mlsanityData to 7 Oct 2026

Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs

arXiv 2402.11218 ↗First posted 17 Feb 2024cs.CLcited by 16

Not on the map. Why?

Abstract (arXiv)

Controlled Text Generation (CTG) aims to produce texts that exhibit specific desired attributes. In this study, we introduce a pluggable CTG framework for Large Language Models (LLMs) named Dynamic Attribute Graphs-based controlled text generation (DATG). This framework utilizes an attribute scorer to evaluate the attributes of sentences generated by LLMs and constructs dynamic attribute graphs. DATG modulates the occurrence of key attribute words and key anti-attribute words, achieving effective attribute control without compromising the original capabilities of the model. We conduct experiments across four datasets in two tasks: toxicity mitigation and sentiment transformation, employing five LLMs as foundational models. Our findings highlight a remarkable enhancement in control accuracy, achieving a peak improvement of 19.29% over baseline methods in the most favorable task across four datasets. Additionally, we observe a significant decrease in perplexity, markedly improving text fluency.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 29 of its 39 references that are in the map. First posted on arXiv 17 Feb 2024.

Builds on

29 of 39 references.

References · 29

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  3. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  4. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  5. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  6. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
  7. 2023LIMA: Less Is More for Alignmentcited by 1,080
  8. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  9. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  10. 2023The Falcon Series of Open Language Modelscited by 526
  11. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 434
  12. 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 377
17 more
  1. 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 374
  2. 2021Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLPcited by 336
  3. 2023The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learningcited by 251
  4. 2023RAIN: Your Language Models Can Align Themselves without Finetuningcited by 149
  5. 2020DART: Open-Domain Structured Data Record to Text Generationcited by 144
  6. 2023Controlled Text Generation with Natural Language Instructionscited by 87
  7. 2022Controllable Natural Language Generation with Contrastive Prefixescited by 75
  8. 2022Critic-Guided Decoding for Controlled Text Generationcited by 45
  9. 2023Self-Detoxifying Language Models via Toxification Reversalcited by 45
  10. 2022DIRECTOR: Generator-Classifiers For Supervised Language Modelingcited by 38
  11. 2022DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Generationcited by 30
  12. 2023PREADD: Prefix-Adaptive Decoding for Controlled Text Generationcited by 29
  13. 2022CounterGeDi: A controllable approach to generate polite, detoxified and emotional counterspeechcited by 28
  14. 2023Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Modelscited by 23
  15. 2022Classifiers are Better Experts for Controllable Text Generationcited by 10
  16. 2023Air-Decoding: Attribute Distribution Reconstruction for Decoding-Time Controllable Text Generationcited by 10
  17. 2024CAT-LLM: Style-enhanced Large Language Models with Text Style Definition for Chinese Article-style Transfercited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 9; 2026: 3.

16 papers.

Sort:

By area:

  1. 2024Internal Consistency and Self-Feedback in Large Language Models: A Surveycited by 49
  2. 2025Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generationcited by 8
  3. 2025Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLMcited by 8
  4. 2024Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Modelscited by 5
  5. 2025JAM: Controllable and Responsible Text Generation via Causal Reasoning and Latent Vector Manipulationcited by 5
  6. 2025PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowchartscited by 3
  7. 2024LaSEr-Edit: Localized Span-level Error Editing with Energy-based Localizationcited by 2
  8. 2024Speak & Spell: LLM-Driven Controllable Phonetic Error Augmentation for Robust Dialogue State Trackingcited by 1
  9. 2025Stance-Driven Multimodal Controlled Statement Generation: New Dataset and Taskcited by 1
  10. 2025LaPA2: Length-Aware Prefix and Prompt Attention Augmentation for Long-Form Controllable Text Generationcited by 1
  11. 2025C3TG: Conflict-aware, Composite, and Collaborative Controlled Text Generationcited by 1
  12. 2026Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuningcited by 1
4 more
  1. 2026Bye Bye Perspective API: Lessons for Building and Governing Measurement Infrastructurecited by 1
  2. 2025AgentCTG: Harnessing Multi-Agent Collaboration for Fine-Grained Precise Control in Text Generationcited by 0
  3. 2025Generating Reading Comprehension Exercises with Large Language Models for Educational Applicationscited by 0
  4. 2026A Cross-lingual Comparison of Human and Classification Model Entrainment Behavior in Code-switched Speech Settingscited by 0