FolioStart free

Computer Science · Literature

Research papers on Prompt engineering

Recent and highly-cited academic work on prompt engineering, gathered from Semantic Scholar, CrossRef and OpenAlex.

Search all 200M+ papers on this topic, free →Or track new prompt engineering papers automatically as they publish

  1. BNAI, NO-TOKEN, and MIND-UNITY: Pillars of a Systemic Revolution in Artificial Intelligence

    Wei, Jason, Wang, Xuezhi, Dale Schuurmans, et al. · 2022 · arXiv (Cornell University) · 4,301 citations

    AbstractThere is a failure mode in large language models that we do not have a good name for, and thatwe therefore tend not to treat seriously enough. It is not hallucination — the model is not assertingsomething false. It is not refusal — the model answers at length. It is the production of responses thatcarry the complete outward form of careful reasoning while the cognitive work that reasoning issupposed to represent has not, in any meaningful sense, occurred. We call this theatrical compliance,and we argue that it is, in practical terms, more dangerous than either of the failure modes thatcurrently dominate alignment research. This paper identifies the phenomenon, characterizes its fivep

  2. Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing

    Pengfei Liu, Weizhe Yuan, Jinlan Fu, et al. · 2022 · ACM Computing Surveys · 3,781 citations

    This article surveys and organizes research works in a new paradigm in natural language processing, which we dub “prompt-based learning.” Unlike traditional supervised learning, which trains a model to take in an input x and predict an output y as P ( y|x ), prompt-based learning is based on language models that model the probability of text directly. To use these models to perform prediction tasks, the original input x is modified using a template into a textual string prompt x′ that has some unfilled slots, and then the language model is used to probabilistically fill the unfilled information to obtain a final string x̂ , from which the final output y can be derived. This framework is powe

  4. A Survey of Large Language Models

    Wayne Xin Zhao, Kun Zhou, Junyi Li, et al. · 2026 · Frontiers of Computer Science · 1,475 citations

    Abstract The rapid evolution of large language models (LLMs) has driven a transformative shift in artificial intelligence (AI), reshaping both research paradigms and practical applications. Distinguished from their predecessors by unprecedented scale and advanced capabilities, LLMs necessitate new frameworks for understanding their development, behavior, and societal impact. This survey systematically reviews recent advancements in LLM techniques across four key dimensions: (1) pre-training methodologies, which establish core model capabilities through large-scale self-supervised training, architectural innovations, and data curation strategies; (2) post-training techniques, including superv

  6. Prompt Engineering in Large Language Models

    Ggaliwango Marvin, Nakayiza Hellen, Daudi Jjingo, et al. · 2024 · Algorithms for intelligent systems · 354 citations

    Prompt engineering has emerged as an indispensable technique for extending the capabilities of large language models (LLMs) and vision-language models (VLMs). This approach leverages task-specific instructions, known as prompts, to enhance model efficacy without modifying the core model parameters. Rather than updating the model parameters, prompts allow seamless integration of pre-trained models into downstream tasks by eliciting desired model behaviors solely based on the given prompt. Prompts can be natural language instructions that provide context to guide the model or learned vector representations that activate relevant knowledge. This burgeoning field has enabled success across vario

  7. Improving large language models for clinical named entity recognition via prompt engineering

    Yan Hu, Qingyu Chen, Jingcheng Du, et al. · 2024 · Journal of the American Medical Informatics Association · 304 citations

    IMPORTANCE: The study highlights the potential of large language models, specifically GPT-3.5 and GPT-4, in processing complex clinical data and extracting meaningful information with minimal training data. By developing and refining prompt-based strategies, we can significantly enhance the models' performance, making them viable tools for clinical NER tasks and possibly reducing the reliance on extensive annotated datasets. OBJECTIVES: This study quantifies the capabilities of GPT-3.5 and GPT-4 for clinical named entity recognition (NER) tasks and proposes task-specific prompts to improve their performance. MATERIALS AND METHODS: We evaluated these models on 2 clinical NER tasks: (1) to ext

  8. Unleashing the potential of prompt engineering for large language models

    B.‐C. CHEN, Zhaofeng Zhang, Nicolas Langrené, et al. · 2025 · Patterns · 301 citations

    This review explores the role of prompt engineering in unleashing the capabilities of large language models (LLMs). Prompt engineering is the process of structuring inputs, and it has emerged as a crucial technique for maximizing the utility and accuracy of these models. Both foundational and advanced prompt engineering methodologies-including techniques such as self-consistency, chain of thought, and generated knowledge, which can significantly enhance the performance of models-are explored in this paper. Additionally, the prompt methods for vision language models (VLMs) are examined in detail. Prompt methods are evaluated with subjective and objective metrics, ensuring a robust analysis of

