mlsanityData to 7 Oct 2026

TIMEDIAL: Temporal Commonsense Reasoning in Dialog

arXiv 2106.04571 ↗First posted 8 Jun 2021cs.CLcited by 55

Not on the map. Why?

Abstract (arXiv)

Everyday conversations require understanding everyday events, which in turn, requires understanding temporal commonsense concepts interwoven with those events. Despite recent progress with massive pre-trained language models (LMs) such as T5 and GPT-3, their capability of temporal reasoning in dialogs remains largely under-explored. In this paper, we present the first study to investigate pre-trained LMs for their temporal reasoning capabilities in dialogs by introducing a new task and a crowd-sourced English challenge set, TIMEDIAL. We formulate TIME-DIAL as a multiple-choice cloze task with over 1.1K carefully curated dialogs. Empirical results demonstrate that even the best performing models struggle on this task compared to humans, with 23 absolute points of gap in accuracy. Furthermore, our analysis reveals that the models fail to reason about dialog context correctly; instead, they rely on shallow cues based on existing temporal patterns in context, motivating future research for modeling temporal concepts in text and robust contextual reasoning about them. The dataset is publicly available at: https://github.com/google-research-datasets/timedial.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). Builds on 27 of its 47 references that are in the map. First posted on arXiv 8 Jun 2021.

Builds on

27 of 47 references.

References · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  6. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  7. 2018Annotation Artifacts in Natural Language Inference Datacited by 656
  8. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
  9. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  10. 2020Towards a Human-like Open-Domain Chatbotcited by 467
  11. 2016A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Storiescited by 413
  12. 2019Commonsense Knowledge Mining from Pretrained Modelscited by 189
15 more
  1. 2020Adversarial Filters of Dataset Biasescited by 159
  2. 2020Injecting Numerical Reasoning Skills into Language Modelscited by 133
  3. 2019"Going on a vacation" takes longer than "Going for a walk": A Study of Temporal Commonsense Understandingcited by 121
  4. 2020Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-trained Language Modelscited by 110
  5. 2019Counterfactual Story Reasoning and Generationcited by 87
  6. 2019Inducing Relational Knowledge from BERTcited by 75
  7. 2020TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questionscited by 65
  8. 2020Do Language Embeddings Capture Scales?cited by 63
  9. 2019Joint Reasoning for Temporal and Causal Relationscited by 60
  10. 2018Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledgecited by 48
  11. 2020Temporal Common Sense Acquisition with Minimal Supervisioncited by 38
  12. 2019Conversing by Reading: Contentful Neural Conversation with On-demand Machine Readingcited by 32
  13. 2016Who did What: A Large-Scale Person-Centered Cloze Datasetcited by 24
  14. 2018Improving Temporal Relation Extraction with a Globally Acquired Statistical Resourcecited by 17
  15. 2018Temporal Information Extraction by Predicting Relative Time-linescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 8; 2023: 17; 2024: 9; 2025: 10; 2026: 8.

55 papers.

Sort:

By area:

  1. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  2. 2024Large Language Models Can Learn Temporal Reasoningcited by 110
  3. 2023Language Model Behavior: A Comprehensive Surveycited by 92
  4. 2021QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehensioncited by 91
  5. 2023Test of Time: Instilling Video-Language Models with a Sense of Timecited by 51
  6. 2023Benchmarks for Automated Commonsense Reasoning: A Surveycited by 40
  7. 2022InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuningcited by 39
  8. 2022Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Surveycited by 38
  9. 2024IndoCulture: Exploring Geographically-Influenced Cultural Commonsense Reasoning Across Eleven Indonesian Provincescited by 38
  10. 2024TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulationcited by 22
  11. 2023Mitigating Temporal Misalignment by Discarding Outdated Factscited by 21
  12. 2023Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinkingcited by 19
38 more
  1. 2024Quantifying the Capabilities of LLMs across Scale and Precisioncited by 17
  2. 2023Salient Span Masking for Temporal Understandingcited by 14
  3. 2024Evaluating Dialect Robustness of Language Models via Conversation Understandingcited by 13
  4. 2022Knowledge Infused Decodingcited by 12
  5. 2025It's High Time: A Survey of Temporal Question Answeringcited by 12
  6. 2022Multiview Contextual Commonsense Inference: A New Dataset and Taskcited by 11
  7. 2023An Overview Of Temporal Commonsense Reasoning and Acquisitioncited by 10
  8. 2023Once Upon a textitTime in textitGraph: Relative-Time Pretraining for Complex Temporal Reasoningcited by 10
  9. 2024Temporal Knowledge Graph Question Answering: A Surveycited by 9
  10. 2025LexTime: A Benchmark for Temporal Ordering of Legal Eventscited by 9
  11. 2023CRoW: Benchmarking Commonsense Reasoning in Real-World Taskscited by 8
  12. 2022Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modelingcited by 7
  13. 2023Commonsense Reasoning for Conversational AI: A Survey of the State of the Artcited by 7
  14. 2023CLOMO: Counterfactual Logical Modification with Large Language Modelscited by 7
  15. 2023SYNDICOM: Improving Conversational Commonsense with Error-Injection and Natural Language Feedbackcited by 6
  16. 2021Natural Language Processing with Commonsense Knowledge: A Surveycited by 4
  17. 2025Towards Quantifying Commonsense Reasoning with Mechanistic Insightscited by 4
  18. 2026Real-Time Deadlines Reveal Fragile Temporal Adaptation in LLM Strategic Dialoguescited by 4
  19. 2023ReTAG: Reasoning Aware Table to Analytic Text Generationcited by 3
  20. 2023SituatedGen: Incorporating Geographical and Temporal Contexts into Generative Commonsense Reasoningcited by 3
  21. 2023CORECODE: A Common Sense Annotated Dialogue Dataset with Benchmark Tasks for Chinese Large Language Modelscited by 3
  22. 2024PARADISE: Evaluating Implicit Planning Skills of Language Models with Procedural Warnings and Tips Datasetcited by 3
  23. 2025AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarioscited by 3
  24. 2024Temporal Validity Change Predictioncited by 2
  25. 2025WinoWhat: A Parallel Corpus of Paraphrased WinoGrande Sentences with Common Sense Categorizationcited by 2
  26. 2025Discrete Minds in a Continuous World: Do Language Models Know Time Passes?cited by 2
  27. 2026Reasoning Gets Harder for LLMs Inside A Dialoguecited by 2
  28. 2022An Application of Pseudo-Log-Likelihoods to Natural Language Scoringcited by 1
  29. 2022DiscoSense: Commonsense Reasoning with Discourse Connectivescited by 1
  30. 2026Neuro-Symbolic Artificial Intelligence: A Task-Directed Survey in the Black-Box Models Eracited by 1
  31. 2021Advances in Multi-turn Dialogue Comprehension: A Surveycited by 0
  32. 2022A Probabilistic-Logic based Commonsense Representation Framework for Modelling Inferences with Multiple Antecedents and Varying Likelihoodscited by 0
  33. 2023Contrastive Learning for Inference in Dialoguecited by 0
  34. 2024Making a Long Story Short in Conversation Modelingcited by 0
  35. 2025From What to Respond to When to Respond: Timely Response Generation for Open-domain Dialogue Agentscited by 0
  36. 2025Commonsense Generation and Evaluation for Dialogue Systems using Large Language Modelscited by 0
  37. 2025TComQA: Extracting Temporal Commonsense from Textcited by 0
  38. 2025Structured yet Bounded Temporal Understanding in Large Language Modelscited by 0

50 most cited of 55 All 55 (JSON)