# Larger Probes Tell a Different Story: Extending Psycholinguistic Datasets Via In-Context Learning

arXiv: https://arxiv.org/abs/2303.16445 · HTML: https://mlsanity.com/paper/2303.16445/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 29 Mar 2023.

## Builds on (most cited first, 26 of 26)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models](https://mlsanity.com/paper/1907.13528/) (2019)
- [Revealing the Dark Secrets of BERT](https://mlsanity.com/paper/1908.08593/) (2019)
- [WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation](https://mlsanity.com/paper/2201.05955/) (2022)
- [Generating Training Data with Language Models: Towards Zero-Shot Language Understanding](https://mlsanity.com/paper/2202.04538/) (2022)
- [Generating Datasets with Pretrained Language Models](https://mlsanity.com/paper/2104.07540/) (2021)
- [Not Enough Data? Deep Learning to the Rescue!](https://mlsanity.com/paper/1911.03118/) (2019)
- [Data Augmentation using Pre-trained Transformer Models](https://mlsanity.com/paper/2003.02245/) (2020)
- [oLMpics -- On what Language Model Pre-training Captures](https://mlsanity.com/paper/1912.13283/) (2019)
- [With Little Power Comes Great Responsibility](https://mlsanity.com/paper/2010.06595/) (2020)
- [When Do You Need Billions of Words of Pretraining Data?](https://mlsanity.com/paper/2011.04946/) (2020)
- [Probing Across Time: What Does RoBERTa Know and When?](https://mlsanity.com/paper/2104.07885/) (2021)
- [InPars: Data Augmentation for Information Retrieval using Large Language Models](https://mlsanity.com/paper/2202.05144/) (2022)
- [Language Models in the Loop: Incorporating Prompting into Weak Supervision](https://mlsanity.com/paper/2205.02318/) (2022)
- [Generative Data Augmentation for Commonsense Reasoning](https://mlsanity.com/paper/2004.11546/) (2020)
- [DARE: Data Augmented Relation Extraction with GPT-2](https://mlsanity.com/paper/2004.13845/) (2020)
- [Unsupervised Neural Machine Translation with Generative Language Models Only](https://mlsanity.com/paper/2110.05448/) (2021)
- [What's the best place for an AI conference, Vancouver or ______: Why completing comparative questions is difficult](https://mlsanity.com/paper/2104.01940/) (2021)
- [Life after BERT: What do Other Muppets Understand about Language?](https://mlsanity.com/paper/2205.10696/) (2022)
- [Using GPT-2 to Create Synthetic Data to Improve the Prediction Performance of NLP Machine Learning Classification Models](https://mlsanity.com/paper/2104.10658/) (2021)

## Built on by (most cited first, 3 of 3)

- [From Monolingual to Bilingual: Investigating Language Conditioning in Large Language Models for Psycholinguistic Tasks](https://mlsanity.com/paper/2508.02502/) (2025)
- [MAGA-Bench: Machine-Augment-Generated Text via Alignment Detection Benchmark](https://mlsanity.com/paper/2601.04633/) (2026)
- [Scale, Drivers, and Limits of Representational Alignment Across Large Language Models](https://mlsanity.com/paper/2610.14476/) (2026)

## Abstract (arXiv)

Language model probing is often used to test specific capabilities of models. However, conclusions from such studies may be limited when the probing benchmarks are small and lack statistical power. In this work, we introduce new, larger datasets for negation (NEG-1500-SIMP) and role reversal (ROLE-1500) inspired by psycholinguistic studies. We dramatically extend existing NEG-136 and ROLE-88 benchmarks using GPT3, increasing their size from 18 and 44 sentence pairs to 750 each. We also create another version of extended negation dataset (NEG-1500-SIMP-TEMP), created using template-based generation. It consists of 770 sentence pairs. We evaluate 22 models on the extended datasets, seeing model performance dip 20-57% compared to the original smaller benchmarks. We observe high levels of negation sensitivity in models like BERT and ALBERT demonstrating that previous findings might have been skewed due to smaller test sets. Finally, we observe that while GPT3 has generated all the examples in ROLE-1500 is only able to solve 24.6% of them during probing. The datasets and code are available on hrefhttps://github.com/text-machine-lab/extendingpsycholinguisticdatasetGithub.