mlsanityData to 7 Oct 2026

Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning

arXiv 2306.03350 ↗First posted 6 Jun 2023cs.CLcited by 41

Not on the map. Why?

Abstract (arXiv)

It has always been an important yet challenging problem to control language models to avoid generating texts with undesirable attributes, such as toxic language and unnatural repetition. We introduce Click for controllable text generation, which needs no modification to the model architecture and facilitates out-of-the-box use of trained models. It employs a contrastive loss on sequence likelihood, which fundamentally decreases the generation probability of negative samples (i.e., generations with undesirable attributes). It also adopts a novel likelihood ranking-based strategy to construct contrastive samples from model generations. On the tasks of language detoxification, sentiment steering, and repetition reduction, we show that Click outperforms strong baselines of controllable text generation and demonstrate the superiority of Click's sample construction strategy.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). Builds on 33 of its 43 references that are in the map. First posted on arXiv 6 Jun 2023.

Builds on

33 of 43 references.

References · 33

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  7. 2016Pointer Sentinel Mixture Modelscited by 2,992
  8. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  9. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  10. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
  11. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  12. 2022Red Teaming Language Models with Language Modelscited by 983
21 more
  1. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 896
  2. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  3. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  4. 2020Recipes for building an open-domain chatbotcited by 593
  5. 2019Neural Text Generation with Unlikelihood Trainingcited by 489
  6. 2021MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontierscited by 466
  7. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 434
  8. 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 377
  9. 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 374
  10. 2022Quark: Controllable Text Generation with Reinforced Unlearningcited by 236
  11. 2022A Contrastive Framework for Neural Text Generationcited by 224
  12. 2022BRIO: Bringing Order to Abstractive Summarizationcited by 161
  13. 2022Calibrating Sequence likelihood Improves Conditional Language Generationcited by 121
  14. 2022AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversationcited by 79
  15. 2020The Radicalization Risks of GPT-3 and Advanced Neural Language Modelscited by 76
  16. 2021On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmarkcited by 73
  17. 2022Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Modelscited by 67
  18. 2022The CRINGE Loss: Learning what language not to modelcited by 39
  19. 2022DIRECTOR: Generator-Classifiers For Supervised Language Modelingcited by 38
  20. 2022CoNT: Contrastive Neural Text Generationcited by 21
  21. 2022A Simple Contrastive Learning Objective for Alleviating Neural Text Degenerationcited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 17; 2025: 11; 2026: 8.

41 papers.

Sort:

By area:

  1. 2024SimPO: Simple Preference Optimization with a Reference-Free Rewardcited by 951
  2. 2025Group Sequence Policy Optimizationcited by 788
  3. 2024Self-Rewarding Language Modelscited by 654
  4. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  5. 2023Large Language Models Are Not Robust Multiple Choice Selectorscited by 454
  6. 2024Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judgecited by 202
  7. 2024On Prompt-Driven Safeguarding for Large Language Modelscited by 109
  8. 2023Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Losscited by 108
  9. 2023Building Emotional Support Chatbots in the Era of LLMscited by 62
  10. 2024Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypescited by 58
  11. 2025Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoningcited by 56
  12. 2024Model Extrapolation Expedites Alignmentcited by 37
29 more
  1. 2025IterResearch: Rethinking Long-Horizon Agents with Interaction Scalingcited by 22
  2. 2025Robust Multi-Objective Preference Alignment with Online DPOcited by 21
  3. 2025Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimizationcited by 16
  4. 2024LLM-based multi-agent poetry generation in non-cooperative environmentscited by 15
  5. 2025The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic Viewcited by 13
  6. 2023Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societiescited by 11
  7. 2024RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Frameworkcited by 11
  8. 2024Yi-Lightning Technical Reportcited by 11
  9. 2024DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusioncited by 9
  10. 2024E2CL: Exploration-based Error Correction Learning for Embodied Agentscited by 9
  11. 2026OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attentioncited by 9
  12. 2024Controllable Text Generation in the Instruction-Tuning Eracited by 7
  13. 2026AT2PO: Agentic Turn-based Policy Optimization via Tree Searchcited by 7
  14. 2026Length-Unbiased Sequence Policy Optimization: Revealing and Controlling Response Length Variation in RLVRcited by 7
  15. 2026CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agentscited by 7
  16. 2024Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimizationcited by 6
  17. 2025More of the Same: Persistent Representational Harms Under Increased Representationcited by 6
  18. 2024AIPO: Improving Training Objective for Iterative Preference Optimizationcited by 5
  19. 2024Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedbackcited by 4
  20. 2025Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMscited by 4
  21. 2025LLM Bias Detection and Mitigation through the Lens of Desired Distributionscited by 4
  22. 2024CLHA: A Simple yet Effective Contrastive Learning Framework for Human Alignmentcited by 3
  23. 2026Test-Time Detoxification without Training or Learning Anythingcited by 2
  24. 2025Social Bias in Multilingual Language Models: A Surveycited by 1
  25. 2024Enhancing Pre-Trained Generative Language Models with Question Attended Span Extraction on Machine Reading Comprehensioncited by 0
  26. 2025Towards Lightweight, Adaptive and Attribute-Aware Multi-Aspect Controllable Text Generation with Large Language Modelscited by 0
  27. 2026Soft Sequence Policy Optimizationcited by 0
  28. 2026Variational Proximal Policy Optimizationcited by 0
  29. 2026ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement Learningcited by 0