11 papers
MineTRACE: An Evidence-Grounded Interactive Reasoning System for Mineral Prospectivity
Yiran Zhang, Jinwen Liu, Daniel Su +7
Mineral exploration requires integrating heterogeneous geochemical, geophysical, and geological evidence, yet existing prospectivity systems often provide only opaque scores or hea…
Locating Failure in Multi-Page Visually Rich Document Understanding Systems: An Empirical Attribution
Lewei Xu, Yihao Ding, Zihan Xu +5
Multi-page visually rich document understanding (MP-VRDU) systems can fail when evidence is not faithfully represented, not selected, or not used correctly, yet final accuracy alon…
Disentangling Structure and Semantics: How Schema Representation Affects LLM-Based SQL Generation
Daniel Yitian Su, Sophie Yiran Su, Qiang Sun +2
LLM-based text-to-SQL pipelines read the database schema as text, which carries both structural cues (tables, keys, relationships) and semantic cues (table and column names); prior…
MonteRET: AI Agent Enhancing Multimodal LLMs with Multi-granularity Knowledge Retrieval for Chest CT Report Generation
Yi Lin, Yihao Ding, Elana Benishay +8
Automated chest CT report generation remains challenging because clinically faithful reporting requires both whole-volume understanding and accurate description of localized anatom…
DocOCR-Eval: A Correction-Based Framework for OCR Tool Selection Without Ground Truth
Zihan Xu, Puzhen Wu, Lawrence Chun Man Lau +4
Document parsing is a foundational step for document understanding tasks such as visual question answering and key information extraction, as it transforms unstructured scanned ima…
MARCH: Multi-Agent Radiology Clinical Hierarchy for CT Report Generation
Yi Lin, Yihao Ding, Yonghui Wu +1
Automated 3D radiology report generation often suffers from clinical hallucinations and a lack of the iterative verification found in human practice. While recent Vision-Language M…
STIndex: A Context-Aware Multi-Dimensional Spatiotemporal Information Extraction System
Wenxiao Zhang, Yu Liu, Qiang sun +5
Extracting structured knowledge from unstructured data still faces practical limitations: entity and event extraction pipelines remain brittle, knowledge graph construction require…
BRIDGE: Benchmark for multi-hop Reasoning In long multimodal Documents with Grounded Evidence
Biao Xiang, Soyeon Caren Han, Yihao Ding
Multi-hop question answering (QA) is widely used to evaluate the reasoning capabilities of large language models, yet most benchmarks focus on final answer correctness and overlook…
Diagnosing Causal Reasoning in Vision-Language Models via Structured Relevance Graphs
Dhita Putri Pratama, Soyeon Caren Han, Yihao Ding
Large Vision-Language Models (LVLMs) achieve strong performance on visual question answering benchmarks, yet often rely on spurious correlations rather than genuine causal reasonin…
Docs2Synth: A Synthetic Data Trained Retriever Framework for Scanned Visually Rich Documents Understanding
Yihao Ding, Qiang Sun, Puzhen Wu +3
Document understanding (VRDU) in regulated domains is particularly challenging, since scanned documents often contain sensitive, evolving, and domain specific knowledge. This leads…
A Disease-Aware Dual-Stage Framework for Chest X-ray Report Generation
Puzhen Wu, Hexin Dong, Yi Lin +2
Radiology report generation from chest X-rays is an important task in artificial intelligence with the potential to greatly reduce radiologists' workload and shorten patient wait t…