Few-Shot Prompting

Follow this topic Ask about this topic

Few-shot prompting studies how examples placed in a model’s input can teach it a task at inference time, supporting uses such as classification, question answering, information extraction, and tool use. Common approaches retrieve or select representative demonstrations, organize them with structured instructions or chain-of-thought reasoning, and optimize prompts or use examples to verify outputs. These methods are tested against zero-shot prompting and fine-tuned models on task-specific benchmarks, including text, clinical, and multimodal settings. Examples can improve accuracy and reduce the need for labeled data, but gains vary by model and task, and poorly matched or excessive context can distract models or fail to transfer to new domains.

Latest papers

43 papers3 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

A Cross-Domain Evaluation of Prompting Techniques for Large Language Models
Oct 17, 2026Kevin Krazius, Tim Schlippe, Paul LibbrechtLLM Prompting LLM Evaluation
IU International University of Applied Sciences, Germany
Multi-Target Few-Shot Prompting with Diffusion Language Models
Oct 15, 2026Anton Xue, Alan Li, Rahul SahaFew-Shot Prompting Diffusion Language Models
University of Texas at Austin
How Much Prompt Is Enough? A Blackbox Minimization of Few-Shots in LLMs
Sep 28, 2026Ali Alfageeh, Rahul Gopinath, Amin AlipourLLM Prompting Few-Shot Prompting
University of Houston · The University of Sydney
Language Specificity vs. Domain Diversity: Benchmarking Transformers for Bangla Medical NER
Sep 24, 2026Rakib Abdullah, Md. Maruful Islam MarufNamed Entity Recognition Multilingual Language Model Evaluation
Department of Artificial Intelligence and Data Science Green University of Bangladesh Dhaka, Bangladesh
ClusterFewshot: Improving Few-shot Optimization for LLMs workflow
Sep 22, 2026Omri Bar Haim, Shahar Katz, Lior WolfIn-Context Example Selection Large Language Model-Guided Optimization
Blavatnik School of Computer Science, Tel Aviv University
Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization
Sep 9, 2026Ayan Majumdar, Shounak Paul, Pushpdeep Singh +6VLM Evaluation LLM Prompting
MPI-SWS, Germany · Saarland University, Germany · INRIA, France
Large Language Model Few-Shot Prompting with Dilemma Training Outperforms Human Surrogates in Predicting Patient Preferences
Aug 26, 2026Natasha Ureyang, Sebastian Porsdam Mann, Yuxin Liu +9Human Preference Modeling Human-AI Decision Making
Telehealth Core, National University of Singapore Singapore, Singapore · Centre for Advanced Studies in Bioscience Innovation Law, Faculty of Law University of Copenhagen Copenhagen, Denmark · Centre for Biomedical Ethics, National University of Singapore Singapore, Singapore +1
DynaContext: Self-Improving Dynamic Contextualization of Optimized Prompts for Heterogeneous Parameter Extraction
Aug 22, 2026Joe Yu, Shibin Thomas Stanley Paul, Sven MayerLLM Prompting LLM Information Extraction
Technical University of Munich, Munich, Germany · TU Dortmund University, Dortmund, Germany · Research Center Trustworthy Data Science and Security, Dortmund, Germany
IDRAAK: From Multi-Agent NLP to Few-Shot Prompting for Semantic Drift Detection in Technical Requirements
Aug 9, 2026Shiva AhirRequirements Engineering Few-Shot Prompting
Department of Electrical & Computer Engineering Stony Brook University New York, United States of America
Example-Guided Prompting for Document-Level Text Simplification
Aug 5, 2026Marina Litvak, Ariel Perstin, Ilan Shtilman +1LLM Prompting Few-Shot Prompting
SCE, Beer Sheva, Israel · ScaDS.AI, TUD · Dresden, Germany
Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve
Aug 4, 2026Denys Pushkin, Albert Q. Jiang, Aryo Lotfi +2LLM Prompting CoT Reasoning
EPFL · Apple · Mistral AI
FLARE: Few-shot Learning-based Adaptive Reflective Engine
Aug 3, 2026Dhanasekar Sundararaman, Bharat Gandhi, Aashna Garg +1LLM Prompting Large Language Model-Guided Optimization
Microsoft Redmond, WA, USA
Few-Shot Concept Prompt Learning for Segmentation Foundation Models via Visual Grounding
Aug 3, 2026Rahul Venkataramani, Rachana SathishMedical Imaging Foundation Models Promptable Image Segmentation
Advanced Technology Group, GE HealthCare
What Transfers Under Source Shift? Definitions, Examples, and Fine-Tuning for Climate Disclosure Classification
Jul 20, 2026Guosheng Li, Fenghui Ren, Bin Liu +5LLM Fine-Tuning Few-Shot Prompting
