mlsanityData to 14 Oct 2026

Time-aware Prompting for Text Generation

arXiv 2211.02162 ↗First posted 3 Nov 2022cs.CLcited by 10

Not on the map. Why?

Abstract (arXiv)

In this paper, we study the effects of incorporating timestamps, such as document creation dates, into generation systems. Two types of time-aware prompts are investigated: (1) textual prompts that encode document timestamps in natural language sentences; and (2) linear prompts that convert timestamps into continuous vectors. To explore extrapolation to future data points, we further introduce a new data-to-text generation dataset, TempWikiBio, containing more than 4 millions of chronologically ordered revisions of biographical articles from English Wikipedia, each paired with structured personal profiles. Through data-to-text generation on TempWikiBio, text-to-text generation on the content transfer dataset, and summarization on XSum, we show that linear prompts on encoder and textual prompts improve the generation quality on all datasets. Despite having less performance drop when testing on data drawn from a later time, linear prompts focus more on non-temporal information and are less sensitive to the given timestamps, according to human evaluations and sensitivity analyses. Meanwhile, textual prompts establish the association between the given timestamps and the output dates, yielding more factual temporal information in the output.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 24 of its 44 references that are in the map. First posted on arXiv 3 Nov 2022.

Builds on

24 of 44 references.

References · 24

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  5. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  6. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  7. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,488
  8. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  9. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,317
  10. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  11. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,102
  12. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 762
12 more
  1. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 669
  2. 2021Time-Aware Language Models as Temporal Knowledge Basescited by 296
  3. 2021QuestEval: Summarization Asks for Fact-based Evaluationcited by 244
  4. 2021The GEM Benchmark: Natural Language Generation, its Evaluation and Metricscited by 239
  5. 2021Mind the Gap: Assessing Temporal Generalization in Neural Language Modelscited by 230
  6. 2021Towards Continual Knowledge Learning of Language Modelscited by 174
  7. 2019Handling Divergent Reference Texts when Evaluating Table-to-Text Generationcited by 119
  8. 2017Controllable Abstractive Summarizationcited by 110
  9. 2014Statistically Significant Detection of Linguistic Changecited by 82
  10. 2016Controlling Output Length in Neural Encoder-Decoderscited by 75
  11. 2021Temporal Effects on Pre-trained Models for Language Processing Taskscited by 46
  12. 2019Towards Content Transfer through Grounded Text Generationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 2; 2025: 2; 2026: 2.

10 papers.

  1. 2023Task-Adaptive Tokenization: Enhancing Long-Form Text Generation Efficacy in Mental Health and Beyondcited by 23
  2. 2024Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Modelscited by 23
  3. 2025It's High Time: A Survey of Temporal Question Answeringcited by 14
  4. 2024LegalLens: Leveraging LLMs for Legal Violation Identification in Unstructured Textcited by 12
  5. 2023Once Upon a textitTime in textitGraph: Relative-Time Pretraining for Complex Temporal Reasoningcited by 11
  6. 2025A Study into Investigating Temporal Robustness of LLMscited by 11
  7. 2023An Overview Of Temporal Commonsense Reasoning and Acquisitioncited by 10
  8. 2026ChronoState: Hidden Elapsed-Time Conditioning for Temporal-State Action Selection in Frozen-Backbone Language Modelscited by 1
  9. 2023Keeping in Time: Adding Temporal Context to Sentiment Analysis Modelscited by 0
  10. 2026RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environmentscited by 0