# Set-Aligning Framework for Auto-Regressive Event Temporal Graph Generation

arXiv: https://arxiv.org/abs/2404.01532 · HTML: https://mlsanity.com/paper/2404.01532/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 1 Apr 2024.

## Builds on (most cited first, 23 of 23)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [Pix2seq: A Language Modeling Framework for Object Detection](https://mlsanity.com/paper/2109.10852/) (2021)
- [Order Matters: Sequence to sequence for sets](https://mlsanity.com/paper/1511.06391/) (2015)
- [Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness](https://mlsanity.com/paper/2304.11633/) (2023)
- [Exploring the Feasibility of ChatGPT for Event Extraction](https://mlsanity.com/paper/2303.03836/) (2023)
- [A Multi-Axis Annotation Scheme for Event Temporal Relations](https://mlsanity.com/paper/1804.07828/) (2018)
- [Joint Event and Temporal Relation Extraction with Shared Representations and Structured Prediction](https://mlsanity.com/paper/1909.05360/) (2019)
- [Joint Constrained Learning for Event-Event Relation Extraction](https://mlsanity.com/paper/2010.06727/) (2020)
- [One2Set: Generating Diverse Keyphrases as a Set](https://mlsanity.com/paper/2105.11134/) (2021)
- [A Sequence-to-Set Network for Nested Named Entity Recognition](https://mlsanity.com/paper/2105.08901/) (2021)
- [An Improved Neural Baseline for Temporal Relation Extraction](https://mlsanity.com/paper/1909.00429/) (2019)
- [Deep Structured Neural Network for Event Temporal Relation Extraction](https://mlsanity.com/paper/1909.10094/) (2019)
- [CogCompTime: A Tool for Understanding Time in Natural Language Text](https://mlsanity.com/paper/1906.04940/) (2019)
- [Think about it! Improving defeasible reasoning by first modeling the question scenario](https://mlsanity.com/paper/2110.12349/) (2021)
- [Knowledge Graph Generation From Text](https://mlsanity.com/paper/2211.10511/) (2022)
- [Neural Language Modeling for Contextualized Temporal Graph Generation](https://mlsanity.com/paper/2010.10077/) (2020)
- [Extracting Event Temporal Relations via Hyperbolic Geometry](https://mlsanity.com/paper/2109.05527/) (2021)
- [Event Temporal Relation Extraction with Bayesian Translational Model](https://mlsanity.com/paper/2302.04985/) (2023)
- [Adapting RNN Sequence Prediction Model to Multi-label Set Prediction](https://mlsanity.com/paper/1904.05829/) (2019)
- [Conditional set generation using Seq2seq models](https://mlsanity.com/paper/2205.12485/) (2022)
- [Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance Minimization](https://mlsanity.com/paper/2305.18926/) (2023)

## Built on by (most cited first, 8 of 8)

- [AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora](https://mlsanity.com/paper/2505.23628/) (2025)
- [Cascading Large Language Models for Salient Event Graph Generation](https://mlsanity.com/paper/2406.18449/) (2024)
- [Beyond Pairwise: Global Zero-shot Temporal Graph Generation](https://mlsanity.com/paper/2502.11114/) (2025)
- [EventFull: Complete and Consistent Event Relation Annotation](https://mlsanity.com/paper/2412.12733/) (2024)
- [Explaining Matters: Leveraging Definitions and Semantic Expansion for Sexism Detection](https://mlsanity.com/paper/2506.06238/) (2025)
- [SafeSpeech: A Comprehensive and Interactive Tool for Analysing Sexist and Abusive Language in Conversations](https://mlsanity.com/paper/2503.06534/) (2025)
- [AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM](https://mlsanity.com/paper/2510.17934/) (2025)
- [Multi-Agent Procedural Graph Extraction with Structural and Logical Refinement](https://mlsanity.com/paper/2601.19170/) (2026)

## Abstract (arXiv)

Event temporal graphs have been shown as convenient and effective representations of complex temporal relations between events in text. Recent studies, which employ pre-trained language models to auto-regressively generate linearised graphs for constructing event temporal graphs, have shown promising results. However, these methods have often led to suboptimal graph generation as the linearised graphs exhibit set characteristics which are instead treated sequentially by language models. This discrepancy stems from the conventional text generation objectives, leading to erroneous penalisation of correct predictions caused by the misalignment of elements in target sequences. To address these challenges, we reframe the task as a conditional set generation problem, proposing a Set-aligning Framework tailored for the effective utilisation of Large Language Models (LLMs). The framework incorporates data augmentations and set-property regularisations designed to alleviate text generation loss penalties associated with the linearised graph edge sequences, thus encouraging the generation of more relation edges. Experimental results show that our framework surpasses existing baselines for event temporal graph generation. Furthermore, under zero-shot settings, the structural knowledge introduced through our framework notably improves model generalisation, particularly when the training examples available are limited.