School of Computing and Information Technology, University of Wollongong · School of Business, University of Wollongong · Business School, University of Sydney +1
Neuron-Aware Active Few-Shot Learning for LLMs
Jul 2, 2026Zhuowei Chen, Liwei Chen, Christian Schunn +2Active Learning Few-Shot Learning
University of Pittsburgh, USA
Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners
Jun 30, 2026Yunhan Wang, Eshika Khandelwal, Edson Araujo +3Multimodal Large Language Models Few-Shot Prompting
Tuebingen AI Center, University of Tuebingen, Germany
Comparing BERT Sentence-Pair Classification and Few-Shot LLM Prompting for Detecting Threat and Solution Framing in German Climate News
Jun 25, 2026Raven Adam, David Maier, Marie KoglerText Classification Few-Shot Prompting
University of Graz, Austria · Technical University of Graz, Austria
Automatic Generation of Highlights for Academic Paper Via Prompt-based Learning
Jun 24, 2026Yi Xiang, Chengzhi Zhang, Heng ZhangPrompt Learning Text Summarization
Department of Information Management, Nanjing University of Science and Technology, Nanjing, China
Concept-Constrained Prompt Learning for Few-Shot CLIP Adaptation
Jun 21, 2026Na Sang, Ding Ma, Rui Sang +1Prompt Learning VLM Adaptation
University of California, San Diego, La Jolla, CA, USA · Georgia Institute of Technology, Atlanta, GA, USA · Independent Researcher
ttda704 at SemEval-2026 Task 6: Structured Chain-of-Thought Prompting for Political Evasion Detection
Jun 14, 2026Tai Tran Tan, An Dinh ThienCoT Reasoning Pragmatic Reasoning in Language Models
University of Information Technology, Ho Chi Minh City, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam
Few-Shot Biomedical Relation Extraction with Large Language Models: A Viable Alternative to Supervised Learning?
Jun 13, 2026Jakob Mraz, Tomaž Curk, Blaž ZupanRelation Extraction Few-Shot Learning
University of Ljubljana, Ljubljana, Slovenia · Baylor College of Medicine, Houston, Texas, USA
Robust Active Learning for Few-Shot Example Selection in Text-to-SQL
Jun 8, 2026Arash PourhabibSubmodular Optimization LLM Grounding
NVIDIA
Sample-Efficient LLM-Based Detection of Malicious Web Server Logs with Forensically Explainable Reasoning
Jun 7, 2026Bernhard Kneip, Nhien-An Le-Khac, Hong-Hanh Nguyen-LeExplainable Artificial Intelligence CoT Reasoning
Automatic Extraction of Structured Information from Brain MRI Reports Using an Open-Weight Large Language Model
Jun 5, 2026Kaouther Mouheb, Amos Pomp, Antoine Manenti +9Few-Shot Prompting Clinical Information Extraction
Department of Radiology & Nuclear Medicine, Erasmus MC, Rotterdam, the Netherlands · Department of Epidemiology, Erasmus MC, Rotterdam, the Netherlands · Department of Electrical and Electronics Engineering, ENSEEIHT, Toulouse, France +3
Temporal Stability and Few-Shot Prompting in Math Task Assessment
May 28, 2026Danielle S. Fox, Brenda L. Robles, Elizabeth DiPietro Brovey +1Generative AI in Education Few-Shot Prompting
Learning Research and Development Center, University of Pittsburgh · Institute for Learning, University of Pittsburgh
Prompting Is All You Need: Multi-view Prompting Large Language Models for Aspect-Based Sentiment Analysis
May 27, 2026Nils Constantin Hellwig, Niklas Donhauser, Jakob Fehle +2LLM Prompting Few-Shot Prompting
1Media Informatics Group, University of Regensburg, Germany · 2Information Science Group, University of Regensburg, Germany
Strategy-Induct: Task-Level Strategy Induction for Instruction Generation
May 20, 2026Po-Chun Chen, Hen-Hsen Huang, Hsin-Hsi ChenLLM Prompting Few-Shot Prompting
Department of Computer Science and Information Engineering, National Taiwan University, Taiwan · Institute of Information Science, Academia Sinica, Taiwan · AI Research Center (AINTU), National Taiwan University, Taiwan
Few-Shot Large Language Models for Actionable Triage Categorization of Online Patient Inquiries
May 15, 2026Liqi Zhou, Jiafu LiHealthcare Clinical Triage
Locale-Conditioned Few-Shot Prompting Mitigates Demonstration Regurgitation in On-Device PII Substitution with Small Language Models
May 13, 2026Anuj Sadani, Deepak KumarPrivacy-Preserving Language Models Few-Shot Prompting
Evaluating Advanced Prompting on Gemini Flash for Multi-Hop Biomedical QA
May 5, 2026Ahmed Bajaber, Mohammed AlliheediMulti-Hop QA LLM Evaluation
1Saudi Med AI Lab (SMAIL) 2Prince Sultan University, Riyadh, Saudi Arabia · 2Prince Sultan University, Riyadh, Saudi Arabia · 3Al-Baha University, Al Baha, Saudi Arabia

