# A Note on Bias to Complete

arXiv: https://arxiv.org/abs/2402.11710 · HTML: https://mlsanity.com/paper/2402.11710/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 102 of its 161 references that are in the map.
- First posted on arXiv 18 Feb 2024.

## Builds on (most cited first, 30 of 102)

- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning](https://mlsanity.com/paper/2203.02053/) (2022)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models](https://mlsanity.com/paper/2305.08283/) (2023)
- [ZeroGen: Efficient Zero-shot Learning via Dataset Generation](https://mlsanity.com/paper/2202.07922/) (2022)
- [In-Context Impersonation Reveals Large Language Models' Strengths and Biases](https://mlsanity.com/paper/2305.14930/) (2023)
- [MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data](https://mlsanity.com/paper/2206.01347/) (2022)
- [On Measuring and Mitigating Biased Inferences of Word Embeddings](https://mlsanity.com/paper/1908.09369/) (2019)
- [DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks](https://mlsanity.com/paper/2110.12884/) (2021)
- [Automatically Neutralizing Subjective Bias in Text](https://mlsanity.com/paper/1911.09709/) (2019)
- [Sustainable Modular Debiasing of Language Models](https://mlsanity.com/paper/2109.03646/) (2021)
- [The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems](https://mlsanity.com/paper/2204.03021/) (2022)
- [Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Models](https://mlsanity.com/paper/2204.08110/) (2022)
- [Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?](https://mlsanity.com/paper/2211.13972/) (2022)
- [Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search](https://mlsanity.com/paper/2109.05433/) (2021)
- [On Decoding Strategies for Neural Text Generators](https://mlsanity.com/paper/2203.15721/) (2022)
- [Mitigating Language-Dependent Ethnic Bias in BERT](https://mlsanity.com/paper/2109.05704/) (2021)
- [Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics](https://mlsanity.com/paper/2106.14574/) (2021)
- [Mitigating Political Bias in Language Models Through Reinforced Calibration](https://mlsanity.com/paper/2104.14795/) (2021)
- [Learning Certified Individually Fair Representations](https://mlsanity.com/paper/2002.10312/) (2020)
- [Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation](https://mlsanity.com/paper/2109.03858/) (2021)
- [Unmasking the Mask -- Evaluating Social Biases in Masked Language Models](https://mlsanity.com/paper/2104.07496/) (2021)
- [Neural Media Bias Detection Using Distant Supervision With BABE -- Bias Annotations By Experts](https://mlsanity.com/paper/2209.14557/) (2022)
- [Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Tasks](https://mlsanity.com/paper/2210.02938/) (2022)
- [Diagnosing failures of fairness transfer across distribution shift in real-world medical settings](https://mlsanity.com/paper/2202.01034/) (2022)
- [pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learning](https://mlsanity.com/paper/2206.03655/) (2022)
- [Fair Algorithms for Multi-Agent Multi-Armed Bandits](https://mlsanity.com/paper/2007.06699/) (2020)
- [Things not Written in Text: Exploring Spatial Commonsense from Visual Signals](https://mlsanity.com/paper/2203.08075/) (2022)
- [Turning the Tables: Biased, Imbalanced, Dynamic Tabular Datasets for ML Evaluation](https://mlsanity.com/paper/2211.13358/) (2022)
- [On-Demand Sampling: Learning Optimally from Multiple Distributions](https://mlsanity.com/paper/2210.12529/) (2022)

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

- [Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions](https://mlsanity.com/paper/2501.04437/) (2025)

## Abstract (arXiv)

Minimizing social bias strengthens societal bonds, promoting shared understanding and better decision-making. We revisit the definition of bias by discovering new bias types (e.g., societal status) in dynamic environments and describe them relative to context, such as culture, region, time, and personal background. Our framework includes eight hypotheses about bias and a minimizing bias strategy for each assumption as well as five methods as proposed solutions in LLM. The realization of the framework is yet to be completed.