Selecting Shots for Demographic Fairness in Few-Shot Learning with Large Language Models
Not on the map. Why?
Abstract (arXiv)
Recently, work in NLP has shifted to few-shot (in-context) learning, with large language models (LLMs) performing well across a range of tasks. However, while fairness evaluations have become a standard for supervised methods, little is known about the fairness of LLMs as prediction systems. Further, common standard methods for fairness involve access to models weights or are applied during finetuning, which are not applicable in few-shot learning. Do LLMs exhibit prediction biases when used for standard NLP tasks? In this work, we explore the effect of shots, which directly affect the performance of models, on the fairness of LLMs as NLP classification systems. We consider how different shot selection strategies, both existing and new demographically sensitive methods, affect model fairness across three standard fairness datasets. We discuss how future work can include LLM fairness evaluations.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 50 of its 71 references that are in the map. First posted on arXiv 14 Nov 2023.
Builds on
50 of 71 references.
References · 50
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
- 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
- 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
- 2017Billion-scale similarity search with GPUscited by 2,497
- 2016Equality of Opportunity in Supervised Learningcited by 2,007
38 more
- 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
- 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
- 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
- 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
- 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
- 2019How Can We Know What Language Models Know?cited by 959
- 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 924
- 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 710
- 2021Learning To Retrieve Prompts for In-Context Learningcited by 648
- 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 541
- 2021Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpuscited by 492
- 2020HateXplain: A Benchmark Dataset for Explainable Hate Speech Detectioncited by 407
- 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 349
- 2020BERTweet: A pre-trained language model for English Tweetscited by 346
- 2021True Few-Shot Learning with Language Modelscited by 344
- 2021Few-shot Learning with Multilingual Language Modelscited by 278
- 2021Surface Form Competition: Why the Highest Probability Answer Isn't Always Rightcited by 263
- 2022Prompting GPT-3 To Be Reliablecited by 260
- 2016Demographic Dialectal Variation in Social Media: A Case Study of African-American Englishcited by 196
- 2021Noisy Channel Language Model Prompting for Few-Shot Text Classificationcited by 165
- 2021Meta-learning via Language Model In-context Tuningcited by 164
- 2023In-Context Impersonation Reveals Large Language Models' Strengths and Biasescited by 155
- 2021CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLPcited by 142
- 2018An Intersectional Definition of Fairnesscited by 127
- 2023Language Model Behavior: A Comprehensive Surveycited by 92
- 2021A Survey on Gender Bias in Natural Language Processingcited by 89
- 2020Hurtful Words: Quantifying Biases in Clinical Contextual Word Embeddingscited by 79
- 2021Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Modelscited by 57
- 2020Investigating African-American Vernacular English in Transformer-Based Text Generationcited by 53
- 2022Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Taskscited by 48
- 2021Characterizing Intersectional Group Fairness with Worst-Case Comparisonscited by 42
- 2020jiant: A Software Toolkit for Research on General-Purpose Text Understanding Modelscited by 39
- 2021Your fairness may vary: Pretrained language model fairness in toxic text classificationcited by 39
- 2022Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Biascited by 33
- 2023Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibilitycited by 30
- 2021Intersectional Bias in Causal Language Modelscited by 24
- 2022Optimising Equal Opportunity Fairness in Model Trainingcited by 22
- 2021Measuring Fairness with Biased Rulers: A Survey on Quantifying Biases in Pretrained Language Modelscited by 20
Built on by
Citing papers per year: 2025: 1.
1 paper.