mlsanityData to 14 Oct 2026

Revisiting Prompt Optimization with Large Reasoning Models-A Case Study on Event Extraction

arXiv 2504.07357 ↗First posted 10 Apr 2025cs.CLcited by 6

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

Large Reasoning Models (LRMs) such as DeepSeek-R1 and OpenAI o1 have demonstrated remarkable capabilities in various reasoning tasks. Their strong capability to generate and reason over intermediate thoughts has also led to arguments that they may no longer require extensive prompt engineering or optimization to interpret human instructions and produce accurate outputs. In this work, we aim to systematically study this open question, using the structured task of event extraction for a case study. We experimented with two LRMs (DeepSeek-R1 and o1) and two general-purpose Large Language Models (LLMs) (GPT-4o and GPT-4.5), when they were used as task models or prompt optimizers. Our results show that on tasks as complicated as event extraction, LRMs as task models still benefit from prompt optimization, and that using LRMs as prompt optimizers yields more effective prompts. Our finding also generalizes to tasks beyond event extraction. Finally, we provide an error analysis of common errors made by LRMs and highlight the stability and consistency of LRMs in refining task instructions and event guidelines.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 29 of its 49 references that are in the map. First posted on arXiv 10 Apr 2025.

Builds on

29 of 49 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution28 Sep
  2. 2023Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling17 May
  3. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them17 Oct

Other references · 26

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  3. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  4. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  5. 2023Large Language Models as Optimizerscited by 864
  6. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 653
  7. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 366
  8. 2023Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discoverycited by 336
  9. 2023PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimizationcited by 233
  10. 2022GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Modelscited by 127
  11. 2024Evaluation of OpenAI o1: Opportunities and Challenges of AGIcited by 127
  12. 2023GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extractioncited by 119
14 more
  1. 2023Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learningcited by 115
  2. 2023Batch Prompting: Efficient Inference with Large Language Model APIscited by 85
  3. 2022Code4Struct: Code Generation for Few-Shot Event Structure Predictioncited by 70
  4. 2023CodeIE: Large Code Generation Models are Better Few-Shot Information Extractorscited by 68
  5. 2025A Survey of Automatic Prompt Engineering: An Optimization Perspectivecited by 41
  6. 2022GPS: Genetic Prompt Search for Efficient Few-shot Learningcited by 37
  7. 2024PromptWizard: Task-Aware Prompt Optimization Frameworkcited by 36
  8. 2024KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extractioncited by 34
  9. 2024G"odel Agent: A Self-Referential Agent Framework for Recursive Self-Improvementcited by 29
  10. 2023TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extractioncited by 28
  11. 2024Do Advanced Language Models Eliminate the Need for Prompt Engineering in Software Engineering?cited by 19
  12. 2025Instruction-Tuning LLMs for Event Extraction with Annotation Guidelinescited by 18
  13. 2023Instances Need More Care: Rewriting Prompts for Instances with LLMs in the Loop Yields Better Zero-Shot Performancecited by 9
  14. 2024EventRL: Enhancing Event Extraction with Outcome Supervision for Large Language Modelscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2025ZERA: Zero-init Instruction Evolving Refinement Agent -- From Zero Instructions to Structured Prompts via Principle-based Optimizationcited by 6
  2. 2025Multimodal Event Detection: Current Approaches and Defining the New Playground through LLMs and VLMscited by 1
  3. 2025When Does Meaning Backfire? Investigating the Role of AMRs in NLIcited by 1
  4. 2025Batch Prompting Suppresses Overthinking Reasoning Under Constraint: How Batch Prompting Suppresses Overthinking in Reasoning Modelscited by 1
  5. 2026RASPRef: Retrieval-Augmented Self-Supervised Prompt Refinement for Large Reasoning Modelscited by 0
  6. 2026TRUST Agents: A Collaborative Multi-Agent Framework for Fake News Detection, Explainable Verification, and Logic-Aware Claim Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Self-Supervised Prompt Optimization
  2. 2024GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers
  3. 2025DETAIL Matters: Measuring the Impact of Prompt Specificity on Reasoning in Large Language Models
  4. 2024Towards Generalist Prompting for Large Language Models by Mental Models
  5. 2025A Survey on Post-training of Large Language Models
  6. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond
  7. 2023StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving
  8. 2025Reasoning Strategies in Large Language Models: Can They Follow, Prefer, and Optimize?