mlsanityData to 7 Oct 2026

Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints

arXiv 2302.09185 ↗First posted 17 Feb 2023cs.CL cs.AI cs.LGcited by 31

Not on the map. Why?

Abstract (arXiv)

The limits of open-ended generative models are unclear, yet increasingly important. What causes them to succeed and what causes them to fail? In this paper, we take a prompt-centric approach to analyzing and bounding the abilities of open-ended generative models. We present a generic methodology of analysis with two challenging prompt constraint types: structural and stylistic. These constraint types are categorized into a set of well-defined constraints that are analyzable by a single prompt. We then systematically create a diverse set of simple, natural, and useful prompts to robustly analyze each individual constraint. Using the GPT-3 text-davinci-002 model as a case study, we generate outputs from our collection of prompts and analyze the model's generative failures. We also show the generalizability of our proposed method on other large models like BLOOM and OPT. Our results and our in-context mitigation strategies reveal open challenges for future research. We have publicly released our code at https://github.com/SALT-NLP/Bound-Cap-LLM.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 28 of its 37 references that are in the map. First posted on arXiv 17 Feb 2023.

Builds on

28 of 37 references.

References · 28

  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. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  7. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  8. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  9. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  10. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,718
  11. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
  12. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
16 more
  1. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
  2. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  3. 2018Hierarchical Neural Story Generationcited by 1,182
  4. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,026
  5. 2021Measuring Coding Challenge Competence With APPScited by 879
  6. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  7. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  8. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 599
  9. 2016A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Storiescited by 413
  10. 2021BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generationcited by 410
  11. 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 377
  12. 2022Can language models learn from explanations in context?cited by 248
  13. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  14. 2021A Recipe For Arbitrary Text Style Transfer with Large Language Modelscited by 107
  15. 2020STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generationcited by 56
  16. 2020CoCon: A Self-Supervised Approach for Controlled Text Generationcited by 47

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 13; 2025: 4; 2026: 7.

31 papers.

Sort:

By area:

  1. 2023Unveiling Security, Privacy, and Ethical Concerns of ChatGPTcited by 53
  2. 2024Understanding Information Storage and Transfer in Multi-modal Large Language Modelscited by 48
  3. 2023Large Language Models as Tax Attorneys: A Case Study in Legal Capabilities Emergencecited by 42
  4. 2023SoK: Memorization in General-Purpose Large Language Modelscited by 36
  5. 2024LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraintscited by 34
  6. 2024Measuring and Benchmarking Large Language Models' Capabilities to Generate Persuasive Languagecited by 31
  7. 2024Adaptable Logical Control for Large Language Modelscited by 30
  8. 2024SPRIG: Improving Large Language Model Performance by System Prompt Optimizationcited by 28
  9. 2024Benchmarking Large Language Models on Controllable Generation under Diversified Instructionscited by 26
  10. 2023GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidencecited by 14
  11. 2024Subtle Biases Need Subtler Measures: Dual Metrics for Evaluating Representative and Affinity Bias in Large Language Modelscited by 10
  12. 2024ELF-Gym: Evaluating Large Language Models Generated Features for Tabular Predictioncited by 10
19 more
  1. 2024CoDa: Constrained Generation based Data Augmentation for Low-Resource NLPcited by 9
  2. 2024ABEX: Data Augmentation for Low-Resource NLU via Expanding Abstract Descriptionscited by 8
  3. 2026Mitigating Bias in Locally Constrained Decoding via Tractable Proposalscited by 8
  4. 2025Bandit-Based Prompt Design Strategy Selection Improves Prompt Optimizerscited by 7
  5. 2023Developing Effective Educational Chatbots with ChatGPT prompts: Insights from Preliminary Tests in a Case Study on Social Media Literacy (with appendix)cited by 6
  6. 2024LLM can Achieve Self-Regulation via Hyperparameter Aware Generationcited by 4
  7. 2025A Large Language Model-Enabled Control Architecture for Dynamic Resource Capability Exploration in Multi-Agent Manufacturing Systemscited by 4
  8. 2026Say It My Way: Exploring Control in Conversational Visual Question Answering with Blind Userscited by 2
  9. 2023When Giant Language Brains Just Aren't Enough! Domain Pizzazz with Knowledge Sparkle Dustcited by 1
  10. 2025Self-Review Framework for Enhancing Instruction Following Capability of LLMcited by 1
  11. 2026LexChronos: An Agentic Framework for Structured Event Timeline Extraction in Indian Jurisprudencecited by 1
  12. 2023Evaluating, Understanding, and Improving Constrained Text Generation for Large Language Modelscited by 0
  13. 2024Task-oriented Prompt Enhancement via Script Generationcited by 0
  14. 2024Automatic Prompt Generation and Grounding Object Detection for Zero-Shot Image Anomaly Detectioncited by 0
  15. 2025Knowledge Conceptualization Impacts RAG Efficacycited by 0
  16. 2026From Instruction to Output: The Role of Prompting in Modern NLGcited by 0
  17. 2026The Parser Already Knows: Lightweight Bias Correction in Constrained Decodingcited by 0
  18. 2026Do Influence Tactics Matter? Investigating Prompt Framing Effects in LLM Code Generationcited by 0
  19. 2026Provably Tractable NFA-Constrained Language Generation via HMMscited by 0