# Weak Supervision Performance Evaluation via Partial Identification

arXiv: https://arxiv.org/abs/2312.04601 · HTML: https://mlsanity.com/paper/2312.04601/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 65 references that are in the map.
- First posted on arXiv 7 Dec 2023.

## Builds on (most cited first, 27 of 27)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Data Programming: Creating Large Training Sets, Quickly](https://mlsanity.com/paper/1605.07723/) (2016)
- [Hate Speech Dataset from a White Supremacy Forum](https://mlsanity.com/paper/1809.04444/) (2018)
- [Training Complex Models with Multi-Task Weak Supervision](https://mlsanity.com/paper/1810.02840/) (2018)
- [Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods](https://mlsanity.com/paper/2002.11955/) (2020)
- [WRENCH: A Comprehensive Benchmark for Weak Supervision](https://mlsanity.com/paper/2109.11377/) (2021)
- [Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach](https://mlsanity.com/paper/2010.07835/) (2020)
- [A Survey on Programmatic Weak Supervision](https://mlsanity.com/paper/2202.05433/) (2022)
- [Language Models in the Loop: Incorporating Prompting into Weak Supervision](https://mlsanity.com/paper/2205.02318/) (2022)
- [Named Entity Recognition without Labelled Data: A Weak Supervision Approach](https://mlsanity.com/paper/2004.14723/) (2020)
- [Distributionally Robust Learning](https://mlsanity.com/paper/2108.08993/) (2021)
- [Fairness Evaluation in Presence of Biased Noisy Labels](https://mlsanity.com/paper/2003.13808/) (2020)
- [End-to-End Weak Supervision](https://mlsanity.com/paper/2107.02233/) (2021)
- [Inferring Generative Model Structure with Static Analysis](https://mlsanity.com/paper/1709.02477/) (2017)
- [Ontology-driven weak supervision for clinical entity classification in electronic health records](https://mlsanity.com/paper/2008.01972/) (2020)
- [What's the Harm? Sharp Bounds on the Fraction Negatively Affected by Treatment](https://mlsanity.com/paper/2205.10327/) (2022)
- [Partial Identification with Noisy Covariates: A Robust Optimization Approach](https://mlsanity.com/paper/2202.10665/) (2022)
- [Losses over Labels: Weakly Supervised Learning via Direct Loss Construction](https://mlsanity.com/paper/2212.06921/) (2022)
- [Adversarial Label Learning](https://mlsanity.com/paper/1805.08877/) (2018)
- [Weaker Than You Think: A Critical Look at Weakly Supervised Learning](https://mlsanity.com/paper/2305.17442/) (2023)
- [Measuring Model Fairness under Noisy Covariates: A Theoretical Perspective](https://mlsanity.com/paper/2105.09985/) (2021)
- [Marginal and dependence uncertainty: bounds, optimal transport, and sharpness](https://mlsanity.com/paper/1709.00641/) (2017)
- [Behavior of Limited Memory BFGS when Applied to Nonsmooth Functions and their Nesterov Smoothings](https://mlsanity.com/paper/2006.11336/) (2020)

## Built on by (most cited first, 4 of 4)

- [Metadata Predictability Is Not Evidence Dependence: An Intervention-Based Audit for Weak-Label Benchmarks](https://mlsanity.com/paper/2605.23701/) (2026)
- [Evaluation Sovereignty in Metadata-Driven Classification: A Multi-Track Framework for Weakly Supervised Information Systems](https://mlsanity.com/paper/2606.13436/) (2026)
- [What Does an Evaluation License? A Commit-Bound Census of Claim Replay in Inspect Evals](https://mlsanity.com/paper/2608.19269/) (2026)
- [Nous: Learning and Certifying Memory Decisions Before Source Calibration](https://mlsanity.com/paper/2610.00094/) (2026)

## Abstract (arXiv)

Programmatic Weak Supervision (PWS) enables supervised model training without direct access to ground truth labels, utilizing weak labels from heuristics, crowdsourcing, or pre-trained models. However, the absence of ground truth complicates model evaluation, as traditional metrics such as accuracy, precision, and recall cannot be directly calculated. In this work, we present a novel method to address this challenge by framing model evaluation as a partial identification problem and estimating performance bounds using Fr'echet bounds. Our approach derives reliable bounds on key metrics without requiring labeled data, overcoming core limitations in current weak supervision evaluation techniques. Through scalable convex optimization, we obtain accurate and computationally efficient bounds for metrics including accuracy, precision, recall, and F1-score, even in high-dimensional settings. This framework offers a robust approach to assessing model quality without ground truth labels, enhancing the practicality of weakly supervised learning for real-world applications.