# Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biases

arXiv: https://arxiv.org/abs/2112.07868 · HTML: https://mlsanity.com/paper/2112.07868/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 71 references that are in the map.
- First posted on arXiv 15 Dec 2021.

## Builds on (most cited first, 30 of 33)

- [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)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [Factual Probing Is [MASK]: Learning vs. Learning to Recall](https://mlsanity.com/paper/2104.05240/) (2021)
- [Predicting the Type and Target of Offensive Posts in Social Media](https://mlsanity.com/paper/1902.09666/) (2019)
- [Racial Bias in Hate Speech and Abusive Language Detection Datasets](https://mlsanity.com/paper/1905.12516/) (2019)
- [HateBERT: Retraining BERT for Abusive Language Detection in English](https://mlsanity.com/paper/2010.12472/) (2020)
- [Commonsense Knowledge Mining from Pretrained Models](https://mlsanity.com/paper/1909.00505/) (2019)
- [Deep Learning for Hate Speech Detection in Tweets](https://mlsanity.com/paper/1706.00188/) (2017)
- [Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models](https://mlsanity.com/paper/2106.13353/) (2021)
- [Understanding Abuse: A Typology of Abusive Language Detection Subtasks](https://mlsanity.com/paper/1705.09899/) (2017)
- [CONAN -- COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech](https://mlsanity.com/paper/1910.03270/) (2019)
- [Evaluating Commonsense in Pre-trained Language Models](https://mlsanity.com/paper/1911.11931/) (2019)
- [A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks](https://mlsanity.com/paper/1611.01587/) (2016)
- [SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identification](https://mlsanity.com/paper/2004.14454/) (2020)
- [Overview of the HASOC track at FIRE 2020: Hate Speech and Offensive Content Identification in Indo-European Languages](https://mlsanity.com/paper/2108.05927/) (2021)

## Built on by (most cited first, 21 of 21)

- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples](https://mlsanity.com/paper/2307.11729/) (2023)
- [COLD: A Benchmark for Chinese Offensive Language Detection](https://mlsanity.com/paper/2201.06025/) (2022)
- [Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models](https://mlsanity.com/paper/2205.11503/) (2022)
- [Toxicity Detection with Generative Prompt-based Inference](https://mlsanity.com/paper/2205.12390/) (2022)
- [The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks](https://mlsanity.com/paper/2210.10040/) (2022)
- [Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions](https://mlsanity.com/paper/2404.11023/) (2024)
- [A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation](https://mlsanity.com/paper/2310.12127/) (2023)
- [Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models](https://mlsanity.com/paper/2302.07388/) (2023)
- [Silenced Biases: The Dark Side LLMs Learned to Refuse](https://mlsanity.com/paper/2511.03369/) (2025)
- [BiasTestGPT: Using ChatGPT for Social Bias Testing of Language Models](https://mlsanity.com/paper/2302.07371/) (2023)
- [Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructions](https://mlsanity.com/paper/2211.11798/) (2022)
- [Disentangling Dialect from Social Bias via Multitask Learning to Improve Fairness](https://mlsanity.com/paper/2406.09977/) (2024)
- [ViDAS: Vision-based Danger Assessment and Scoring](https://mlsanity.com/paper/2410.00477/) (2024)
- [ViLBias: Detecting and Reasoning about Bias in Multimodal Content](https://mlsanity.com/paper/2412.17052/) (2024)
- [Self-Anchored Attention Model for Sample-Efficient Classification of Prosocial Text Chat](https://mlsanity.com/paper/2506.09259/) (2025)
- [Prosocial Behavior Detection in Player Game Chat: From Aligning Human-AI Definitions to Efficient Annotation at Scale](https://mlsanity.com/paper/2508.05938/) (2025)
- [VARS: Vision-based Assessment of Risk in Security Systems](https://mlsanity.com/paper/2410.19642/) (2024)
- [Bias Testing and Mitigation in Black Box LLMs using Metamorphic Relations](https://mlsanity.com/paper/2512.00556/) (2025)
- [Contextual StereoSet: Stress-Testing Bias Alignment Robustness in Large Language Models](https://mlsanity.com/paper/2601.10460/) (2026)
- [Discovering the Hidden Role of Gini Index In Prompt-based Classification](https://mlsanity.com/paper/2603.15654/) (2026)

## Abstract (arXiv)

Detecting social bias in text is challenging due to nuance, subjectivity, and difficulty in obtaining good quality labeled datasets at scale, especially given the evolving nature of social biases and society. To address these challenges, we propose a few-shot instruction-based method for prompting pre-trained language models (LMs). We select a few class-balanced exemplars from a small support repository that are closest to the query to be labeled in the embedding space. We then provide the LM with instruction that consists of this subset of labeled exemplars, the query text to be classified, a definition of bias, and prompt it to make a decision. We demonstrate that large LMs used in a few-shot context can detect different types of fine-grained biases with similar and sometimes superior accuracy to fine-tuned models. We observe that the largest 530B parameter model is significantly more effective in detecting social bias compared to smaller models (achieving at least 13% improvement in AUC metric compared to other models). It also maintains a high AUC (dropping less than 2%) when the labeled repository is reduced to as few as 100 samples. Large pretrained language models thus make it easier and quicker to build new bias detectors.