mlsanityData to 7 Oct 2026

Guiding Large Language Models via Directional Stimulus Prompting

arXiv 2302.11520 ↗First posted 22 Feb 2023cs.CLcited by 94

Not on the map. Why?

Abstract (arXiv)

We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a small tunable policy model (e.g., T5) to generate an auxiliary directional stimulus prompt for each input instance. These directional stimulus prompts act as nuanced, instance-specific hints and clues to guide LLMs in generating desired outcomes, such as including specific keywords in the generated summary. Our approach sidesteps the challenges of direct LLM tuning by optimizing the policy model to explore directional stimulus prompts that align LLMs with desired behaviors. The policy model can be optimized through 1) supervised fine-tuning using labeled data and 2) reinforcement learning from offline or online rewards based on the LLM's output. We assess our method across summarization, dialogue response generation, and chain-of-thought reasoning tasks. Our experiments demonstrate that the framework consistently improves LLMs' (e.g., ChatGPT, Codex, InstructGPT) performance on these supervised tasks using minimal labeled data. Notably, using just 80 dialogues on the MultiWOZ dataset, our approach enhances ChatGPT's performance by an impressive 41.4%, matching or surpassing some fully supervised start-of-the-art models. Additionally, the instance-specific chain-of-thought prompt generated by our approach improves InstructGPT's reasoning accuracy compared to human-crafted or automatically generated prompts. The code and data are publicly available at urlhttps://github.com/Leezekun/Directional-Stimulus-Prompting.

Key facts. Cited by 94 papers in the map (data through 7 Oct 2026). Builds on 74 of its 110 references that are in the map. First posted on arXiv 22 Feb 2023.

Builds on

74 of 110 references.

References · 74

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2017Proximal Policy Optimization Algorithmscited by 14,441
  6. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  7. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  8. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  9. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  10. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  11. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  12. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
38 more
  1. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  2. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  3. 2020Learning to summarize from human feedbackcited by 2,562
  4. 2022Emergent Abilities of Large Language Modelscited by 2,483
  5. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  6. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  7. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  8. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,968
  9. 2019Language Models as Knowledge Bases?cited by 1,922
  10. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  11. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,548
  12. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,471
  13. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  14. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  15. 2019How Can We Know What Language Models Know?cited by 953
  16. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  17. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 809
  18. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  19. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  20. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  21. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  22. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 642
  23. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 599
  24. 2016Self-critical Sequence Training for Image Captioningcited by 544
  25. 2023Benchmarking Large Language Models for News Summarizationcited by 444
  26. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 434
  27. 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 377
  28. 2017A Deep Reinforced Model for Abstractive Summarizationcited by 364
  29. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 361
  30. 2016Solving General Arithmetic Word Problemscited by 353
  31. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 347
  32. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  33. 2022News Summarization and Evaluation in the Era of GPT-3cited by 324
  34. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
  35. 2021Recursively Summarizing Books with Human Feedbackcited by 287
  36. 2016Deep Reinforcement Learning for Dialogue Generationcited by 286
  37. 2022Black-Box Tuning for Language-Model-as-a-Servicecited by 254
  38. 2020AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Promptscited by 246

50 most cited of 74 All 74 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 20; 2024: 42; 2025: 25; 2026: 7.

94 papers.

Sort:

By area:

