mlsanityData to 7 Oct 2026

From Instruction to Output: The Role of Prompting in Modern NLG

arXiv 2602.11179 ↗First posted 21 Jan 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Prompt engineering has emerged as an integral technique for extending the strengths and abilities of Large Language Models (LLMs) to gain significant performance gains in various Natural Language Processing (NLP) tasks. This approach, which requires instructions to be composed in natural language to bring out the knowledge from LLMs in a structured way, has driven breakthroughs in various NLP tasks. Yet there is still no structured framework or coherent understanding of the varied prompt engineering methods and techniques, particularly in the field of Natural Language Generation (NLG). This survey aims to help fill that gap by outlining recent developments in prompt engineering, and their effect on different NLG tasks. It reviews recent advances in prompting methods and their impact on NLG tasks, presenting prompt design as an input-level control mechanism that complements fine-tuning and decoding approaches. The paper introduces a taxonomy of prompting paradigms, a decision framework for prompt selection based on varying factors for the practitioners, outlines emerging trends and challenges, and proposes a framework that links design, optimization, and evaluation to support more controllable and generalizable NLG.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 49 of its 66 references that are in the map. First posted on arXiv 21 Jan 2026.

Builds on

49 of 66 references.

References · 49

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  5. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  6. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  7. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  8. 2020Learning to summarize from human feedbackcited by 2,562
  9. 2024A Survey on LLM-as-a-Judgecited by 1,384
  10. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
  11. 2018Hierarchical Neural Story Generationcited by 1,182
  12. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
37 more
  1. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 778
  2. 2024LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methodscited by 451
  3. 2021True Few-Shot Learning with Language Modelscited by 343
  4. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 319
  5. 2020Evaluation of Text Generation: A Surveycited by 275
  6. 2023Better Zero-Shot Reasoning with Role-Play Promptingcited by 220
  7. 2023Large Language Model Guided Tree-of-Thoughtcited by 218
  8. 2017Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluationcited by 206
  9. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  10. 2020A Survey of Evaluation Metrics Used for NLG Systemscited by 164
  11. 2020NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraintscited by 146
  12. 2024ProSA: Assessing and Understanding the Prompt Sensitivity of LLMscited by 145
  13. 2023Large Language Models Understand and Can be Enhanced by Emotional Stimulicited by 143
  14. 2023Black-Box Prompt Optimization: Aligning Large Language Models without Model Trainingcited by 122
  15. 2024The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performancecited by 97
  16. 2023Thread of Thought Unraveling Chaotic Contextscited by 71
  17. 2022Contrastive Search Is What You Need For Neural Text Generationcited by 58
  18. 2024POSIX: A Prompt Sensitivity Index For Large Language Modelscited by 56
  19. 2024A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Taskscited by 46
  20. 2024Human-Centered Design Recommendations for LLM-as-a-Judgecited by 35
  21. 2024SPML: A DSL for Defending Language Models Against Prompt Attackscited by 33
  22. 2023Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraintscited by 31
  23. 2019A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directionscited by 26
  24. 2023Enhancing Large Language Models Against Inductive Instructions with Dual-critique Promptingcited by 21
  25. 2023Stealing the Decoding Algorithms of Language Modelscited by 19
  26. 2024Prompt-Based Length Controlled Generation with Multiple Control Typescited by 19
  27. 2024Selective Prompt Anchoring for Code Generationcited by 16
  28. 2025Consistency in Language Models: Current Landscape, Challenges, and Future Directionscited by 14
  29. 2024Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfercited by 13
  30. 2023Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Codecited by 9
  31. 2024Controlling Emotion in Text-to-Speech with Natural Language Promptscited by 8
  32. 2025Steering Large Language Models with Register Analysis for Arbitrary Style Transfercited by 5
  33. 2025Multilingual Prompt Engineering in Large Language Models: A Survey Across NLP Taskscited by 5
  34. 2021Discourse-Aware Soft Prompting for Text Generationcited by 4
  35. 2024Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarizationcited by 4
  36. 2023Guided scenarios with simulated expert personae: a remarkable strategy to perform cognitive workcited by 3
  37. 2024Plug and Play with Prompts: A Prompt Tuning Approach for Controlling Text Generationcited by 1

Built on by

Not cited yet.