# A Study of Temporal Fusion Strategies for Named Entity Recognition in Historical Texts

arXiv: https://arxiv.org/abs/2606.27881 · HTML: https://mlsanity.com/paper/2606.27881/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 26 Jun 2026.

## Builds on (most cited first, 22 of 22)

- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Language Models Represent Space and Time](https://mlsanity.com/paper/2310.02207/) (2023)
- [Time-Aware Language Models as Temporal Knowledge Bases](https://mlsanity.com/paper/2106.15110/) (2021)
- [ST-LLM: Large Language Models Are Effective Temporal Learners](https://mlsanity.com/paper/2404.00308/) (2024)
- [A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal](https://mlsanity.com/paper/2212.05767/) (2022)
- [Time Masking for Temporal Language Models](https://mlsanity.com/paper/2110.06366/) (2021)
- [Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models](https://mlsanity.com/paper/2306.08952/) (2023)
- [How Can Large Language Models Understand Spatial-Temporal Data?](https://mlsanity.com/paper/2401.14192/) (2024)
- [Arrows of Time for Large Language Models](https://mlsanity.com/paper/2401.17505/) (2024)
- [History Matters: Temporal Knowledge Editing in Large Language Model](https://mlsanity.com/paper/2312.05497/) (2023)
- [Probing Language Models for Understanding of Temporal Expressions](https://mlsanity.com/paper/2110.01113/) (2021)
- [Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering](https://mlsanity.com/paper/2412.13782/) (2024)
- [hmBERT: Historical Multilingual Language Models for Named Entity Recognition](https://mlsanity.com/paper/2205.15575/) (2022)
- [A Comprehensive Evaluation of Large Language Models on Temporal Event Forecasting](https://mlsanity.com/paper/2407.11638/) (2024)
- [Mitigating Temporal-Drift: A Simple Approach to Keep NER Models Crisp](https://mlsanity.com/paper/2104.09742/) (2021)
- [Temporal Blind Spots in Large Language Models](https://mlsanity.com/paper/2401.12078/) (2024)
- [Understanding Why Large Language Models Can Be Ineffective in Time Series Analysis: The Impact of Modality Alignment](https://mlsanity.com/paper/2410.12326/) (2024)
- [Navigating Tomorrow: Reliably Assessing Large Language Models Performance on Future Event Prediction](https://mlsanity.com/paper/2501.05925/) (2025)
- [Remember This Event That Year? Assessing Temporal Information and Reasoning in Large Language Models](https://mlsanity.com/paper/2402.11997/) (2024)
- [Multilingual Knowledge Graph Completion from Pretrained Language Models with Knowledge Constraints](https://mlsanity.com/paper/2406.18085/) (2024)
- [NER4all or Context is All You Need: Using LLMs for low-effort, high-performance NER on historical texts. A humanities informed approach](https://mlsanity.com/paper/2502.04351/) (2025)
- [On the Temporal Question-Answering Capabilities of Large Language Models Over Anonymized Data](https://mlsanity.com/paper/2504.07646/) (2025)

## Abstract (arXiv)

Temporal variation poses a unique challenge for named entity recognition (NER) in historical texts, where entities drift in surface form and salience across time. While language models (LMs) have made progress in various NLP tasks, their ability to reason about temporality, especially in diachronic contexts, remains limited or at least, questionable. In this paper, we systematically study how temporal metadata can be structurally embedded into NER models using a range of lightweight fusion strategies. We experiment with both absolute and relative temporal representations, injected into Transformer-based architectures via early or late fusion mechanisms such as cross-attention, adapters, and concatenation. Our evaluations on French and German historical datasets reveal that late fusion strategies yield more robust and temporally generalisable performance, particularly in early and noisy periods.