arXiv AI September 18, 2026 By Yichao Jin, Yushuo Wang, Yuxuan Han, Kwan Ching Yee Sonia, Weiyang Song, Chiu Jin-Chun Kent, Wong Chong Hwee, Wong Tiong Kiat, Kenneth Zhu Ke, Jingyuan Zhao

Perception, Layout, and Validation: Calibrated Confidence for Reliable Straight-Through Processing of Financial Documents

Read the original on arXiv AI →

The paper presents a new calibrated confidence framework for straight‑through processing (STP) of financial documents, decomposing confidence into perception, layout, and validation channels and applying conformal risk control. Using Vision‑Language Models (Qwen3.6‑27B and Gemini‑3.1‑Flash‑Lite) on three public datasets, the method raises AUROC from 0.54‑0.74 to 0.90‑0.99 and increases auto‑approval rates to 49‑72% while keeping empirical error below the target. This approach enables reliable, large‑scale STP without human review.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 2

Compliance-Scored Best-of-N Guardrail Orchestration for Multimodal Document Generation in Payments Dispute Defense

arXiv:2606. 01513v1 Announce Type: cross Abstract: High-stakes enterprise document generation, including financial dispute narratives, compliance notices, and audit summaries, demands schema correctness, policy compliance, and low-latency operation at scale.

By Nataraj Agaram Sundar, Tejas Morabia

agents computer-vision multimodal safety

arXiv AI

Aug 17

A Four-Axis Trustworthiness Benchmark for LLM-as-Judge in Principle-Based Regulation

arXiv:2608. 14329v1 Announce Type: cross Abstract: Principle-based regulation, with evaluative standards such as "fair, clear, and not misleading" or "deliver good outcomes", cannot be reduced to binary predicates, and LLM-as-judge is increasingly used as the substitute.

By Dipankar Sarkar

llms benchmarks safety

arXiv AI

Jun 19

AgentFinVQA: A Deployable Multi-Agent Pipeline for Auditable Financial Chart QA

arXiv:2606. 19782v1 Announce Type: new Abstract: Financial chart question answering in regulated settings demands more than accuracy: practitioners must know which answers to trust before acting on them, and many institutions cannot send client data to external model providers.

By Aravind Narayanan, Shaina Raza

llms agents computer-vision nlp

arXiv Machine Learning

Jul 27

Small Vision-Language Models Know When They Are Wrong But Cannot Say So: A Two-Model Study of Stated versus Internal Confidence Under Realistic Image Degradation

arXiv:2607. 22034v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly deployed on consumer hardware where input images are degraded by compression, camera shake, and poor lighting.

By M M Asif Ferdous

llms multimodal

arXiv AI

Aug 25

FinixDoc: Rethinking Financial Document Parsing Beyond Saturated Benchmarks

arXiv:2608.22842v1 Announce Type: new Abstract: Financial document parsing requires accuracy, structural consistency, and verifiability that current benchmarks often fail to reflect. We present Finix...

By Hang Wang, Jin Zhang, Guoliang Xu, Pengyue Lu, Yao Li, Zijiao Zhang, Tianyu Huang, Weiqi Xiong, Yulong Wang, Chuqiao Lu, Wenkang Huang, Kai Yang, Yadong Li, Hui Li, Xingzhong Xu, Xiao Xu

llms agents reinforcement-learning multimodal benchmarks

arXiv AI

Sep 15

Beyond Accuracy: Robustness, Cost, and Governance Trade-offs for Vision-Language Models in Templated Document Extraction

The paper evaluates eleven vision‑language models (VLMs) for extracting structured fields from business documents, focusing on robustness, cost, and governance rather than just accuracy. Using a held‑out set of 750 synthetic checks, the study finds that fine‑tuning open‑source VLMs on 3,000 samples yields an F1 score above 0.98, surpassing all zero‑shot commercial systems, while GPT‑5 tops the commercial group and Claude Sonnet 4.5 fails on date extraction. The authors also present a practitioner‑oriented selection framework that maps task profiles—such as quality, latency, governance, and volume—to recommended approaches via filtering and total‑cost minimization, demonstrated on a mid‑volume document‑extraction scenario.

By Kushal Patel, Pushkal Shrivastava, Mackenzie Lees, Qirui Lu, Bhargobjyoti Saikia, Liying Li, Junlin Jiang

llms computer-vision fine-tuning multimodal benchmarks

One email a morning, machine-written

Related stories

Compliance-Scored Best-of-N Guardrail Orchestration for Multimodal Document Generation in Payments Dispute Defense

A Four-Axis Trustworthiness Benchmark for LLM-as-Judge in Principle-Based Regulation

AgentFinVQA: A Deployable Multi-Agent Pipeline for Auditable Financial Chart QA

Small Vision-Language Models Know When They Are Wrong But Cannot Say So: A Two-Model Study of Stated versus Internal Confidence Under Realistic Image Degradation

FinixDoc: Rethinking Financial Document Parsing Beyond Saturated Benchmarks

Beyond Accuracy: Robustness, Cost, and Governance Trade-offs for Vision-Language Models in Templated Document Extraction