  10. Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation With Large Language Models

    Hendrik Strobelt, Albert Webson, Victor Sanh, et al. · 2022 · IEEE Transactions on Visualization and Computer Graphics · 196 citations

    State-of-the-art neural language models can now be used to solve ad-hoc language tasks through zero-shot prompting without the need for supervised training. This approach has gained popularity in recent years, and researchers have demonstrated prompts that achieve strong accuracy on specific NLP tasks. However, finding a prompt for new tasks requires experimentation. Different prompt templates with different wording choices lead to significant accuracy differences. PromptIDE allows users to experiment with prompt variations, visualize prompt performance, and iteratively optimize prompts. We developed a workflow that allows users to first focus on model feedback using small data before moving

  13. Prompt engineering for large language models in test case generation

    Anatolii Husakovskyi · 2026 · Information Technology and Computer Engineering

    The purpose of this study was to perform a three-scenario comparative analysis of the accuracy of intelligent fault diagnosis in complex technical systems using ship power plants (SPPs) as a representative case. The research sought to determine which diagnostic configuration ensures the highest accuracy and robustness under varying operational conditions. Three methodological configurations were analysed: a baseline model based on Case-Based Reasoning (CBR); CBR enhanced with probabilistic analysis using Bayesian networks and Markov chains; and a comprehensive integration of CBR with probabilistic models and simulation modelling of cascading failures. Experiments were conducted under three t

  14. Prompt Engineering and Optimization in Large Language Models

    Ranjith Gundam, Kalyan Mandadhi · 2026 · International Scientific Journal of Engineering and Management

    Abstract: Large Language Models (LLMs) have emerged as transformative technologies, enabling sophisticated natural language understanding and generation across diverse applications. However, their effectiveness is heavily dependent on how instructions and queries are formulated. Prompt engineering—the art and science of crafting optimal input instructions—has become critical to unlocking the full potential of these models. This systematic review investigates contemporary approaches to prompt engineering and optimization in LLMs, examining techniques such as few-shot learning, chain-of-thought prompting, retrieval augmented generation, and dynamic prompt optimization. The study analyzes vari

  15. Beyond Prompt Engineering: The Evolution of Reasoning in Advanced Large Language Models

    Nan Wu - · 2025 · International Journal on Science and Technology

    This paper explores the evolving role of prompt engineering as large language models (LLMs) develop enhanced intrinsic reasoning capabilities. Initially essential for effective model performance, explicit prompting techniques are becoming less crucial with advanced models like GPT-4.5 and DeepSeek R1. Benchmark analyses indicate that intrinsic reasoning now solves most reasoning tasks efficiently, though explicit prompting still provides incremental benefits in specialized scenarios. Future directions emphasize intrinsic reasoning improvements, automated prompting strategies, and refined evaluation methods, marking a fundamental shift in leveraging LLMs.

  16. Cost, Complexity, and Efficacy of Prompt Engineering Techniques for Large Language Models

    Milind Cherukuri - · 2025 · International Journal on Science and Technology

    This research investigates the impact of various prompt engineering techniques on the length, cost, complexity, and accuracy of responses from large language models (LLMs). By comparing direct prompting with zero-shot, few-shot, and chain-of-thought (CoT) methods on tasks like GSM8K and creative writing, I analyze the trade-offs between token usage and response quality. Results show that while zero-shot CoT prompting is highly effective and cost-efficient, other methods like Least-to-Most and Tree-of-Thought add significant length and complexity without proportional accuracy gains. Additionally, I discuss the financial implications, finding that GPT-4’s unique pricing structure narrows the c

  18. Hierarchical Prompt Engineering for Remote Sensing Scene Understanding with Large Vision–Language Models

    Tianyang Chen, Jianliang Ai · 2025 · Remote Sensing

    Vision–language models (VLMs) show strong potential for remote-sensing scene classification but still struggle with fine-grained categories and distribution shifts. We introduce a hierarchical prompting framework that decomposes recognition into a coarse-to-fine decision process with structured outputs, combined with parameter-efficient adaptation using LoRA/QLoRA. To evaluate robustness without depending on external benchmarks, we construct five protocol variants of the AID (V0–V4) that systematically vary label granularity, class consolidation, and augmentation settings. Each variant is designed to align with a specific prompting style and hierarchy. The data pipeline follows a strict spli

Write your paper with these sources

Folio is the integrity-first research workspace: search 200M+ papers, save sources, and write with citations that format themselves. Free for students and researchers.

Start writing free →