mlsanityData to 7 Oct 2026

Plug and Play Language Models: A Simple Approach to Controlled Text Generation

arXiv 1912.02164 ↗First posted 4 Dec 2019cs.CL cs.AI cs.LGcited by 793

Not on the map. Why?

Cited by 57 in LLM alignment / RLHF / preference optimisation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Large transformer-based language models (LMs) trained on huge text corpora have shown unparalleled generation capabilities. However, controlling attributes of the generated language (e.g. switching topic or sentiment) is difficult without modifying the model architecture or fine-tuning on attribute-specific data and entailing the significant cost of retraining. We propose a simple alternative: the Plug and Play Language Model (PPLM) for controllable language generation, which combines a pretrained LM with one or more simple attribute classifiers that guide text generation without any further training of the LM. In the canonical scenario we present, the attribute models are simple classifiers consisting of a user-specified bag of words or a single learned layer with 100,000 times fewer parameters than the LM. Sampling entails a forward and backward pass in which gradients from the attribute model push the LM's hidden activations and thus guide the generation. Model samples demonstrate control over a range of topics and sentiment styles, and extensive automated and human annotated evaluations show attribute alignment and fluency. PPLMs are flexible in that any combination of differentiable attribute models may be used to steer text generation, which will allow for diverse and creative applications beyond the examples given in this paper.

Key facts. Cited by 793 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 82; 2022: 150; 2023: 159; 2024: 153; 2025: 123; 2026: 126.

793 papers.

Sort:

By area:

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  3. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  4. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  5. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
  6. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
  7. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  8. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  9. 2023Steering Language Models With Activation Engineeringcited by 824
  10. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  11. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  12. 2023RRHF: Rank Responses to Align Language Models with Human Feedback without tearscited by 454
38 more
  1. 2022DiffuSeq: Sequence to Sequence Text Generation with Diffusion Modelscited by 439
  2. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 434
  3. 2022Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskcited by 417
  4. 2023Fine-Grained Human Feedback Gives Better Rewards for Language Model Trainingcited by 399
  5. 2021Differentially Private Fine-tuning of Language Modelscited by 392
  6. 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 374
  7. 2021Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLPcited by 336
  8. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 294
  9. 2022Generating Sequences by Learning to Self-Correctcited by 271
  10. 2022CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilitiescited by 245
  11. 2022Quark: Controllable Text Generation with Reinforced Unlearningcited by 236
  12. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 236
  13. 2021Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Modelscited by 219
  14. 2022Extracting Latent Steering Vectors from Pretrained Language Modelscited by 217
  15. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  16. 2021Societal Biases in Language Generation: Progress and Challengescited by 201
  17. 2022Generating Training Data with Language Models: Towards Zero-Shot Language Understandingcited by 199
  18. 2022Re3: Generating Longer Stories With Recursive Reprompting and Revisioncited by 193
  19. 2022Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionalscited by 191
  20. 2022SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Controlcited by 191
  21. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 189
  22. 2022Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Modelscited by 187
  23. 2023Automatically Auditing Large Language Models via Discrete Optimizationcited by 187
  24. 2023A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicitycited by 180
  25. 2022Convergence of score-based generative modeling for general data distributionscited by 179
  26. 2024A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicitycited by 179
  27. 2021Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Docited by 178
  28. 2022Convergence for score-based generative modeling with polynomial complexitycited by 176
  29. 2023Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Datacited by 171
  30. 2021Challenges in Detoxifying Language Modelscited by 169
  31. 2024COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllabilitycited by 162
  32. 2022COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamicscited by 159
  33. 2023Protein Design with Guided Discrete Diffusioncited by 154
  34. 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristicscited by 153
  35. 2021Symbolic Music Generation with Diffusion Modelscited by 152
  36. 2021ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmeticcited by 150
  37. 2023Large Language Models for Code: Security Hardening and Adversarial Testingcited by 149
  38. 2024Improving Instruction-Following in Language Models through Activation Steeringcited by 149

50 most cited of 793 All 793 (JSON)