# ChronoLens: Measuring Language Change Across Time, Languages, and Linguistic Levels

arXiv: https://arxiv.org/abs/2608.03507 · HTML: https://mlsanity.com/paper/2608.03507/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 70 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Builds on (most cited first, 30 of 31)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection](https://mlsanity.com/paper/2004.10643/) (2020)
- [Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change](https://mlsanity.com/paper/1605.09096/) (2016)
- [Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet](https://mlsanity.com/paper/2605.29358/) (2026)
- [SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability](https://mlsanity.com/paper/2503.09532/) (2025)
- [Are Sparse Autoencoders Useful? A Case Study in Sparse Probing](https://mlsanity.com/paper/2502.16681/) (2025)
- [EuroLLM: Multilingual Language Models for Europe](https://mlsanity.com/paper/2409.16235/) (2024)
- [Analysing Lexical Semantic Change with Contextualised Word Representations](https://mlsanity.com/paper/2004.14118/) (2020)
- [Sparse Autoencoders Do Not Find Canonical Units of Analysis](https://mlsanity.com/paper/2502.04878/) (2025)
- [Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing](https://mlsanity.com/paper/1902.09492/) (2019)
- [Cultural Shift or Linguistic Drift? Comparing Two Computational Measures of Semantic Change](https://mlsanity.com/paper/1606.02821/) (2016)
- [Why do language models perform worse for morphologically complex languages?](https://mlsanity.com/paper/2411.14198/) (2024)
- [A Systematic Comparison of Contextualized Word Embeddings for Lexical Semantic Change](https://mlsanity.com/paper/2402.12011/) (2024)
- [Diachronic Analysis of German Parliamentary Proceedings: Ideological Shifts through the Lens of Political Biases](https://mlsanity.com/paper/2108.06295/) (2021)
- [Cross-Architecture Model Diffing with Crosscoders: Unsupervised Discovery of Differences Between LLMs](https://mlsanity.com/paper/2602.11729/) (2026)
- [On the Linearity of Semantic Change: Investigating Meaning Variation via Dynamic Graph Models](https://mlsanity.com/paper/1704.02497/) (2017)
- [Crosslinguistic word order variation reflects evolutionary pressures of dependency and information locality](https://mlsanity.com/paper/2206.04239/) (2022)
- [Joint Semantic Synthesis and Morphological Analysis of the Derived Word](https://mlsanity.com/paper/1701.00946/) (2017)
- [Fine-Grained Detection of Solidarity for Women and Migrants in 155 Years of German Parliamentary Debates](https://mlsanity.com/paper/2210.04359/) (2022)
- [Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining](https://mlsanity.com/paper/2509.05291/) (2025)
- [Narrative Media Framing in Political Discourse](https://mlsanity.com/paper/2506.00737/) (2025)
- [Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy](https://mlsanity.com/paper/2505.24473/) (2025)
- [Sparse Autoencoders Can Capture Language-Specific Concepts Across Diverse Languages](https://mlsanity.com/paper/2507.11230/) (2025)
- [Target Based Speech Act Classification in Political Campaign Text](https://mlsanity.com/paper/1905.07856/) (2019)
- [Quantifying Lexical Semantic Shift via Unbalanced Optimal Transport](https://mlsanity.com/paper/2412.12569/) (2024)
- [Framing Migration: A Computational Analysis of UK Parliamentary Discourse](https://mlsanity.com/paper/2509.14197/) (2025)
- [DHPLT: large-scale multilingual diachronic corpora and word representations for semantic change modelling](https://mlsanity.com/paper/2602.11968/) (2026)

## Abstract (arXiv)

Historical language change affects morphology, syntax, semantics, and pragmatics, yet computational studies typically examine these levels with incompatible representations and therefore cannot determine whether they evolve together across languages. We address this problem by asking how the magnitude and direction of change vary across linguistic levels, languages, and historical periods within a single analytical space. We introduce ChronoLens, a framework that combines frozen multilingual language models, feature-aligned crosscoders, and post-hoc linguistic interventions, and apply it to 44.98 million documents and approximately 17.2 billion tokens from five parliamentary traditions spanning 1803--2026. The resulting sparse representations agree substantially more strongly with linguistic statistics than dense embeddings or a pooled sparse autoencoder (ρ=0.72 versus 0.29 and 0.28), and reveal that morphology, syntax, semantics, and pragmatics generally change by comparable amounts within a language, while languages differ markedly in when, how far, and in which direction they change. These findings show that historical language change is a structured, multidimensional process: similar magnitudes can conceal different trajectories, and meaningful cross-linguistic comparison requires measuring both distance and direction.