# Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of Language Models

arXiv: https://arxiv.org/abs/2402.10353 · HTML: https://mlsanity.com/paper/2402.10353/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 60 references that are in the map.
- First posted on arXiv 15 Feb 2024.

## Builds on (most cited first, 30 of 38)

- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [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)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [Surface Form Competition: Why the Highest Probability Answer Isn't Always Right](https://mlsanity.com/paper/2104.08315/) (2021)
- [Simple, Scalable Adaptation for Neural Machine Translation](https://mlsanity.com/paper/1909.08478/) (2019)
- [Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets](https://mlsanity.com/paper/2106.10328/) (2021)
- [Noisy Channel Language Model Prompting for Few-Shot Text Classification](https://mlsanity.com/paper/2108.04106/) (2021)
- [Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation](https://mlsanity.com/paper/1911.03842/) (2019)
- [Reducing Sentiment Bias in Language Models via Counterfactual Evaluation](https://mlsanity.com/paper/1911.03064/) (2019)
- [Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models](https://mlsanity.com/paper/2106.13353/) (2021)
- [TimeLMs: Diachronic Language Models from Twitter](https://mlsanity.com/paper/2202.03829/) (2022)

## Built on by (most cited first, 8 of 8)

- [CatRAG: Functor-Guided Structural Debiasing with Retrieval Augmentation for Fair LLMs](https://mlsanity.com/paper/2603.21524/) (2026)
- [When to Speak, When to Abstain: Contrastive Decoding with Abstention](https://mlsanity.com/paper/2412.12527/) (2024)
- [Exposing and Mitigating Calibration Biases and Demographic Unfairness in MLLM Few-Shot In-Context Learning for Medical Image Classification](https://mlsanity.com/paper/2506.23298/) (2025)
- [Bias in, Bias out: Annotation Bias in Multilingual Large Language Models](https://mlsanity.com/paper/2511.14662/) (2025)
- [RBCorr: Response Bias Correction in Language Models](https://mlsanity.com/paper/2602.12445/) (2026)
- [A Comprehensive Survey of Challenges and Opportunities of Few-Shot Learning Across Multiple Domains](https://mlsanity.com/paper/2504.04017/) (2025)
- [Enabling Fine-Grained Operating Points for Black-Box LLMs](https://mlsanity.com/paper/2510.17727/) (2025)
- [Label Collapse in Diffusion Language Model In-Context Learning](https://mlsanity.com/paper/2610.16839/) (2026)

## Abstract (arXiv)

Prompt-based learning is susceptible to intrinsic bias present in pre-trained language models (LMs), leading to sub-optimal performance in prompt-based zero/few-shot settings. In this work, we propose a null-input prompting method to calibrate intrinsic bias encoded in pre-trained LMs. Different from prior efforts that address intrinsic bias primarily for social fairness and often involve excessive computational cost, our objective is to explore enhancing LMs' performance in downstream zero/few-shot learning while emphasizing the efficiency of intrinsic bias calibration. Specifically, we leverage a diverse set of auto-selected null-meaning inputs generated from GPT-4 to probe intrinsic bias of pre-trained LMs. Utilizing the bias-reflected probability distribution, we formulate a distribution disparity loss for bias calibration, where we exclusively update bias parameters (0.1% of total parameters) of LMs towards equal probability distribution. Experimental results show that the calibration promotes an equitable starting point for LMs while preserving language modeling abilities. Across a wide range of datasets, including sentiment analysis and topic classification, our method significantly improves zero/few-shot learning performance of LMs for both in-context learning and prompt-based fine-tuning (on average 9% and 2%, respectively).