mlsanityData to 14 Oct 2026

RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework

arXiv 2410.19109 ↗First posted 24 Oct 2024cs.AI cs.CLcited by 11

Not on the map. Why?

Abstract (arXiv)

Despite significant advancements in natural language generation, controlling language models to produce texts with desired attributes remains a formidable challenge. In this work, we introduce RSA-Control, a training-free controllable text generation framework grounded in pragmatics. RSA-Control directs the generation process by recursively reasoning between imaginary speakers and listeners, enhancing the likelihood that target attributes are correctly interpreted by listeners amidst distractors. Additionally, we introduce a self-adjustable rationality parameter, which allows for automatic adjustment of control strength based on context. Our experiments, conducted with two task types and two types of language models, demonstrate that RSA-Control achieves strong attribute control while maintaining language fluency and content consistency. Our code is available at https://github.com/Ewanwong/RSA-Control.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 58 of its 85 references that are in the map. First posted on arXiv 24 Oct 2024.

Builds on

58 of 85 references.

References · 58

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  6. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  7. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  8. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  9. 2024Qwen2 Technical Reportcited by 2,120
  10. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
  11. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,255
  12. 2015Teaching Machines to Read and Comprehendcited by 1,049
38 more
  1. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  2. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 938
  3. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 799
  4. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 762
  5. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 710
  6. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 441
  7. 2021SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarizationcited by 407
  8. 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 378
  9. 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 376
  10. 2021Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLPcited by 337
  11. 2023Evaluating Large Language Models in Theory of Mind Taskscited by 222
  12. 2021Societal Biases in Language Generation: Progress and Challengescited by 202
  13. 2022COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamicscited by 161
  14. 2017Controlling Linguistic Style Aspects in Neural Language Generationcited by 149
  15. 2021Detoxifying Language Models Risks Marginalizing Minority Voicescited by 107
  16. 2022Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Modelscited by 97
  17. 2022Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Surveycited by 80
  18. 2016Reasoning About Pragmatics with Neural Listeners and Speakerscited by 68
  19. 2022Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Modelscited by 68
  20. 2022Mix and Match: Learning-free Controllable Text Generation using Energy Language Modelscited by 66
  21. 2019Zero-shot Text Classification With Generative Language Modelscited by 55
  22. 2022Making Science Simple: Corpora for the Lay Summarisation of Scientific Literaturecited by 55
  23. 2023Controlled Text Generation via Language Model Arithmeticcited by 51
  24. 2023ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfercited by 50
  25. 2023Self-Detoxifying Language Models via Toxification Reversalcited by 46
  26. 2023On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Researchcited by 44
  27. 2021Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causescited by 43
  28. 2018Pragmatically Informative Image Captioning with Character-Level Inferencecited by 42
  29. 2022Controllable Text Generation with Neurally-Decomposed Oraclecited by 41
  30. 2023Click: Controllable Text Generation with Sequence Likelihood Contrastive Learningcited by 41
  31. 2022DIRECTOR: Generator-Classifiers For Supervised Language Modelingcited by 38
  32. 2022Toxicity Detection with Generative Prompt-based Inferencecited by 35
  33. 2019Pragmatically Informative Text Generationcited by 32
  34. 2022DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Generationcited by 30
  35. 2023PREADD: Prefix-Adaptive Decoding for Controlled Text Generationcited by 29
  36. 2023Generating Summaries with Controllable Readability Levelscited by 24
  37. 2023Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Modelscited by 23
  38. 2024Overview of the BioLaySumm 2024 Shared Task on the Lay Summarization of Biomedical Research Articlescited by 18

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 5.

11 papers.

  1. 2026Value of Information: A Framework for Human-Agent Communicationcited by 12
  2. 2025B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainabilitycited by 4
  3. 2026Steering Language Models Before They Speak: Logit-Level Interventionscited by 4
  4. 2025C3TG: Conflict-aware, Composite, and Collaborative Controlled Text Generationcited by 3
  5. 2025Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialogcited by 2
  6. 2025LaPA2: Length-Aware Prefix and Prompt Attention Augmentation for Long-Form Controllable Text Generationcited by 1
  7. 2026Bye Bye Perspective API: Lessons for Building and Governing Measurement Infrastructurecited by 1
  8. 2025PG-CE: A Progressive Generation Dataset with Constraint Enhancement for Controllable Text Generationcited by 0
  9. 2025Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?cited by 0
  10. 2026Controllable Narrative Rendering for Enhanced Assisted Writingcited by 0
  11. 2026Sentence Specificity Scores for Collaborative Technical Documentation: A Domain-Transfer Studycited by 0