{"slug": "continuity-and-ordinality-matter-constraining-time-series-tokens-for-effective", "title": "Continuity and Ordinality Matter: Constraining Time Series Tokens for Effective Time Series Analysis with Large Language Models", "summary": "Researchers have introduced COM, a strategy that enforces geometric constraints on time series token embeddings to preserve their inherent continuity and ordinality in large language models. The approach, detailed in a new paper, consistently improves performance across multiple time series analysis benchmarks by addressing a key limitation in prior token-based TS-LLMs. The work demonstrates that maintaining these temporal properties is crucial for effective time series analysis and reasoning.", "body_md": "arXiv:2605.28866v1 Announce Type: new\nAbstract: Token-based time series large language models (TS-LLMs) have emerged as a promising direction for time series analysis and reasoning. However, prior studies largely overlook the inherent continuity and ordinality of time series tokens, which substantially limits model performance. In this paper, we argue that preserving these properties in time series token embeddings is crucial for the effectiveness of token-based TS-LLMs. To this end, we propose COM (Continuity and Ordinality Matter), a continuity- and ordinality-aware strategy that integrates geometric constraints into both the initialization and training stages. Empirical results on multiple time series analysis benchmarks demonstrate that COM consistently improves the performance of token-based TS-LLMs, achieving competitive results and strong generalizability. Code is available at https://anonymous.4open.science/r/COM .", "url": "https://wpnews.pro/news/continuity-and-ordinality-matter-constraining-time-series-tokens-for-effective", "canonical_source": "https://arxiv.org/abs/2605.28866", "published_at": "2026-05-29 04:00:00+00:00", "updated_at": "2026-05-29 04:17:43.226757+00:00", "lang": "en", "topics": ["large-language-models", "machine-learning", "artificial-intelligence"], "entities": ["COM"], "alternates": {"html": "https://wpnews.pro/news/continuity-and-ordinality-matter-constraining-time-series-tokens-for-effective", "markdown": "https://wpnews.pro/news/continuity-and-ordinality-matter-constraining-time-series-tokens-for-effective.md", "text": "https://wpnews.pro/news/continuity-and-ordinality-matter-constraining-time-series-tokens-for-effective.txt", "jsonld": "https://wpnews.pro/news/continuity-and-ordinality-matter-constraining-time-series-tokens-for-effective.jsonld"}}