mlsanityData to 14 Oct 2026

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

arXiv 2606.27881 ↗First posted 26 Jun 2026cs.CL cs.AIcited by 0

Not on the map. Why?

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.

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

22 of 38 references.

References · 22

  1. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  2. 2023Language Models Represent Space and Timecited by 316
  3. 2021Time-Aware Language Models as Temporal Knowledge Basescited by 296
  4. 2024ST-LLM: Large Language Models Are Effective Temporal Learnerscited by 126
  5. 2022A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodalcited by 106
  6. 2021Time Masking for Temporal Language Modelscited by 46
  7. 2023Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Modelscited by 37
  8. 2024How Can Large Language Models Understand Spatial-Temporal Data?cited by 33
  9. 2024Arrows of Time for Large Language Modelscited by 20
  10. 2023History Matters: Temporal Knowledge Editing in Large Language Modelcited by 17
  11. 2021Probing Language Models for Understanding of Temporal Expressionscited by 16
  12. 2024Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answeringcited by 10
10 more
  1. 2022hmBERT: Historical Multilingual Language Models for Named Entity Recognitioncited by 8
  2. 2024A Comprehensive Evaluation of Large Language Models on Temporal Event Forecastingcited by 8
  3. 2021Mitigating Temporal-Drift: A Simple Approach to Keep NER Models Crispcited by 7
  4. 2024Temporal Blind Spots in Large Language Modelscited by 7
  5. 2024Understanding Why Large Language Models Can Be Ineffective in Time Series Analysis: The Impact of Modality Alignmentcited by 7
  6. 2025Navigating Tomorrow: Reliably Assessing Large Language Models Performance on Future Event Predictioncited by 5
  7. 2024Remember This Event That Year? Assessing Temporal Information and Reasoning in Large Language Modelscited by 4
  8. 2024Multilingual Knowledge Graph Completion from Pretrained Language Models with Knowledge Constraintscited by 4
  9. 2025NER4all or Context is All You Need: Using LLMs for low-effort, high-performance NER on historical texts. A humanities informed approachcited by 4
  10. 2025On the Temporal Question-Answering Capabilities of Large Language Models Over Anonymized Datacited by 2

Built on by

Not cited yet.