This paper investigates whether a group of people highlighting the same document forms a single consensus or is internally structured into reader sub-groups.

The paper introduces Dr. DocBench, a difficulty-aware, comprehensive benchmark designed to rigorously test expert-level and challenging document parsing capabilities for VLMs, demonstrating that curre…

The paper introduces DocFormBench, a new benchmark for content-aware document formatting, and proposes DocFormFlow, a workflow that improves formatting accuracy and efficiency by decoupling target loc…

This paper predicts the aggregate crowd salience of a document from its text before its marks accumulate.

SkillPager is a novel two-stage framework that efficiently selects minimal, execution-sufficient context from large procedural skill documents by leveraging typed semantic nodes, significantly reducin…

The paper systematically compares multimodal transformer and LLM approaches for document type classification, finding that specialized multimodal Transformers outperform LLM-based models, especially w…

This paper introduces a new benchmark dataset and evaluation framework for 'data snapshot extraction,' focusing on identifying and localizing semantically meaningful analytical artifacts within operat…

The paper introduces Self-Conditioned Positional HNSW (SCP-HNSW), a method that modifies chunk embeddings and retrieval process to mitigate redundant evidence retrieval from overlapping document chunk…

The paper introduces a new benchmark for multi-target cross-lingual summarization (MTXLS) and proposes an activation steering method that significantly improves LLM performance by guiding the generati…

The paper introduces I-WebGenBench, a framework and benchmark that converts static scientific papers into executable, interactive web systems, allowing users to dynamically explore the paper's mechani…

The paper introduces TVIR, a new benchmark and multi-agent framework for deep research, to evaluate and improve the generation of factually reliable, text-visual interleaved reports.

This paper demonstrates a proof-of-concept method using top-view video to detect 'Pen-Up' states in handwriting, showing it can reliably complement traditional digitizing tablets for developmental dis…

The paper introduces a novel guardrail orchestration layer that improves the compliance and efficiency of high-stakes multimodal document generation by scoring multiple generated candidates against we…

The paper proposes a novel KAN-enhanced BiGRU architecture to improve legal document classification and summarization in a low-resource, multilingual setting using Bengali and English legal texts.

The paper introduces OpAI-Bench, a novel benchmark designed to study how AI authorship signals evolve and accumulate during the progressive co-editing process between humans and AI.

This paper empirically evaluates LLM-generated reviews for academic papers, finding that while LLM reviews show some alignment with human ones, authors can effectively 'game' the system using iterativ…

The paper introduces SPECTRA, a scalable framework for generating large, synthetic, and controllable information retrieval test collections, demonstrating its ability to expose system scaling and fail…

The paper proposes SteganoPrompt, an input-side watermark embedded in the assignment prompt that forces LLMs to generate a detectable signature in their output, thereby exposing verbatim copy-pasting.

This paper proposes CompRank, a token-efficient reranking framework for large language models that reduces redundant computation and achieves strong reranking performance.

The paper introduces FOSSIL, a new multilingual dataset and specialized workflow designed to significantly improve the extraction of citations embedded within complex footnotes common in law and human…