Oct 17, 2026J/K move · Enter open · S save

A Cross-Domain Evaluation of Prompting Techniques for Large Language Models

Kevin Krazius, Tim Schlippe, Paul Libbrecht

IU International University of Applied Sciences, Germany

LLM Prompting LLM Evaluation Few-Shot Prompting Automatic Prompt Optimization Retrieval-Augmented Generation

Open paper AskPDF arXiv

Prompt engineering has become a central mechanism for guiding the behavior of Large Language Models (LLMs) across a wide range of reasoning and language understanding tasks [1], [2]. However, existing studies frequently evaluate prompting techniques using different LLMs, datasets, or task settings, making direct comparisons across methods and domains difficult [3]. Consequently, in this paper we present a controlled cross-domain evaluation of Zero-Shot prompting, Few-Shot prompting, Retrieval-Augmented Generation (RAG), and automatic prompt optimization based on a PE2-inspired optimization pipeline [4]-[6]. All experiments were conducted with the same LLM and evaluated on six benchmark datasets covering arithmetic reasoning, logical reasoning, commonsense reasoning, and factual verification. The results show that no prompting strategy consistently outperforms the others across all domains, and pairwise statistical comparisons of the highest-performing configurations revealed no significant differences. RAG achieves the highest overall average accuracy of 78.33% when 300 examples are available for retrieval, while Few-Shot Prompting achieves comparatively high accuracies across several structured reasoning tasks. Zero-Shot Prompting remains competitive on tasks with self-contained inputs, whereas the PE2-inspired optimization approach produces stable but not systematically superior results compared to the other evaluated prompting techniques. Furthermore, increasing the number of task-specific examples does not consistently improve performance across prompting techniques, indicating strong domain and task dependency. These findings suggest that prompting techniques should be selected adaptively based on task characteristics rather than treated as universally applicable optimization strategies.