paper-with-me

홈 › Papers

DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding

2026-05-09 · Xiang Feng, Jiawei Zhou, Zhangfeng Huang, Kewei Wang, Shanshan Ye, Jinxin Hu, Zulong Chen, Yong Luo, Jing Zhang arxiv

Evaluating whether Multimodal Large Language Models can produce trustworthy, verifiable reasoning over long, visually rich documents requires evaluation beyond end-to-end answer accuracy. We introduce DocScope, a benchmark that formulates long-document QA as a structured reasoning trajectory prediction problem: given a complete PDF document and a question, the model outputs evidence pages, supporting evidence regions, relevant factual statements, and a final answer. We design a four-stage evaluation protocol -- Page Localization, Region Grounding, Fact Extraction, and Answer Verification -- that audits each level of the trajectory independently through inter-stage decoupling, with all judges selected and calibrated via human alignment studies. DocScope comprises 1,124 questions derived from 273 documents, with all hierarchical evidence annotations completed by human annotators. We benchmark 6 proprietary models, 12 open-weight models, and several domain-specific systems. Our experiments reveal that answer accuracy cannot substitute for trajectory-level evaluation: even among correct answers, the highest observed rate of complete evidence chains is only 29\%. Across all models, region grounding remains the weakest trajectory stage. Furthermore, the primary difficulty stems from aggregating evidence dispersed across long distances and multiple document clusters, while an oracle study identifies faithful perception and fact extraction as the dominant capability bottleneck. Cross-architecture comparisons further suggest that activated parameter count matters more than total scale. The benchmark and code will be publicly released at https://github.com/MiliLab/DocScope.

📄 PDF Abstract BibTeX arXiv:2605.08888

Code (0)

등록된 구현이 없습니다.

Tasks

Trajectory Prediction

Similar Papers 제목 키워드 기반

LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning

2026-04-15 · Sumeet Ramesh Motwani, Daniel Nichols, Charles London, Peggy Li 외 arxiv

As language models are increasingly deployed for complex autonomous tasks, their ability to reason accurately over longer horizons becomes critical. An essential component of this ability is planning and managing a long,…

BioDSA-1K: Benchmarking Data Science Agents for Biomedical Research

2025-05-22 · Zifeng Wang, Benjamin Danek, Jimeng Sun

Validating scientific hypotheses is a central challenge in biomedical research, and remains difficult for artificial intelligence (AI) agents due to the complexity of real-world data analysis and evidence interpretation.…

Benchmarking

Inverse Knowledge Search over Verifiable Reasoning: Synthesizing a Scientific Encyclopedia from a Long Chains-of-Thought Knowledge Base

2025-10-30 · Yu Li, Yuan Huang, Tao Wang, Caiyu Fan 외 arxiv

Most scientific materials compress reasoning, presenting conclusions while omitting the derivational chains that justify them. This compression hinders verification by lacking explicit, step-wise justifications and inhib…

Towards Trustworthy Multi-Turn LLM Agents via Behavioral Guidance

2025-12-12 · Gonca Gürsun arxiv

Large Language Models demonstrate strong reasoning and generation abilities, yet their behavior in multi-turn tasks often lacks reliability and verifiability. We present a task completion framework that enables LLM-based…

Reinforcement Learning

Multimodal Fact-Level Attribution for Verifiable Reasoning

2026-02-12 · David Wan, Han Wang, Ziyang Wang, Elias Stengel-Eskin 외 arxiv

Multimodal large language models (MLLMs) are increasingly used for real-world tasks involving multi-step reasoning and long-form generation, where reliability requires grounding model outputs in heterogeneous input sourc…

Multimodal Reasoning