# Mitigating Word Bias in Zero-shot Prompt-based Classifiers

arXiv: https://arxiv.org/abs/2309.04992 · HTML: https://mlsanity.com/paper/2309.04992/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 10 Sep 2023.

## Builds on (most cited first, 13 of 13)

- [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)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Surface Form Competition: Why the Highest Probability Answer Isn't Always Right](https://mlsanity.com/paper/2104.08315/) (2021)
- [Competency Problems: On Finding and Removing Artifacts in Language Data](https://mlsanity.com/paper/2104.08646/) (2021)

## Built on by (most cited first, 9 of 9)

- [Type-Safe Is Not Error-Free: Typed Decision Models Follow the Option Name, Not the Definition Bound to It](https://mlsanity.com/paper/2609.26758/) (2026)
- [ASR Error Correction using Large Language Models](https://mlsanity.com/paper/2409.09554/) (2024)
- [Assessment of L2 Oral Proficiency using Speech Large Language Models](https://mlsanity.com/paper/2505.21148/) (2025)
- [Investigating the Emergent Audio Classification Ability of ASR Foundation Models](https://mlsanity.com/paper/2311.09363/) (2023)
- [Teacher-Student Training for Debiasing: General Permutation Debiasing for Large Language Models](https://mlsanity.com/paper/2403.13590/) (2024)
- [Decoupling Template Bias in CLIP: Harnessing Empty Prompts for Enhanced Few-Shot Learning](https://mlsanity.com/paper/2512.08606/) (2025)
- [Zero-shot Audio Topic Reranking using Large Language Models](https://mlsanity.com/paper/2309.07606/) (2023)
- [OTTER: Effortless Label Distribution Adaptation of Zero-shot Models](https://mlsanity.com/paper/2404.08461/) (2024)
- [GeoTTER: Leveraging Local Geometry of Optimal Transport for Zero-Shot Classification](https://mlsanity.com/paper/2609.13518/) (2026)

## Abstract (arXiv)

Prompt-based classifiers are an attractive approach for zero-shot classification. However, the precise choice of the prompt template and label words can largely influence performance, with semantically equivalent settings often showing notable performance difference. This discrepancy can be partly attributed to word biases, where the classifier may be biased towards classes. To address this problem, it is possible to optimise classification thresholds on a labelled data set, however, this mitigates some of the advantages of prompt-based classifiers. This paper instead approaches this problem by examining the expected marginal probabilities of the classes. Here, probabilities are reweighted to have a uniform prior over classes, in an unsupervised fashion. Further, we draw a theoretical connection between the class priors and the language models' word prior, and offer the ability to set a threshold in a zero-resource fashion. We show that matching class priors correlates strongly with the oracle upper bound performance and demonstrate large consistent performance gains for prompt settings over a range of NLP tasks.