mlsanityData to 14 Oct 2026

Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training

arXiv 1911.03860 ↗First posted 10 Nov 2019cs.CLcited by 110

Not on the map. Why?

Abstract (arXiv)

Generative dialogue models currently suffer from a number of problems which standard maximum likelihood training does not address. They tend to produce generations that (i) rely too much on copying from the context, (ii) contain repetitions within utterances, (iii) overuse frequent words, and (iv) at a deeper level, contain logical flaws. In this work we show how all of these problems can be addressed by extending the recently introduced unlikelihood loss (Welleck et al., 2019) to these cases. We show that appropriate loss functions which regularize generated outputs to match human distributions are effective for the first three issues. For the last important general issue, we show applying unlikelihood to collected data of what a model should not do is effective for improving logical consistency, potentially paving the way to generative models with greater reasoning ability. We demonstrate the efficacy of our approach across several dialogue tasks.

Key facts. Cited by 110 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 31; 2022: 26; 2023: 25; 2024: 17; 2025: 7; 2026: 4.

110 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  2. 2022Red Teaming Language Models with Language Modelscited by 1,026
  3. 2024ORPO: Monolithic Preference Optimization without Reference Modelcited by 562
  4. 2022Memory-Based Model Editing at Scalecited by 447
  5. 2022Quark: Controllable Text Generation with Reinforced Unlearningcited by 237
  6. 2025The Surprising Effectiveness of Negative Reinforcement in LLM Reasoningcited by 162
  7. 2023Chain of Hindsight Aligns Language Models with Feedbackcited by 148
  8. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  9. 2021How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVENcited by 124
  10. 2021CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarizationcited by 120
  11. 2021Entity-level Factual Consistency of Abstractive Text Summarizationcited by 118
  12. 2022Locally Typical Samplingcited by 111
38 more
  1. 2023Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Losscited by 108
  2. 2021BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Datacited by 75
  3. 2024Don't Say No: Jailbreaking LLM by Suppressing Refusalcited by 56
  4. 2021Improving Factual Consistency of Abstractive Summarization via Question Answeringcited by 55
  5. 2021Paragraph-level Simplification of Medical Textscited by 53
  6. 2022Contrastive Learning Reduces Hallucination in Conversationscited by 40
  7. 2021AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Modelscited by 31
  8. 2022EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Trainingcited by 31
  9. 2022Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methodscited by 27
  10. 2021DeliData: A dataset for deliberation in multi-party problem solvingcited by 26
  11. 2022Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Modelscited by 26
  12. 2021Diversifying Dialog Generation via Adaptive Label Smoothingcited by 25
  13. 2021Decomposed Mutual Information Estimation for Contrastive Representation Learningcited by 25
  14. 2023CAT: A Contextualized Conceptualization and Instantiation Framework for Commonsense Reasoningcited by 25
  15. 2024A Survey on Human Preference Learning for Large Language Modelscited by 24
  16. 2021Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue modelscited by 23
  17. 2021Am I Me or You? State-of-the-Art Dialogue Models Cannot Maintain an Identitycited by 22
  18. 2024Improving Open-Ended Text Generation via Adaptive Decodingcited by 21
  19. 2024Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluationscited by 20
  20. 2021Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generationcited by 19
  21. 2021Relating Neural Text Degeneration to Exposure Biascited by 19
  22. 2021Transferring Knowledge from Vision to Language: How to Achieve it and how to Measure it?cited by 18
  23. 2024Non-autoregressive Generative Models for Reranking Recommendationcited by 18
  24. 2023Evolving Diverse Red-team Language Models in Multi-round Multi-agent Gamescited by 17
  25. 2021Implicit Unlikelihood Training: Improving Neural Text Generation with Reinforcement Learningcited by 16
  26. 2022Measuring and Improving Semantic Diversity of Dialogue Generationcited by 16
  27. 2023MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropiescited by 16
  28. 2023PRODIGy: a PROfile-based DIalogue Generation datasetcited by 16
  29. 2022Context Variance Evaluation of Pretrained Language Models for Prompt-based Biomedical Knowledge Probingcited by 15
  30. 2023Selective Generation for Controllable Language Modelscited by 15
  31. 2025RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalizationcited by 15
  32. 2021Unsupervised Enrichment of Persona-grounded Dialog with Background Storiescited by 14
  33. 2022Recent Advances in Neural Text Generation: A Task-Agnostic Surveycited by 14
  34. 2023Leveraging Large Language Models for Automated Dialogue Analysiscited by 14
  35. 2023Building Persona Consistent Dialogue Agents with Offline Reinforcement Learningcited by 14
  36. 2024Zero-shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrievalcited by 14
  37. 2021Accurate, yet inconsistent? Consistency Analysis on Language Understanding Modelscited by 13
  38. 2022BotsTalk: Machine-sourced Framework for Automatic Curation of Large-scale Multi-skill Dialogue Datasetscited by 13

50 most cited of 110 All 110 (JSON)