# Beyond Pairwise: Global Zero-shot Temporal Graph Generation

arXiv: https://arxiv.org/abs/2502.11114 · HTML: https://mlsanity.com/paper/2502.11114/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 41 references that are in the map.
- First posted on arXiv 16 Feb 2025.

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](https://mlsanity.com/paper/2305.04091/) (2023)
- [Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model](https://mlsanity.com/paper/1906.01749/) (2019)
- [COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs](https://mlsanity.com/paper/2010.05953/) (2020)
- [Multi-relational Poincar'e Graph Embeddings](https://mlsanity.com/paper/1905.09791/) (2019)
- [A Multi-Axis Annotation Scheme for Event Temporal Relations](https://mlsanity.com/paper/1804.07828/) (2018)
- [MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction](https://mlsanity.com/paper/2211.07342/) (2022)
- [Joint Reasoning for Temporal and Causal Relations](https://mlsanity.com/paper/1906.04941/) (2019)
- [PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents](https://mlsanity.com/paper/2305.14564/) (2023)
- [Joint Constrained Learning for Event-Event Relation Extraction](https://mlsanity.com/paper/2010.06727/) (2020)
- [Zero-shot Temporal Relation Extraction with ChatGPT](https://mlsanity.com/paper/2304.05454/) (2023)
- [An Improved Neural Baseline for Temporal Relation Extraction](https://mlsanity.com/paper/1909.00429/) (2019)
- [Cross-document Coreference Resolution over Predicted Mentions](https://mlsanity.com/paper/2106.01210/) (2021)
- [Pre-trained Language Models Can be Fully Zero-Shot Learners](https://mlsanity.com/paper/2212.06950/) (2022)
- [Event Temporal Relation Extraction with Bayesian Translational Model](https://mlsanity.com/paper/2302.04985/) (2023)
- [Context-aware Event Forecasting via Graph Disentanglement](https://mlsanity.com/paper/2308.06480/) (2023)
- [TIMELINE: Exhaustive Annotation of Temporal Relations Supporting the Automatic Ordering of Events in News Articles](https://mlsanity.com/paper/2310.17802/) (2023)
- [Identifying Conspiracy Theories News based on Event Relation Graph](https://mlsanity.com/paper/2310.18545/) (2023)
- [Set-Aligning Framework for Auto-Regressive Event Temporal Graph Generation](https://mlsanity.com/paper/2404.01532/) (2024)
- [Are LLMs Good Annotators for Discourse-level Event Relation Extraction?](https://mlsanity.com/paper/2407.19568/) (2024)
- [NarrativeTime: Dense Temporal Annotation on a Timeline](https://mlsanity.com/paper/1908.11443/) (2019)
- [EventFull: Complete and Consistent Event Relation Annotation](https://mlsanity.com/paper/2412.12733/) (2024)

## Built on by (most cited first, 3 of 3)

- [Transformer-Based Temporal Information Extraction and Application: A Review](https://mlsanity.com/paper/2504.07470/) (2025)
- [Building Patient Journeys in Hebrew: A Language Model for Clinical Timeline Extraction](https://mlsanity.com/paper/2512.11502/) (2025)
- [Evaluating Temporal Reasoning in Large Language Models: Event Temporal Relation Extraction with Allen's Interval Algebra, Logical Consistency, and Relative Time in Narratives](https://mlsanity.com/paper/2610.17402/) (2026)

## Abstract (arXiv)

Temporal relation extraction (TRE) is a fundamental task in natural language processing (NLP) that involves identifying the temporal relationships between events in a document. Despite the advances in large language models (LLMs), their application to TRE remains limited. Most existing approaches rely on pairwise classification, where event pairs are classified in isolation, leading to computational inefficiency and a lack of global consistency in the resulting temporal graph. In this work, we propose a novel zero-shot method for TRE that generates a document's complete temporal graph in a single step, followed by temporal constraint optimization to refine predictions and enforce temporal consistency across relations. Additionally, we introduce OmniTemp, a new dataset with complete annotations for all pairs of targeted events within a document. Through experiments and analyses, we demonstrate that our method outperforms existing zero-shot approaches and offers a competitive alternative to supervised TRE models.