# NBIAS: A Natural Language Processing Framework for Bias Identification in Text

arXiv: https://arxiv.org/abs/2308.01681 · HTML: https://mlsanity.com/paper/2308.01681/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 79 references that are in the map.
- First posted on arXiv 3 Aug 2023.

## Builds on (most cited first, 30 of 35)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Named Entity Recognition with Bidirectional LSTM-CNNs](https://mlsanity.com/paper/1511.08308/) (2015)
- [Social Biases in NLP Models as Barriers for Persons with Disabilities](https://mlsanity.com/paper/2005.00813/) (2020)
- [Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings](https://mlsanity.com/paper/1904.04047/) (2019)
- [MultiVerS: Improving scientific claim verification with weak supervision and full-document context](https://mlsanity.com/paper/2112.01640/) (2021)
- [A Unified Generative Framework for Various NER Subtasks](https://mlsanity.com/paper/2106.01223/) (2021)
- [M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection](https://mlsanity.com/paper/2305.14902/) (2023)
- [Automatically Neutralizing Subjective Bias in Text](https://mlsanity.com/paper/1911.09709/) (2019)
- [On Measures of Biases and Harms in NLP](https://mlsanity.com/paper/2108.03362/) (2021)
- [TENER: Adapting Transformer Encoder for Named Entity Recognition](https://mlsanity.com/paper/1911.04474/) (2019)
- [Few-shot classification in Named Entity Recognition Task](https://mlsanity.com/paper/1812.06158/) (2018)
- [Theories of "Gender" in NLP Bias Research](https://mlsanity.com/paper/2205.02526/) (2022)
- [Neural Media Bias Detection Using Distant Supervision With BABE -- Bias Annotations By Experts](https://mlsanity.com/paper/2209.14557/) (2022)
- [Multimodal Named Entity Recognition for Short Social Media Posts](https://mlsanity.com/paper/1802.07862/) (2018)
- [T-NER: An All-Round Python Library for Transformer-based Named Entity Recognition](https://mlsanity.com/paper/2209.12616/) (2022)
- [Massive vs. Curated Word Embeddings for Low-Resourced Languages. The Case of Yor`ub'a and Twi](https://mlsanity.com/paper/1912.02481/) (2019)
- [Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens](https://mlsanity.com/paper/2110.00521/) (2021)
- [Dbias: Detecting biases and ensuring Fairness in news articles](https://mlsanity.com/paper/2208.05777/) (2022)
- [Semi-Supervised Learning with Scarce Annotations](https://mlsanity.com/paper/1905.08845/) (2019)
- [Named Entity Recognition for Social Media Texts with Semantic Augmentation](https://mlsanity.com/paper/2010.15458/) (2020)
- [Biomedical named entity recognition using BERT in the machine reading comprehension framework](https://mlsanity.com/paper/2009.01560/) (2020)
- [Decomposed Meta-Learning for Few-Shot Named Entity Recognition](https://mlsanity.com/paper/2204.05751/) (2022)
- [An Annotated Dataset for Explainable Interpersonal Risk Factors of Mental Disturbance in Social Media Posts](https://mlsanity.com/paper/2305.18727/) (2023)
- [Word Embeddings via Causal Inference: Gender Bias Reducing and Semantic Information Preserving](https://mlsanity.com/paper/2112.05194/) (2021)
- [Probing Pre-trained Auto-regressive Language Models for Named Entity Typing and Recognition](https://mlsanity.com/paper/2108.11857/) (2021)
- [How Far Can It Go?: On Intrinsic Gender Bias Mitigation for Text Classification](https://mlsanity.com/paper/2301.12855/) (2023)
- [Combating Unknown Bias with Effective Bias-Conflicting Scoring and Gradient Alignment](https://mlsanity.com/paper/2111.13108/) (2021)

