# Language Models in the Loop: Incorporating Prompting into Weak Supervision

arXiv: https://arxiv.org/abs/2205.02318 · HTML: https://mlsanity.com/paper/2205.02318/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 79 references that are in the map.
- First posted on arXiv 4 May 2022.

## Builds on (most cited first, 30 of 53)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [Do Prompt-Based Models Really Understand the Meaning of their Prompts?](https://mlsanity.com/paper/2109.01247/) (2021)
- [AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts](https://mlsanity.com/paper/2010.15980/) (2020)
- [Data Programming: Creating Large Training Sets, Quickly](https://mlsanity.com/paper/1605.07723/) (2016)
- [ZeroGen: Efficient Zero-shot Learning via Dataset Generation](https://mlsanity.com/paper/2202.07922/) (2022)
- [Generating Datasets with Pretrained Language Models](https://mlsanity.com/paper/2104.07540/) (2021)
- [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)
- [Prompt Consistency for Zero-Shot Task Generalization](https://mlsanity.com/paper/2205.00049/) (2022)

## Built on by (most cited first, 30 of 52)

- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey](https://mlsanity.com/paper/2406.15126/) (2024)
- [Large Language Models are Few-Shot Clinical Information Extractors](https://mlsanity.com/paper/2205.12689/) (2022)
- [Ask Me Anything: A simple strategy for prompting language models](https://mlsanity.com/paper/2210.02441/) (2022)
- [Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes](https://mlsanity.com/paper/2304.09433/) (2023)
- [Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction](https://mlsanity.com/paper/2303.04132/) (2023)
- [Anchor Points: Benchmarking Models with Much Fewer Examples](https://mlsanity.com/paper/2309.08638/) (2023)
- [UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition](https://mlsanity.com/paper/2308.03279/) (2023)
- [PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptions](https://mlsanity.com/paper/2305.14908/) (2023)
- [Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models](https://mlsanity.com/paper/2310.13671/) (2023)
- [Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model](https://mlsanity.com/paper/2210.02498/) (2022)
- [Mixed Distillation Helps Smaller Language Model Better Reasoning](https://mlsanity.com/paper/2312.10730/) (2023)
- [Small Language Models are Good Too: An Empirical Study of Zero-Shot Classification](https://mlsanity.com/paper/2404.11122/) (2024)
- [Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey](https://mlsanity.com/paper/2208.03197/) (2022)
- [Weakly Supervised Veracity Classification with LLM-Predicted Credibility Signals](https://mlsanity.com/paper/2309.07601/) (2023)
- [FreeAL: Towards Human-Free Active Learning in the Era of Large Language Models](https://mlsanity.com/paper/2311.15614/) (2023)
- [Distilling Large Language Models for Biomedical Knowledge Extraction: A Case Study on Adverse Drug Events](https://mlsanity.com/paper/2307.06439/) (2023)
- [Unsupervised Distractor Generation via Large Language Model Distilling and Counterfactual Contrastive Decoding](https://mlsanity.com/paper/2406.01306/) (2024)
- [LLM Chain Ensembles for Scalable and Accurate Data Annotation](https://mlsanity.com/paper/2410.13006/) (2024)
- [A Survey on Symbolic Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2408.10210/) (2024)
- [Predicting the Performance of Black-box LLMs through Follow-up Queries](https://mlsanity.com/paper/2501.01558/) (2025)
- [Weaker Than You Think: A Critical Look at Weakly Supervised Learning](https://mlsanity.com/paper/2305.17442/) (2023)
- [Alfred: A System for Prompted Weak Supervision](https://mlsanity.com/paper/2305.18623/) (2023)
- [Leveraging Large Language Models for Knowledge-free Weak Supervision in Clinical Natural Language Processing](https://mlsanity.com/paper/2406.06723/) (2024)
- [MAO: A Framework for Process Model Generation with Multi-Agent Orchestration](https://mlsanity.com/paper/2408.01916/) (2024)
- [AutoWS-Bench-101: Benchmarking Automated Weak Supervision with 100 Labels](https://mlsanity.com/paper/2208.14362/) (2022)
- [Towards an On-device Agent for Text Rewriting](https://mlsanity.com/paper/2308.11807/) (2023)
- [PIEClass: Weakly-Supervised Text Classification with Prompting and Noise-Robust Iterative Ensemble Training](https://mlsanity.com/paper/2305.13723/) (2023)
- [Weak Supervision Performance Evaluation via Partial Identification](https://mlsanity.com/paper/2312.04601/) (2023)
- [Larger Probes Tell a Different Story: Extending Psycholinguistic Datasets Via In-Context Learning](https://mlsanity.com/paper/2303.16445/) (2023)

## Abstract (arXiv)

We propose a new strategy for applying large pre-trained language models to novel tasks when labeled training data is limited. Rather than apply the model in a typical zero-shot or few-shot fashion, we treat the model as the basis for labeling functions in a weak supervision framework. To create a classifier, we first prompt the model to answer multiple distinct queries about an example and define how the possible responses should be mapped to votes for labels and abstentions. We then denoise these noisy label sources using the Snorkel system and train an end classifier with the resulting training data. Our experimental evaluation shows that prompting large language models within a weak supervision framework can provide significant gains in accuracy. On the WRENCH weak supervision benchmark, this approach can significantly improve over zero-shot performance, an average 19.5% reduction in errors. We also find that this approach produces classifiers with comparable or superior accuracy to those trained from hand-engineered rules.