# MTGER: Multi-view Temporal Graph Enhanced Temporal Reasoning over Time-Involved Document

arXiv: https://arxiv.org/abs/2311.04816 · HTML: https://mlsanity.com/paper/2311.04816/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 3 of its 45 references that are in the map.
- First posted on arXiv 8 Nov 2023.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 3 of 3)

- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [Relational Graph Attention Networks](https://mlsanity.com/paper/1904.05811/) (2019)

## Built on by (most cited first, 2 of 2)

- [TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models](https://mlsanity.com/paper/2405.18027/) (2024)
- [It's High Time: A Survey of Temporal Question Answering](https://mlsanity.com/paper/2505.20243/) (2025)

## Abstract (arXiv)

The facts and time in the document are intricately intertwined, making temporal reasoning over documents challenging. Previous work models time implicitly, making it difficult to handle such complex relationships. To address this issue, we propose MTGER, a novel Multi-view Temporal Graph Enhanced Temporal Reasoning framework for temporal reasoning over time-involved documents. Concretely, MTGER explicitly models the temporal relationships among facts by multi-view temporal graphs. On the one hand, the heterogeneous temporal graphs explicitly model the temporal and discourse relationships among facts; on the other hand, the multi-view mechanism captures both time-focused and fact-focused information, allowing the two views to complement each other through adaptive fusion. To further improve the implicit reasoning capability of the model, we design a self-supervised time-comparing objective. Extensive experimental results demonstrate the effectiveness of our method on the TimeQA and SituatedQA datasets. Furthermore, MTGER gives more consistent answers under question perturbations.