  1. 2024R-Judge: Benchmarking Safety Risk Awareness for LLM Agentscited by 268
  2. 2023Large Language Model Alignment: A Surveycited by 241
  3. 2024Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMscited by 224
  4. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 211
  5. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 203
  6. 2024Marco-o1: Towards Open Reasoning Models for Open-Ended Solutionscited by 142
  7. 2023Black-Box Prompt Optimization: Aligning Large Language Models without Model Trainingcited by 122
  8. 2025SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMscited by 110
  9. 2023Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agentscited by 76
  10. 2023Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Modelscited by 62
  11. 2023Explaining black box text modules in natural language with language modelscited by 61
  12. 2025A Systematic Survey of Automatic Prompt Optimization Techniquescited by 61
38 more
  1. 2024Large Language Model for Table Processing: A Surveycited by 52
  2. 2024Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledgecited by 49
  3. 2023Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4cited by 48
  4. 2023Learning from models beyond fine-tuningcited by 47
  5. 2024Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Modelscited by 44
  6. 2023Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RLcited by 37
  7. 2024Large Language Models as Zero-shot Dialogue State Tracker through Function Callingcited by 34
  8. 2023Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue Systemcited by 32
  9. 2024Planning Like Human: A Dual-process Framework for Dialogue Planningcited by 32
  10. 2023MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Followingcited by 30
  11. 2024Exploring Autonomous Agents through the Lens of Large Language Models: A Reviewcited by 30
  12. 2024FlowVQA: Mapping Multimodal Logic in Visual Question Answering with Flowchartscited by 27
  13. 2024AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Modelscited by 26
  14. 2024Evaluating the Prompt Steerability of Large Language Modelscited by 26
  15. 2023Grounding Foundation Models through Federated Transfer Learning: A General Frameworkcited by 24
  16. 2024MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimizationcited by 20
  17. 2025How to Train Your Advisor: Steering Black-Box LLMs with Advisor Modelscited by 20
  18. 2024Guided Profile Generation Improves Personalization with LLMscited by 19
  19. 2025On the Effect of Sampling Diversity in Scaling LLM Inferencecited by 18
  20. 2024Verbalized Machine Learning: Revisiting Machine Learning with Language Modelscited by 17
  21. 2024PromSec: Prompt Optimization for Secure Generation of Functional Source Code with Large Language Models (LLMs)cited by 17
  22. 2023Crystal: Introspective Reasoners Reinforced with Self-Feedbackcited by 15
  23. 2024WorldAfford: Affordance Grounding based on Natural Language Instructionscited by 14
  24. 2023Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Modelscited by 13
  25. 2023CHATEDIT: Towards Multi-turn Interactive Facial Image Editing via Dialoguecited by 12
  26. 2024Empowering Language Models with Active Inquiry for Deeper Understandingcited by 11
  27. 2024Exploring Prompt Engineering Practices in the Enterprisecited by 11
  28. 2024The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trendscited by 11
  29. 2024CAT-LLM: Style-enhanced Large Language Models with Text Style Definition for Chinese Article-style Transfercited by 10
  30. 2024AmbigNLG: Addressing Task Ambiguity in Instruction for NLGcited by 10
  31. 2024Towards Hierarchical Multi-Agent Workflows for Zero-Shot Prompt Optimizationcited by 10
  32. 2024LLM Based Multi-Agent Generation of Semi-structured Documents from Semantic Templates in the Public Administration Domaincited by 9
  33. 2024DARD: A Multi-Agent Approach for Task-Oriented Dialog Systemscited by 9
  34. 2023Enhancing Large Language Model Induced Task-Oriented Dialogue Systems Through Look-Forward Motivated Goalscited by 8
  35. 2024DisasterQA: A Benchmark for Assessing the performance of LLMs in Disaster Responsecited by 8
  36. 2023Advancements in Scientific Controllable Text Generation Methodscited by 7
  37. 2025The Behavior Gap: Evaluating Zero-shot LLM Agents in Complex Task-Oriented Dialogscited by 6
  38. 2026Protecting Language Models Against Unauthorized Distillation through Trace Rewritingcited by 6

50 most cited of 94 All 94 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025A Self-Supervised Reinforcement Learning Approach for Fine-Tuning Large Language Models Using Cross-Attention Signals
  2. 2025Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning
  3. 2026LLMs as High-Dimensional Nonlinear Autoregressive Models with Attention: Training, Alignment and Inference
  4. 2024Mixture-of-Instructions: Aligning Large Language Models via Mixture Prompting
  5. 2026Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning
  6. 2025REFINE-AF: A Task-Agnostic Framework to Align Language Models via Self-Generated Instructions using Reinforcement Learning from Automated Feedback
  7. 2025Thinking Inside the Mask: In-Place Prompting in Diffusion LLMs
  8. 2024Self-Instructed Derived Prompt Generation Meets In-Context Learning: Unlocking New Potential of Black-Box LLMs