Showing cs.AIShow all
3 papers · 1 filter
cs.AI2026
AgentFinVQA: A Deployable Multi-Agent Pipeline for Auditable Financial Chart QA
Aravind Narayanan, Shaina Raza
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 can…
cs.AI2026
CaVe-VLM-CoT: An Interpretable Vision-Language Model Framework
Sneha Rao, Shaina Raza, Dhanesh Ramachandram
Vision-Language Models (VLMs) remain prone to hallucinations, producing fluent but visually unfaithful outputs. Existing chain-of-thought and retrieval-augmented methods only parti…
cs.AI2026
DiagFlowBench: Evaluating How Language Models Handle Off-Procedure Inputs in Grounded Diagnostic Dialogue
Guillermo Gil de Avalle, Laura Maruster, Shaina Raza +1
Language models increasingly serve as advisory systems in maintenance operations. To prevent hallucination, recent systems ground these models in procedural documentation to constr…