# Improving Weak-to-Strong Generalization with Scalable Oversight and Ensemble Learning

arXiv: https://arxiv.org/abs/2402.00667 · HTML: https://mlsanity.com/paper/2402.00667/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 1 Feb 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 9 of 9)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Crowdsourcing Multiple Choice Science Questions](https://mlsanity.com/paper/1707.06209/) (2017)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [Selective Annotation Makes Language Models Better Few-Shot Learners](https://mlsanity.com/paper/2209.01975/) (2022)
- [OpenICL: An Open-Source Framework for In-context Learning](https://mlsanity.com/paper/2303.02913/) (2023)

## Built on by (most cited first, 18 of 18)

- [Weak-to-Strong Reasoning](https://mlsanity.com/paper/2407.13647/) (2024)
- [The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment](https://mlsanity.com/paper/2412.16468/) (2024)
- [Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safety](https://mlsanity.com/paper/2506.12482/) (2025)
- [Bayesian WeakS-to-Strong from Text Classification to Generation](https://mlsanity.com/paper/2406.03199/) (2024)
- [Generalizable Video Quality Assessment via Weak-to-Strong Learning](https://mlsanity.com/paper/2505.03631/) (2025)
- [Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning](https://mlsanity.com/paper/2410.12621/) (2024)
- [EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles](https://mlsanity.com/paper/2505.21959/) (2025)
- [Weak-to-Strong Generalization via Bregman Bias-Variance Decomposition](https://mlsanity.com/paper/2505.24313/) (2025)
- [Weak-to-Strong Generalization under Distribution Shifts](https://mlsanity.com/paper/2510.21332/) (2025)
- [Training Deliberative Monitors for Black-Box Scheming Detection](https://mlsanity.com/paper/2605.29601/) (2026)
- [A Benchmark for Scalable Oversight Protocols](https://mlsanity.com/paper/2504.03731/) (2025)
- [Weak-to-Strong Generalization with Failure Trajectories: A Tree-based Approach to Elicit Optimal Policy in Strong Models](https://mlsanity.com/paper/2507.18858/) (2025)
- [The Capabilities and Limitations of Weak-to-Strong Generalization: Generalization and Calibration](https://mlsanity.com/paper/2502.01458/) (2025)
- [EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles](https://mlsanity.com/paper/2410.04571/) (2024)
- [Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization](https://mlsanity.com/paper/2503.07660/) (2025)
- [Alice: Proactive Learning with Teacher's Demonstrations for Weak-to-Strong Generalization](https://mlsanity.com/paper/2504.07316/) (2025)
- [On the Blessing of Pre-training in Weak-to-Strong Generalization](https://mlsanity.com/paper/2605.05710/) (2026)
- [AdaStop: Cost-Aware Early Stopping for DNN Test Selection](https://mlsanity.com/paper/2607.05461/) (2026)

## Abstract (arXiv)

This paper presents a follow-up study to OpenAI's recent superalignment work on Weak-to-Strong Generalization (W2SG). Superalignment focuses on ensuring that high-level AI systems remain consistent with human values and intentions when dealing with complex, high-risk tasks. The W2SG framework has opened new possibilities for empirical research in this evolving field. Our study simulates two phases of superalignment under the W2SG framework: the development of general superhuman models and the progression towards superintelligence. In the first phase, based on human supervision, the quality of weak supervision is enhanced through a combination of scalable oversight and ensemble learning, reducing the capability gap between weak teachers and strong students. In the second phase, an automatic alignment evaluator is employed as the weak supervisor. By recursively updating this auto aligner, the capabilities of the weak teacher models are synchronously enhanced, achieving weak-to-strong supervision over stronger student models.We also provide an initial validation of the proposed approach for the first phase. Using the SciQ task as example, we explore ensemble learning for weak teacher models through bagging and boosting. Scalable oversight is explored through two auxiliary settings: human-AI interaction and AI-AI debate. Additionally, the paper discusses the impact of improved weak supervision on enhancing weak-to-strong generalization based on in-context learning. Experiment code and dataset will be released at https://github.com/ADaM-BJTU/W2SG.