| title | RICoT: Recurrent Interleaved Chain-of-Thought for Page Stream Segmentation |
|---|---|
| authors | Prashant Khatri, Bhavana Malagavalli, Saiful Haq, Niyati Chhaya |
| date | 2026-11-17 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2611.22382 |
| upvotes | 4 (Hugging Face Daily Papers, 2026-11-21) |
| links | abs pdf hf |
| cite | |
| abstract | Large language models (LLMs) have renewed interest in Page Stream Segmentation (PSS), splitting a multi-page file into its constituent documents. Yet published LLM methods still frame the task as boundary classification over one or a few neighboring pages, and commercial document-splitting APIs do not disclose their methods. We reimagine PSS for LLMs as a sequential process over the whole stream and propose RICoT (Recurrent Interleaved Chain-of-Thought), a prompting framework that works through the pages as a reader would: within a sliding window it reasons about each page and commits its boundary decision before moving on, and across windows it carries forward a compact record of what it has read, keeping per-call cost bounded. We also introduce FinancePSS-205, a benchmark of 205 real-world, de-identified financial page streams, to be released publicly. On FinancePSS-205, RICoT matches or outperforms pairwise and windowed prompting with the same backbone for each of three open-weight LLMs; on a TABME test subset, RICoT with GLM-5 reaches document F1 0.847 and boundary F1 0.915, above published zero-shot results. A 2B-parameter student, trained on a larger teacher's decisions with and without the page-level reasoning, performs comparably in both modes and comes within 0.05 document F1 of the strongest prompted model on FinancePSS-205. |
bibtex
@misc{khatri2026ricot,
title={RICoT: Recurrent Interleaved Chain-of-Thought for Page Stream Segmentation},
author={Prashant Khatri and Bhavana Malagavalli and Saiful Haq and Niyati Chhaya},
year={2026},
eprint={2611.22382},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2611.22382}
}