# MICRO: Multi-Fidelity Active Search for Severe Error Discovery

arXiv: https://arxiv.org/abs/2609.26025 · HTML: https://mlsanity.com/paper/2609.26025/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 22 Sep 2026.

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

- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation](https://mlsanity.com/paper/2104.14478/) (2021)
- [Bandit Structured Prediction for Neural Sequence-to-Sequence Learning](https://mlsanity.com/paper/1704.06497/) (2017)
- [Identifying Unknown Unknowns in the Open World: Representations and Policies for Guided Exploration](https://mlsanity.com/paper/1610.09064/) (2016)
- [Active Learning from Weak and Strong Labelers](https://mlsanity.com/paper/1510.02847/) (2015)
- [Evaluating User Perception of Speech Recognition System Quality with Semantic Distance Metric](https://mlsanity.com/paper/2110.05376/) (2021)
- [Nonmyopic Multifidelity Active Search](https://mlsanity.com/paper/2106.06356/) (2021)

## Abstract (arXiv)

Human feedback can vary in cost and informativeness. Strong feedback can reveal severe errors but is costly, so cheaper quality ratings can help decide which items to annotate. We propose MICRO (Multi-Fidelity Impact Clustered Rollout), an active search framework that allocates a shared budget to these feedback types to maximise confirmed severe error discoveries. MICRO jointly models ratings and annotation losses conditional on item features to steer acquisition. It clusters acquisitions by their predicted impact on severity probabilities to select diverse candidates, then uses rollout to estimate their discovery value. Experiments on WMT20 English-German show that ratings improve both loss reconstruction and severity prediction. MICRO achieves the highest mean discovery count across four budget and rating cost settings, with similar performance to adapted MF-ENS in one and significant gains over all six comparison policies, including two rollout controls, in the other three (p<.001).