跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 5 天前AI 評分38

RICoT:用於頁面串流分段的循環交錯鏈式推理

RICoT: Recurrent Interleaved Chain-of-Thought for Page Stream Segmentation

AI 導讀

研究提出 RICoT,將頁面串流分段視為整段串流上的序列處理,並在滑動視窗間保留已讀內容摘要。在 FinancePSS-205 上,RICoT 對三款開放權重大語言模型的效果媲美或優於配對式及視窗提示;在 TABME 測試子集上,搭配 GLM-5 達到 document F1 0.847、boundary F1 0.915。

正文

Published on Nov 17

Authors:

,

,

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.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2611.22382

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.22382 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.22382 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.22382 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co