SAGE: From Direct Answering to Evidence-Grounded Inference for Chinese Ancient Document Understanding

arXiv:2608.24011 · cs.CL, cs.AI · Submitted 2026-08-25 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-08-25

Updated: 2026-08-25

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Verification — 60× in this paper · explained in 2 episodes
• Verifier — 38× in this paper · explained in 2 episodes
• Trace — 30× in this paper · explained in 2 episodes
• Benchmark — 18× in this paper · explained in 2 episodes
• Abstention — 14× in this paper · explained in 1 episode
• Grounding — 12× in this paper · explained in 3 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Multi-Agent Framework — 5× in this paper · explained in 3 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Ablation study — 2× in this paper · explained in 1 episode
• Action Space — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Core — 2× in this paper · explained in 2 episodes
• State Management — 2× in this paper · explained in 3 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Multimodal Inputs — 1× in this paper · explained in 2 episodes
• Ontology — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Task Decomposition — 1× in this paper · explained in 2 episodes

Sources

• GPT-4o System Card
• LLaVA-OneVision: Easy Visual Task Transfer
• Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
• DocVQA: A Dataset for VQA on Document Images
• Towards VQA Models That Can Read
• C$^{3}$Bench: A Comprehensive Classical Chinese Understanding Benchmark for Large Language Models
• Seed1.5-VL Technical Report
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• AnchiBERT: A Pre-Trained Model for Ancient ChineseLanguage Understanding and Generation
• OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning
• DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
• WenyanGPT: A Large Language Model for Classical Chinese Tasks
• Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning
• F\`ux\`i: A Benchmark for Evaluating Language Models on Ancient Chinese Text Understanding and Generation
• InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering