One-Shot Calibration via Model Editing
Model editing aims to correct errors in large, pretrained models by replacing model generations with user-provided responses. Existing editors assume a single target answer for each edit. However, many real tasks inherently entail uncertainty, resulting in multiple plausible answers with varying likelihoods in user feedback. Such feedback forms a target distribution to not only correct but also calibrate model generations. We therefore propose SoftEdit, the first model editor to leverage uncertainty in user responses and perform one-shot calibration during editing. To generalize calibration to unseen samples, SoftEdit uses co-plausibility relationships between answers while preserving real distributional shifts, balancing the new distributional generality-locality tradeoff. Across three language models, three vision-language models, and two large datasets, SoftEdit achieves state-of-the-art performance, ultimately showing that uncertainty in user responses enables generalizable calibration of pretrained models beyond single-answer corrections.
Authors
- Roxana Daneshjou (ORCID: https://orcid.org/0000-0001-7988-9356)
- Ahmed M. Alaa (ORCID: https://orcid.org/0000-0001-9936-7141)
- Thomas Hartvigsen (ORCID: https://orcid.org/0000-0002-5288-2792)
- Jiaxing Qiu
- Luke Hakso
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-11-16
- DOI
- https://doi.org/10.48550/arxiv.2611.20562
- Primary Topic
- Topic Modeling
- Type
- preprint