arXiv cs.AI· Prashant Khatri, Bhavana Malagavalli, Saiful Haq, Niyati Chhaya·· 4 小时前AI 评分20
RICoT:面向页面流分割的循环交错思维链提示框架
RICoT: Recurrent Interleaved Chain-of-Thought for Page Stream Segmentation
AI 导读
RICoT 是一种将页面流分割(PSS)重构为整段顺序处理过程的提示框架,在滑动窗口内逐页推理并即时给出边界判断,跨窗口携带已读内容的紧凑记录以控制单次调用成本。
正文 · 原文
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.
| Comments: | 18 pages, 3 figures, 19 tables. Dataset and code to be released |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR) |
| ACM classes: | I.2.7; I.7.5 |
| Cite as: | arXiv:2611.22382 [cs.CL] |
| (or arXiv:2611.22382v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22382 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Prashant Khatri [view email]
[v1]
Tue, 17 Nov 2026 08:33:25 UTC (736 KB)
来源:arXiv cs.AI · arxiv.org