mlsanityData to 14 Oct 2026

Stay on topic with Classifier-Free Guidance

arXiv 2306.17806 ↗First posted 30 Jun 2023cs.CL cs.CV cs.LGcited by 91

Not on the map. Why?

Abstract (arXiv)

Classifier-Free Guidance (CFG) has recently emerged in text-to-image generation as a lightweight technique to encourage prompt-adherence in generations. In this work, we demonstrate that CFG can be used broadly as an inference-time technique in pure language modeling. We show that CFG (1) improves the performance of Pythia, GPT-2 and LLaMA-family models across an array of tasks: Q&A, reasoning, code generation, and machine translation, achieving SOTA on LAMBADA with LLaMA-7B over PaLM-540B; (2) brings improvements equivalent to a model with twice the parameter-count; (3) can stack alongside other inference-time methods like Chain-of-Thought and Self-Consistency, yielding further improvements in difficult tasks; (4) can be used to increase the faithfulness and coherence of assistants in challenging form-driven and content-driven prompts: in a human evaluation we show a 75% preference for GPT4All using CFG over baseline.

Key facts. Cited by 91 papers in the map (data through 14 Oct 2026). Builds on 59 of its 100 references that are in the map. First posted on arXiv 30 Jun 2023.

Builds on

59 of 100 references.

References · 59

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2022Training language models to follow instructions with human feedbackcited by 15,971
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  7. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  8. 2020Denoising Diffusion Implicit Modelscited by 9,781
  9. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  10. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  11. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  12. 2022Classifier-Free Diffusion Guidancecited by 5,847
38 more
  1. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  2. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  4. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  5. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  6. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  7. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  8. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  9. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  10. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  11. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,883
  12. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,183
  13. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,984
  14. 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,786
  15. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  16. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,255
  17. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,202
  18. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,125
  19. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,055
  20. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
  21. 2016The LAMBADA dataset: Word prediction requiring a broad discourse contextcited by 992
  22. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  23. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 885
  24. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 810
  25. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 799
  26. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 762
  27. 2023OpenAssistant Conversations -- Democratizing Large Language Model Alignmentcited by 721
  28. 2023Instruction Tuning with GPT-4cited by 686
  29. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 650
  30. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 642
  31. 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 609
  32. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 606
  33. 2019Release Strategies and the Social Impacts of Language Modelscited by 513
  34. 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 378
  35. 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 376
  36. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 327
  37. 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 310
  38. 2022VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidancecited by 285

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 31; 2025: 24; 2026: 30.

91 papers.

Sort:

By area:

  1. 2025Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Modelscited by 409
  2. 2025PaperBench: Evaluating AI's Ability to Replicate AI Researchcited by 321
  3. 2023Challenges and Applications of Large Language Modelscited by 254
  4. 2024Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMscited by 179
  5. 2024Simple Guidance Mechanisms for Discrete Diffusion Modelscited by 155
  6. 2024Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretrainingcited by 150
  7. 2024Why are Visually-Grounded Language Models Bad at Image Classification?cited by 102
  8. 2024Fine-Tuned Language Models Generate Stable Inorganic Materials as Textcited by 93
  9. 2023On Measuring Faithfulness or Self-consistency of Natural Language Explanationscited by 73
  10. 2024Scaling Instructable Agents Across Many Simulated Worldscited by 71
  11. 2024SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Wordscited by 68
  12. 2024Decoding-time Realignment of Language Modelscited by 67
38 more
  1. 2024V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimizationcited by 67
  2. 2024Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Trainingcited by 64
  3. 2024ControlVAR: Exploring Controllable Visual Autoregressive Modelingcited by 58
  4. 2025DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generationcited by 57
  5. 2024Measuring and Controlling Instruction (In)Stability in Language Model Dialogscited by 53
  6. 2023Controlled Text Generation via Language Model Arithmeticcited by 51
  7. 2024Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidancecited by 46
  8. 2024Erasing Conceptual Knowledge from Language Modelscited by 34
  9. 2025A Closer Look at System Prompt Robustnesscited by 32
  10. 2024Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budgetcited by 30
  11. 2025Parallel Scaling Law for Language Modelscited by 30
  12. 2023Prompt Highlighter: Interactive Control for Multi-Modal LLMscited by 29
  13. 2025Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidancecited by 27
  14. 2024SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Modelscited by 23
  15. 2024Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentationcited by 20
  16. 2023Guiding Image Captioning Models Toward More Specific Captionscited by 17
  17. 2025CtrlDiff: Boosting Large Diffusion Language Models with Dynamic Block Prediction and Controllable Generationcited by 17
  18. 2024Suppressing Pink Elephants with Direct Principle Feedbackcited by 15
  19. 2024UIClip: A Data-driven Model for Assessing User Interface Designcited by 14
  20. 2024Generalized Multi-Source Inference for Text Conditioned Music Diffusion Modelscited by 13
  21. 2024Audio Prompt Adapter: Unleashing Music Editing Abilities for Text-to-Music with Lightweight Finetuningcited by 12
  22. 2024Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LMcited by 11
  23. 2025Execution Guided Line-by-Line Code Generationcited by 10
  24. 2025Live Music Modelscited by 10
  25. 2024Diversity-Rewarded CFG Distillationcited by 9
  26. 2025Resurrect Mask AutoRegressive Modeling for Efficient and Scalable Image Generationcited by 9
  27. 2025A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMscited by 7
  28. 2024Can Large Language Model Summarizers Adapt to Diverse Scientific Communication Goals?cited by 6
  29. 2024Mitigating Hallucinations of Large Language Models in Medical Information Extraction via Contrastive Decodingcited by 5
  30. 2025KL Penalty Control via Perturbation for Direct Preference Optimizationcited by 5
  31. 2025Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLMcited by 5
  32. 2025Less is More: Improving LLM Reasoning with Minimal Test-Time Interventioncited by 5
  33. 2026HiRAS: A Hierarchical Multi-Agent Framework for Paper-to-Code Generation and Executioncited by 5
  34. 2025Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Modelscited by 4
  35. 2024Any-Property-Conditional Molecule Generation with Self-Criticism using Spanning Treescited by 3
  36. 2024Towards Zero-Shot Multimodal Machine Translationcited by 3
  37. 2024CorrSynth -- A Correlated Sampling Method for Diverse Dataset Generation from LLMscited by 3
  38. 2025Factored Agents: Decoupling In-Context Learning and Memorization for Robust Tool Usecited by 3

50 most cited of 91 All 91 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking
  2. 2025Classifier-Free Guidance: From High-Dimensional Analysis to Generalized Guidance Forms
  3. 2025Dynamic Classifier-Free Diffusion Guidance via Online Feedback
  4. 2025Classifier-free Guidance with Adaptive Scaling
  5. 2025Towards Understanding the Mechanisms of Classifier-Free Guidance
  6. 2026Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation
  7. 2024Analysis of Classifier-Free Guidance Weight Schedulers
  8. 2024Classifier-Free Guidance is a Predictor-Corrector