# Revisiting Prompt Sensitivity in Large Language Models for Text Classification: The Role of Prompt Underspecification

arXiv: https://arxiv.org/abs/2602.04297 · HTML: https://mlsanity.com/paper/2602.04297/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 28 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [State of What Art? A Call for Multi-Prompt LLM Evaluation](https://mlsanity.com/paper/2401.00595/) (2023)
- [When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards](https://mlsanity.com/paper/2402.01781/) (2024)
- [The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance](https://mlsanity.com/paper/2401.03729/) (2024)
- [Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering](https://mlsanity.com/paper/2309.17249/) (2023)
- [What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineering](https://mlsanity.com/paper/2406.12334/) (2024)
- [Mitigating Label Biases for In-context Learning](https://mlsanity.com/paper/2305.19148/) (2023)
- [Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements](https://mlsanity.com/paper/2401.06766/) (2024)
- [Prompt Consistency for Zero-Shot Task Generalization](https://mlsanity.com/paper/2205.00049/) (2022)
- [Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answering](https://mlsanity.com/paper/2503.14996/) (2025)
- [Beyond Performance: Quantifying and Mitigating Label Bias in LLMs](https://mlsanity.com/paper/2405.02743/) (2024)
- [DOVE: A Large-Scale Multi-Dimensional Predictions Dataset Towards Meaningful LLM Evaluation](https://mlsanity.com/paper/2503.01622/) (2025)
- [Zero-shot Approach to Overcome Perturbation Sensitivity of Prompts](https://mlsanity.com/paper/2305.15689/) (2023)
- [Beyond the Next Token: Towards Prompt-Robust Zero-Shot Classification via Efficient Multi-Token Prediction](https://mlsanity.com/paper/2504.03159/) (2025)

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

- [Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking](https://mlsanity.com/paper/2604.11581/) (2026)
- [Benchmarking Source-Sensitive Reasoning in Turkish: Humans and LLMs under Evidential Trust Manipulation](https://mlsanity.com/paper/2604.24665/) (2026)
- [Discourse-Role Labels as Presentation-Time Variables for Context Use in Language Models](https://mlsanity.com/paper/2606.04109/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are widely used as zero-shot and few-shot classifiers, where task behaviour is largely controlled through prompting. A growing number of works have observed that LLMs are sensitive to prompt variations, with small changes leading to large changes in performance. However, in many cases, the investigation of sensitivity is performed using underspecified prompts that provide minimal task instructions and weakly constrain the model's output space. In this work, we argue that a significant portion of the observed prompt sensitivity can be attributed to prompt underspecification. We systematically study and compare the sensitivity of underspecified prompts and prompts that provide specific instructions. Utilising performance analysis, logit analysis, and linear probing, we find that underspecified prompts exhibit higher performance variance and lower logit values for relevant tokens, while instruction-prompts suffer less from such problems. However, linear probing analysis suggests that the effects of prompt underspecification have only a marginal impact on the internal LLM representations, instead emerging in the final layers. Overall, our findings highlight the need for more rigour when investigating and mitigating prompt sensitivity.