](https://mlsanity.com/paper/2505.20072/) (2025)
- [Unraveling Misinformation Propagation in LLM Reasoning](https://mlsanity.com/paper/2505.18555/) (2025)
- [Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight](https://mlsanity.com/paper/2606.00424/) (2026)
- [Challenges and Future Directions of Data-Centric AI Alignment](https://mlsanity.com/paper/2410.01957/) (2024)
- [Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner](https://mlsanity.com/paper/2508.15044/) (2025)
- [Super Co-alignment of Human and AI for Sustainable Symbiotic Society](https://mlsanity.com/paper/2504.17404/) (2025)
- [Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment](https://mlsanity.com/paper/2509.23564/) (2025)
- [Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis](https://mlsanity.com/paper/2509.26074/) (2025)
- [General Exploratory Bonus for Optimistic Exploration in RLHF](https://mlsanity.com/paper/2510.03269/) (2025)
- [Contrastive Weak-to-strong Generalization](https://mlsanity.com/paper/2510.07884/) (2025)
- [More Than the Final Answer: Improving Visual Extraction and Logical Consistency in Vision-Language Models](https://mlsanity.com/paper/2512.12487/) (2025)
- [The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge](https://mlsanity.com/paper/2605.12908/) (2026)
- [When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger](https://mlsanity.com/paper/2603.04968/) (2026)
- [Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher](https://mlsanity.com/paper/2606.01000/) (2026)
- [ABC-Align: Prediction-Powered Alignment with Adaptive Bias Control](https://mlsanity.com/paper/2609.34374/) (2026)

## Abstract (arXiv)

The burgeoning capabilities of large language models (LLMs) have underscored the need for alignment to ensure these models act in accordance with human values and intentions. Existing alignment frameworks present constraints either in the form of expensive human effort or high computational costs. This paper explores a promising middle ground, where we employ a weak LLM that is significantly less resource-intensive than top-tier models, yet offers more automation than purely human feedback. We present a systematic study to evaluate and understand weak LLM's ability to generate feedback for alignment. Our empirical findings demonstrate that weak LLMs can provide feedback that rivals or even exceeds that of fully human-annotated data. Our study indicates a minimized impact of model size on feedback efficacy, shedding light on a scalable and sustainable alignment strategy. To deepen our understanding of alignment under weak LLM feedback, we conduct a series of qualitative and quantitative analyses, offering novel insights into the quality discrepancies between human feedback vs. weak LLM feedback.