Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning
Open Access
- 8 August 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 3978-3987
Abstract
No abstract availableFunding Information
- Australian Research Council (DP240101108)
- Australian Research Council (DP260100326)
- Australian Research Council (LP240200546)
This publication has 14 references indexed in Scilit:
- NL2SQL-BUGs: A Benchmark for Detecting Semantic Errors in NL2SQL Translation2025
- SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMs2025
- UniBridge: A Unified Approach to Cross-Lingual Transfer Learning for Low-Resource Languages2024
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Predicting with Confidence on Unseen Distributions2021
- Are Labels Always Necessary for Classifier Accuracy Evaluation?2021
- Want To Reduce Labeling Cost? GPT-3 Can Help2021
- Learning to Validate the Predictions of Black Box Classifiers on Unseen Data2020
- Cost-effective data annotation using game-based crowdsourcingProceedings of the VLDB Endowment, 2018
- ImageNet: A large-scale hierarchical image database2009