# Ensemble Debiasing Across Class and Sample Levels for Fairer Prompting Accuracy

arXiv: https://arxiv.org/abs/2503.05157 · HTML: https://mlsanity.com/paper/2503.05157/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 56 references that are in the map.
- First posted on arXiv 7 Mar 2025.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [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)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [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)
- [CVXPY: A Python-Embedded Modeling Language for Convex Optimization](https://mlsanity.com/paper/1603.00943/) (2016)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [Chain-of-Thought Reasoning Without Prompting](https://mlsanity.com/paper/2402.10200/) (2024)
- [A Rewriting System for Convex Optimization Problems](https://mlsanity.com/paper/1709.04494/) (2017)
- [Certified Robustness to Adversarial Word Substitutions](https://mlsanity.com/paper/1909.00986/) (2019)
- [Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering](https://mlsanity.com/paper/2309.17249/) (2023)
- [Open (Clinical) LLMs are Sensitive to Instruction Phrasings](https://mlsanity.com/paper/2407.09429/) (2024)
- [Implicit Geometry of Next-token Prediction: From Language Sparsity Patterns to Model Representations](https://mlsanity.com/paper/2408.15417/) (2024)
- [Implicit Optimization Bias of Next-Token Prediction in Linear Models](https://mlsanity.com/paper/2402.18551/) (2024)
- [System Combination for Grammatical Error Correction Based on Integer Programming](https://mlsanity.com/paper/2111.01465/) (2021)
- [Let the Fuzzy Rule Speak: Enhancing In-context Learning Debiasing with Interpretability](https://mlsanity.com/paper/2412.19018/) (2024)

## Built on by (most cited first, 1 of 1)

- [Discovering the Hidden Role of Gini Index In Prompt-based Classification](https://mlsanity.com/paper/2603.15654/) (2026)

## Abstract (arXiv)

Language models are strong few-shot learners and achieve good overall accuracy in text classification tasks, masking the fact that their results suffer from great class accuracy imbalance. We believe that the pursuit of overall accuracy should not come from enriching the strong classes, but from raising up the weak ones. To address the imbalance, we propose a Heaviside step function based ensemble debiasing method, which enables flexible rectifications of in-context learned class probabilities at both class and sample levels. Evaluations with Llama-2-13B on seven text classification benchmarks show that our approach achieves state-of-the-art overall accuracy gains with balanced class accuracies. More importantly, we perform analyses on the resulted probability correction scheme, showing that sample-level corrections are necessary to elevate weak classes. Due to effectively correcting weak classes, our method also brings significant performance gains to a larger model variant, Llama-2-70B, especially on a biomedical domain task, further demonstrating the necessity of ensemble debiasing at both levels. Our source code is available at https://github.com/NUS-HPC-AI-Lab/DCS.