## Built on by (most cited first, 23 of 23)

- [Akal Badi ya Bias: An Exploratory Study of Gender Bias in Hindi Language Technology](https://mlsanity.com/paper/2405.06346/) (2024)
- [MBIAS: Mitigating Bias in Large Language Models While Retaining Context](https://mlsanity.com/paper/2405.11290/) (2024)
- [Quantifying and Mitigating Self-Preference Bias of LLM Judges](https://mlsanity.com/paper/2604.22891/) (2026)
- [FAIR Enough: How Can We Develop and Assess a FAIR-Compliant Dataset for Large Language Models' Training?](https://mlsanity.com/paper/2401.11033/) (2024)
- [Fake News Detection: Comparative Evaluation of BERT-like Models and Large Language Models with Generative AI-Annotated Data](https://mlsanity.com/paper/2412.14276/) (2024)
- [Unlocking Bias Detection: Leveraging Transformer-Based Models for Content Analysis](https://mlsanity.com/paper/2310.00347/) (2023)
- [Adaptable and Reliable Text Classification using Large Language Models](https://mlsanity.com/paper/2405.10523/) (2024)
- [FakeWatch: A Framework for Detecting Fake News to Ensure Credible Elections](https://mlsanity.com/paper/2403.09858/) (2024)
- [BEADs: Bias Evaluation Across Domains](https://mlsanity.com/paper/2406.04220/) (2024)
- [FakeWatch ElectionShield: A Benchmarking Framework to Detect Fake News for Credible US Elections](https://mlsanity.com/paper/2312.03730/) (2023)
- [REFINE-LM: Mitigating Language Model Stereotypes via Reinforcement Learning](https://mlsanity.com/paper/2408.09489/) (2024)
- [Desert Camels and Oil Sheikhs: Arab-Centric Red Teaming of Frontier LLMs](https://mlsanity.com/paper/2410.24049/) (2024)
- [FairSense-AI: Responsible AI Meets Sustainability](https://mlsanity.com/paper/2503.02865/) (2025)
- [Evaluating LLMs for Demographic-Targeted Social Bias Detection: A Comprehensive Benchmark Study](https://mlsanity.com/paper/2510.04641/) (2025)
- [AI Text Detectors and the Misclassification of Slightly Polished Arabic Text](https://mlsanity.com/paper/2511.16690/) (2025)
- [She had Cobalt Blue Eyes: Prompt Testing to Create Aligned and Sustainable Language Models](https://mlsanity.com/paper/2310.18333/) (2023)
- [Towards Fairer Health Recommendations: finding informative unbiased samples via Word Sense Disambiguation](https://mlsanity.com/paper/2409.07424/) (2024)
- [Responsible AI in NLP: GUS-Net Span-Level Bias Detection Dataset and Benchmark for Generalizations, Unfairness, and Stereotypes](https://mlsanity.com/paper/2410.08388/) (2024)
- [Cross-cultural value alignment frameworks for responsible AI governance: Evidence from China-West comparative analysis](https://mlsanity.com/paper/2511.17256/) (2025)
- [Textual Data Bias Detection and Mitigation -- An Extensible Pipeline with Experimental Evaluation](https://mlsanity.com/paper/2512.10734/) (2025)
- [A Multifaceted Analysis of Social Biases in Large Language Models](https://mlsanity.com/paper/2512.15792/) (2025)
- [Cross-Lingual Probing and Community-Grounded Analysis of Gender Bias in Low-Resource Bengali](https://mlsanity.com/paper/2601.17764/) (2026)
- [Investigating Disability Representations in Text-to-Image Models](https://mlsanity.com/paper/2602.04687/) (2026)

## Abstract (arXiv)

Bias in textual data can lead to skewed interpretations and outcomes when the data is used. These biases could perpetuate stereotypes, discrimination, or other forms of unfair treatment. An algorithm trained on biased data may end up making decisions that disproportionately impact a certain group of people. Therefore, it is crucial to detect and remove these biases to ensure the fair and ethical use of data. To this end, we develop a comprehensive and robust framework NBIAS that consists of four main layers: data, corpus construction, model development and an evaluation layer. The dataset is constructed by collecting diverse data from various domains, including social media, healthcare, and job hiring portals. As such, we applied a transformer-based token classification model that is able to identify bias words/ phrases through a unique named entity BIAS. In the evaluation procedure, we incorporate a blend of quantitative and qualitative measures to gauge the effectiveness of our models. We achieve accuracy improvements ranging from 1% to 8% compared to baselines. We are also able to generate a robust understanding of the model functioning. The proposed approach is applicable to a variety of biases and contributes to the fair and ethical use of textual data.