EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles

Aakriti Agrawal, Mucong Ding, Chenghao Deng, Zora Che, Arjun Rajaram, Anirudh Satheesh, Bang An, C. Bayan Bruss, John Langford, Furong Huang


Abstract
With Large Language Models (LLMs) rapidly approaching and potentially surpassing human-level performance, it has become imperative to develop approaches capable of effectively supervising and enhancing these powerful models using smaller, human-level models exposed to only human-level data. We address this critical weak-to-strong (W2S) generalization challenge by proposing a novel method aimed at improving weak experts, by training on the same limited human-level data, enabling them to generalize to complex, super-human-level tasks. Our approach, called EnsemW2S, employs a token-level ensemble strategy that iteratively combines multiple weak experts, systematically addressing the shortcomings identified in preceding iterations. By continuously refining these weak models, we significantly enhance their collective ability to supervise stronger student models. We extensively evaluate the generalization performance of both the ensemble of weak experts and the subsequent strong student model across in-distribution (ID) and out-of-distribution (OOD) datasets. For OOD, we specifically introduce question difficulty as an additional dimension for defining distributional shifts. Our empirical results demonstrate notable improvements, achieving 4%, and 3.2% improvements on ID datasets and, upto 6% and 2.28% on OOD datasets for experts and student models respectively, underscoring the effectiveness of our proposed method in advancing W2S generalization.
Anthology ID:
2026.findings-acl.2093
Volume:
Findings of the Association for Computational Linguistics: ACL 2026
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
42187–42216
Language:
URL:
https://aclanthology.org/2026.findings-acl.2093/
DOI:
Bibkey:
Cite (ACL):
Aakriti Agrawal, Mucong Ding, Chenghao Deng, Zora Che, Arjun Rajaram, Anirudh Satheesh, Bang An, C. Bayan Bruss, John Langford, and Furong Huang. 2026. EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles. In Findings of the Association for Computational Linguistics: ACL 2026, pages 42187–42216, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles (Agrawal et al., Findings 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.findings-acl.2093.pdf
Checklist:
 2026.findings-acl.2093.checklist.pdf