Predicting generalization performance with correctness discriminators

2023/11/15 by Yuekun Yao, Alexander Koller, Yao, Yuekun +1
Computer Science · #Adversarial Robustness in Machine Learning #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2311.09422

openalex publication_date 2023/11/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The ability to predict an NLP model's accuracy on unseen, potentially out-of-distribution data is a prerequisite for trustworthiness. We present a novel model that establishes upper and lower bounds on the accuracy, without requiring gold labels for the unseen data. We achieve this by training a discriminator which predicts whether the output of a given sequence-to-sequence model is correct or not. We show across a variety of tagging, parsing, and semantic parsing tasks that the gold accuracy is reliably between the predicted upper and lower bounds, and that these bounds are remarkably close together.

Related

• Understanding and Mitigating Classification Errors Through Interpretable Token Patterns
• Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models
• Memorization vs. Generalization: Quantifying Data Leakage in NLP\n Performance Evaluation
• Towards Improving Selective Prediction Ability of NLP Systems
• Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs