mlsanityData to 14 Oct 2026

Fairness-guided Few-shot Prompting for Large Language Models

arXiv 2303.13217 ↗First posted 23 Mar 2023cs.CL cs.AIcited by 53

Not on the map. Why?

Abstract (arXiv)

Large language models have demonstrated surprising ability to perform in-context learning, i.e., these models can be directly applied to solve numerous downstream tasks by conditioning on a prompt constructed by a few input-output examples. However, prior research has shown that in-context learning can suffer from high instability due to variations in training examples, example order, and prompt formats. Therefore, the construction of an appropriate prompt is essential for improving the performance of in-context learning. In this paper, we revisit this problem from the view of predictive bias. Specifically, we introduce a metric to evaluate the predictive bias of a fixed prompt against labels or a given attributes. Then we empirically show that prompts with higher bias always lead to unsatisfactory predictive quality. Based on this observation, we propose a novel search strategy based on the greedy search to identify the near-optimal prompt for improving the performance of in-context learning. We perform comprehensive experiments with state-of-the-art mainstream models such as GPT-3 on various downstream tasks. Our results indicate that our method can enhance the model's in-context learning performance in an effective and interpretable manner.

Key facts. Cited by 53 papers in the map (data through 14 Oct 2026). Builds on 19 of its 23 references that are in the map. First posted on arXiv 23 Mar 2023.

Builds on

19 of 23 references.

References · 19

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  5. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  6. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,984
  7. 2019Language Models as Knowledge Bases?cited by 1,936
  8. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  9. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  10. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  11. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  12. 2021GPT Understands, Toocited by 716
7 more
  1. 2021P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Taskscited by 689
  2. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 688
  3. 2021Learning How to Ask: Querying LMs with Mixtures of Soft Promptscited by 377
  4. 2021WARP: Word-level Adversarial ReProgrammingcited by 221
  5. 2023Active Prompting with Chain-of-Thought for Large Language Modelscited by 154
  6. 2022Improving Few-Shot Performance of Language Models via Nearest Neighbor Calibrationcited by 24
  7. 2022Fast Rates in Pool-Based Batch Active Learningcited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 19; 2025: 20; 2026: 6.

53 papers.

Sort:

By area:

  1. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,125
  2. 2025Memory in the Age of AI Agentscited by 303
  3. 2023Personality Traits in Large Language Modelscited by 169
  4. 2023Compositional Chain-of-Thought Prompting for Large Multimodal Modelscited by 164
  5. 2024OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AIcited by 71
  6. 2024In-context Learning with Retrieved Demonstrations for Language Models: A Surveycited by 70
  7. 2024When Search Engine Services meet Large Language Models: Visions and Challengescited by 59
  8. 2024Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learningcited by 50
  9. 2024Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Modelscited by 45
  10. 2023Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selectioncited by 37
  11. 2024Navigating LLM Ethics: Advancements, Challenges, and Future Directionscited by 28
  12. 2024Is the System Message Really Important to Jailbreaks in Large Language Models?cited by 20
38 more
  1. 2023Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation Extractioncited by 19
  2. 2024Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrappingcited by 14
  3. 2025UGMathBench: A Diverse and Dynamic Benchmark for Undergraduate-Level Mathematical Reasoning with Large Language Modelscited by 13
  4. 2025How Deep Do Large Language Models Internalize Scientific Literature and Citation Practices?cited by 10
  5. 2024DisasterQA: A Benchmark for Assessing the performance of LLMs in Disaster Responsecited by 9
  6. 2025Guiding LLM Decision-Making with Fairness Reward Modelscited by 9
  7. 2025Towards Fair In-Context Learning with Tabular Foundation Modelscited by 8
  8. 2024Image-to-Text Logic Jailbreak: Your Imagination can Help You Do Anythingcited by 7
  9. 2023KERMIT: Knowledge Graph Completion of Enhanced Relation Modeling with Inverse Transformationcited by 6
  10. 2025Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Studycited by 6
  11. 2024Automatic Combination of Sample Selection Strategies for Few-Shot Learningcited by 5
  12. 2025Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuningcited by 5
  13. 2025Exposing and Mitigating Calibration Biases and Demographic Unfairness in MLLM Few-Shot In-Context Learning for Medical Image Classificationcited by 5
  14. 2023Survey on AI Ethics: A Socio-technical Perspectivecited by 4
  15. 2024One size doesn't fit all: Predicting the Number of Examples for In-Context Learningcited by 4
  16. 2024SLIM-RAFT: A Novel Fine-Tuning Approach to Improve Cross-Linguistic Performance for Mercosur Common Nomenclaturecited by 3
  17. 2024Fair In-Context Learning via Latent Concept Variablescited by 3
  18. 2025Giving AI Personalities Leads to More Human-Like Reasoningcited by 3
  19. 2025On Fairness of Task Arithmetic: The Role of Task Vectorscited by 3
  20. 2025Large Language Models as Search Engines: Societal Challengescited by 3
  21. 2024The Future of Intelligent Healthcare: A Systematic Analysis and Discussion on the Integration and Impact of Robots Using Large Language Models for Healthcarecited by 2
  22. 2025Choices Speak Louder than Questionscited by 2
  23. 2025Prompt Engineering and the Effectiveness of Large Language Models in Enhancing Human Productivitycited by 2
  24. 2026IoT-Brain: Grounding LLMs for Semantic-Spatial Sensor Schedulingcited by 2
  25. 2023Metacognition-Enhanced Few-Shot Prompting With Positive Reinforcementcited by 1
  26. 2024Towards a Unified Paradigm: Integrating Recommendation Systems as a New Language in Large Modelscited by 1
  27. 2025In-Context Bias Propagation in LLM-Based Tabular Data Generationcited by 1
  28. 2025Prompt engineering and framework: implementation to increase code reliability based guideline for LLMscited by 1
  29. 2025A comprehensive study of LLM-based argument classification: from LLAMA through GPT-4o to Deepseek-R1cited by 1
  30. 2026DSIPA: Detecting LLM-Generated Texts via Sentiment-Invariant Patterns Divergence Analysiscited by 1
  31. 2024HateDebias: On the Diversity and Variability of Hate Speech Debiasingcited by 0
  32. 2024TaskComplexity: A Dataset for Task Complexity Classification with In-Context Learning, FLAN-T5 and GPT-4o Benchmarkscited by 0
  33. 2024The Power of Adaptation: Boosting In-Context Learning through Adaptive Promptingcited by 0
  34. 2025Zero-Shot Industrial Anomaly Segmentation with Image-Aware Prompt Generationcited by 0
  35. 2025Towards Human-AI Synergy in Requirements Engineering: A Framework and Preliminary Studycited by 0
  36. 2025Retrieval-Augmented Few-Shot Prompting Versus Fine-Tuning for Code Vulnerability Detectioncited by 0
  37. 2025Improving Fairness of Large Language Model-Based ICU Mortality Prediction via Case-Based Promptingcited by 0
  38. 2026Time-Continuous Modeling for Temporal Affective Pattern Recognition in LLMscited by 0

50 most cited of 53 All 53 (JSON)