mlsanityData to 7 Oct 2026

Prompting GPT-3 To Be Reliable

arXiv 2210.09150 ↗First posted 17 Oct 2022cs.CLcited by 258

Not on the map. Why?

Cited by 23 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Large language models (LLMs) show impressive abilities via few-shot prompting. Commercialized APIs such as OpenAI GPT-3 further increase their use in real-world language applications. However, the crucial problem of how to improve the reliability of GPT-3 is still under-explored. While reliability is a broad and vaguely defined term, we decompose reliability into four main facets that correspond to the existing framework of ML safety and are well-recognized to be important: generalizability, social biases, calibration, and factuality. Our core contribution is to establish simple and effective prompts that improve GPT-3's reliability as it: 1) generalizes out-of-distribution, 2) balances demographic distribution and uses natural language instructions to reduce social biases, 3) calibrates output probabilities, and 4) updates the LLM's factual knowledge and reasoning chains. With appropriate prompts, GPT-3 is more reliable than smaller-scale supervised models on all these facets. We release all processed datasets, evaluation scripts, and model predictions. Our systematic empirical study not only sheds new insights on the reliability of prompting LLMs, but more importantly, our prompting strategies can help practitioners more reliably use LLMs like GPT-3.

Key facts. Cited by 258 papers in the map (data through 7 Oct 2026). Builds on 87 of its 105 references that are in the map. First posted on arXiv 17 Oct 2022.

Builds on

87 of 105 references.

References · 87

  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. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  6. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  7. 2020Scaling Laws for Neural Language Modelscited by 6,411
  8. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  9. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  10. 2017On Calibration of Modern Neural Networkscited by 4,860
  11. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  12. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
38 more
  1. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  2. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  4. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  5. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  6. 2022Emergent Abilities of Large Language Modelscited by 2,483
  7. 2020Extracting Training Data from Large Language Modelscited by 2,144
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  9. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  10. 2019Language Models as Knowledge Bases?cited by 1,922
  11. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  12. 2016Concrete Problems in AI Safetycited by 1,582
  13. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  14. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  15. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  16. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  17. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
  18. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  19. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  20. 2022Red Teaming Language Models with Language Modelscited by 983
  21. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 979
  22. 2021Ethical and social risks of harm from Language Modelscited by 957
  23. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  24. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
  25. 2019Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inferencecited by 864
  26. 2022Quantifying Memorization Across Neural Language Modelscited by 755
  27. 2022Teaching Models to Express Their Uncertainty in Wordscited by 731
  28. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 713
  29. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
  30. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 703
  31. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 702
  32. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 683
  33. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 663
  34. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 657
  35. 2018Annotation Artifacts in Natural Language Inference Datacited by 656
  36. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  37. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
  38. 2021Editing Factual Knowledge in Language Modelscited by 548

50 most cited of 87 All 87 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 82; 2024: 94; 2025: 48; 2026: 28.

258 papers.

Sort:

By area:

  1. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  2. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  3. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  4. 2022A Survey on In-context Learningcited by 717
  5. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  6. 2023A Comprehensive Overview of Large Language Modelscited by 639
  7. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
  8. 2024Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researcherscited by 348
  9. 2023NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Railscited by 347
  10. 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflictscited by 333
  11. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
  12. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
38 more
  1. 2023Can We Edit Factual Knowledge by In-Context Learning?cited by 284
  2. 2024A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Modelscited by 266
  3. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 253
  4. 2023Specializing Smaller Language Models towards Multi-Step Reasoningcited by 249
  5. 2023Evaluating the Ripple Effects of Knowledge Editing in Language Modelscited by 238
  6. 2023Fine-tuning Language Models for Factualitycited by 219
  7. 2022On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoningcited by 191
  8. 2023Active Prompting with Chain-of-Thought for Large Language Modelscited by 154
  9. 2024Large Legal Fictions: Profiling Legal Hallucinations in Large Language Modelscited by 144
  10. 2023Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoningcited by 140
  11. 2023Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluationcited by 134
  12. 2023Deductive Verification of Chain-of-Thought Reasoningcited by 122
  13. 2023Evaluating and Mitigating Discrimination in Language Model Decisionscited by 117
  14. 2023Decomposing Uncertainty for Large Language Models through Input Clarification Ensemblingcited by 113
  15. 2024Unfamiliar Finetuning Examples Control How Language Models Hallucinatecited by 85
  16. 2024On Verbalized Confidence Scores for LLMscited by 83
  17. 2023Boosting Language Models Reasoning with Chain-of-Knowledge Promptingcited by 77
  18. 2023Context-faithful Prompting for Large Language Modelscited by 76
  19. 2023Eight Things to Know about Large Language Modelscited by 73
  20. 2024SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMscited by 67
  21. 2023Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competitioncited by 65
  22. 2023The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensivenesscited by 63
  23. 2023Uncertainty in Natural Language Generation: From Theory to Applicationscited by 61
  24. 2023Meta-in-context learning in large language modelscited by 59
  25. 2024Fairness in Large Language Models: A Taxonomic Surveycited by 57
  26. 2024Confidence Regulation Neurons in Language Modelscited by 57
  27. 2023Maybe Only 0.5% Data is Needed: A Preliminary Exploration of Low Training Data Instruction Tuningcited by 56
  28. 2024Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluationcited by 56
  29. 2024SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Modelscited by 54
  30. 2023Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLUcited by 53
  31. 2024WPO: Enhancing RLHF with Weighted Preference Optimizationcited by 53
  32. 2023Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noisecited by 52
  33. 2023All Languages Matter: On the Multilingual Safety of Large Language Modelscited by 51
  34. 2023Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrongcited by 51
  35. 2023Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Methodcited by 51
  36. 2024Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsensecited by 50
  37. 2024Context-DPO: Aligning Language Models for Context-Faithfulnesscited by 50
  38. 2023Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrationscited by 49

50 most cited of 258 All 258 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks
  2. 2023GPT-3.5, GPT-4, or BARD? Evaluating LLMs Reasoning Ability in Zero-Shot Setting and Performance Boosting Through Prompts
  3. 2026What Single-Prompt Accuracy Misses: A Multi-Variant Reliability Audit of Language Models
  4. 2024From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities
  5. 2023Assessing the Impact of Prompting Methods on ChatGPT's Mathematical Capabilities
  6. 2024Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models
  7. 2023GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond
  8. 2025Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks