mlsanityData to 7 Oct 2026

PCFG-based Natural Language Interface Improves Generalization for Controlled Text Generation

arXiv 2210.07431 ↗First posted 14 Oct 2022cs.CL cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Existing work on controlled text generation (CTG) assumes a control interface of categorical attributes. In this work, we propose a natural language (NL) interface, where we craft a PCFG to embed the control attributes into natural language commands, and propose variants of existing CTG models that take commands as input. In our experiments, we design tailored setups to test model's generalization abilities. We find our PCFG-based command generation approach is effective for handling unseen commands compared to fix-set templates; our proposed NL models can effectively generalize to unseen attributes, a new ability enabled by the NL interface, as well as unseen attribute combinations. Interestingly, we discover that the simple conditional generation approach, enhanced with our proposed NL interface, is a strong baseline in those challenging settings.

Key facts. Cited by 4 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 14 Oct 2022.

Builds on

28 of 37 references.

References · 28

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  5. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  6. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  7. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  8. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  9. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  10. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  11. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  12. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 696
16 more
  1. 2022Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Modelcited by 557
  2. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 434
  3. 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 377
  4. 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 374
  5. 2018Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translationcited by 181
  6. 2022COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamicscited by 159
  7. 2018Generating Informative and Diverse Conversational Responses via Adversarial Information Maximizationcited by 114
  8. 2021A Recipe For Arbitrary Text Style Transfer with Large Language Modelscited by 107
  9. 2020Few-Shot Text Generation with Pattern-Exploiting Trainingcited by 87
  10. 2021A Plug-and-Play Method for Controlled Text Generationcited by 55
  11. 2022News Category Datasetcited by 42
  12. 2021Attribute Alignment: Controlling Text Generation from Pre-trained Language Modelscited by 27
  13. 2020Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generationcited by 26
  14. 2021Control Prefixes for Parameter-Efficient Text Generationcited by 23
  15. 2022Tailor: A Prompt-Based Approach to Attribute-Based Controlled Text Generationcited by 22
  16. 2020COD3S: Diverse Generation with Discrete Semantic Signaturescited by 9

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 2.

4 papers.

  1. 2024Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirementscited by 35
  2. 2025Re-Imagining Multimodal Instruction Tuning: A Representation Viewcited by 9
  3. 2024Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generationcited by 5
  4. 2025HiCaM: A Hierarchical-Causal Modification Framework for Long-Form Text Modificationcited by 0