Chronoberg: EMNLP oral paper releases 250-year English corpus with temporal emotion lexicons to test LLMs
mundt_martin · x · 2026-10-23
The Chronoberg paper (Hegde et al.), an oral at EMNLP 2026, introduces a temporally structured corpus of English books spanning 250 years (1750–2000), curated from Project Gutenberg: 2.7B tokens across 25k books, enriched with era-specific Valence-Arousal-Dominance lexicons, sentence sentiment, and hate-speech annotations.
Experiments show modern LLM-based tools struggle with diachronic shifts in meaning — sentiment contextualization and discriminatory-language detection degrade across time periods — arguing for temporally aware training and evaluation pipelines. The authors also position it as a testbed for continual/lifelong learning. Data and code are publicly available.
Related event: Chronoberg: 250 Years of English Books Corpus Hits EMNLP Oral(3 posts)→
More from Research
- Researcher uses Grok to hunt LLM-driven UAE bot network on X with self-written prompts — FlorianGallwitz · 2026-10-23
- Dev converts Qwen3-0.6B into a MoE model: quality drops and no speed gain at this scale — Bayliner1980 · 2026-10-23
- Tencent's WeChat Vision releases WeVisOne-VL, unifying object- and pixel-level perception — jacek2023 · 2026-10-23
- Batching benchmark: 50x throughput for ~24% latency cost on PyTorch — cneuralnetwork · 2026-10-23
- De novo designed ligases validate in lab: 27 of 30 computer-designed enzymes work — AllThingsApx · 2026-10-23
- Commenters dissect a "best decision model" leaderboard: same AUC, swing driven by calibration priors — antoine_chaffin · 2026-10-23