# A Query Is Not a Commitment: Learning to Correct Expert Answers in Online Deferral

arXiv: https://arxiv.org/abs/2610.07084 · HTML: https://mlsanity.com/paper/2610.07084/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 74 references that are in the map.
- First posted on arXiv 5 Oct 2026.

## Builds on (most cited first, 10 of 10)

- [Introduction to Online Convex Optimization](https://mlsanity.com/paper/1909.05207/) (2019)
- [Classification with Costly Features using Deep Reinforcement Learning](https://mlsanity.com/paper/1711.07364/) (2017)
- [Budgeted Multiple-Expert Deferral](https://mlsanity.com/paper/2510.26706/) (2025)
- [Learning-to-defer for sequential medical decision-making under uncertainty](https://mlsanity.com/paper/2109.06312/) (2021)
- [Improving Learning-to-Defer Algorithms Through Fine-Tuning](https://mlsanity.com/paper/2112.10768/) (2021)
- [To Ask or Not to Ask: Learning to Require Human Feedback](https://mlsanity.com/paper/2510.08314/) (2025)
- [Learning-to-Defer in Non-Stationary Time Series via Switching State-Space Models](https://mlsanity.com/paper/2601.22538/) (2026)
- [Beyond Augmented-Action Surrogates for Multi-Expert Learning-to-Defer](https://mlsanity.com/paper/2604.09414/) (2026)
- [Consistent Learning-to-Defer with Expert-Conditional Advice](https://mlsanity.com/paper/2603.14324/) (2026)
- [Online Learning-to-Defer with Varying Experts](https://mlsanity.com/paper/2605.12340/) (2026)

## Abstract (arXiv)

An inaccurate expert can still provide useful information after correction. We study online learning to defer in which the learner chooses an expert and fixes a correction function before purchasing its answer, then applies that function to the answer received. The difficulty is that observed losses reflect both expert quality and an unfinished correction: early errors can discourage queries that would be valuable after learning. We propose ORUCB, which pools shared and expert-specific polynomial responses. A bound on cumulative response-learning error calibrates confidence-weighted risk regression and exploration, allowing the router to account for this error when deciding which answers to buy. Under bounded residuals and disagreements, a fixed feasible model of optimal responses, and linear models of free and optimal queried risk, the calibrated algorithm achieves high-probability pseudo-regret O(√ Tlog(T+1)) over T rounds for fixed problem parameters. The guarantee permits singular answer distributions and misspecified shared responses; optimality is relative to the bounded response class. On four test streams, the selected cubic policy has lower fee-inclusive cost than seven baselines that deploy answers unchanged. Comparisons with a common correction learner examine routing, while six-price comparisons measure cost and query rates.