ChronoLens: Measuring Language Change Across Time, Languages, and Linguistic Levels
Gagan Bhatia, Julian Schlenker, Simone Paolo Ponzetto, Steffen Eger
cs.CL, cs.AI
Submitted: 2026-08-04
License: http://creativecommons.org/licenses/by-sa/4.0/
The gist: Historical language change affects morphology, syntax, semantics, and pragmatics, yet computational studies typically examine these levels with incompatible representations and therefore cannot
Terminology
Abstract
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 (rho=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.
Sources
- Sparse Autoencoders Can Capture Language-Specific Concepts Across Diverse Languages
- Framing Migration: A Computational Analysis of UK Parliamentary Discourse
- Mistral 7B
- Cross-Architecture Model Diffing with Crosscoders: Unsupervised Discovery of Differences Between LLMs
- SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
- EuroLLM: Multilingual Language Models for Europe
- Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning
- Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
- The Llama 3 Herd of Models
- Qwen3 Technical Report
- Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing
- Diachronic Analysis of German Parliamentary Proceedings: Ideological Shifts through the Lens of Political Biases
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering