ChartCitor: Multi-Agent Framework for Fine-Grained Chart Visual Attribution
Large Language Models (LLMs) can perform chart question-answering tasks but often generate unverified hallucinated responses. Existing answer attribution methods struggle to ground responses in source charts due to limited visual-semantic context, complex visual-text alignment requirements, and difficulties in bounding box prediction across complex layouts. We present ChartCitor, a multi-agent framework that provides fine-grained bounding box citations by identifying supporting evidence within chart images. The system orchestrates LLM agents to perform chart-to-table extraction, answer reformulation, table augmentation, evidence retrieval through pre-filtering and re-ranking, and table-to-chart mapping. ChartCitor outperforms existing baselines across different chart types. Qualitative user studies show that ChartCitor helps increase user trust in Generative AI by providing enhanced explainability for LLM-assisted chart QA and enables professionals to be more productive.
Code (0)
등록된 구현이 없습니다.
Tasks
Chart Question AnsweringQuestion AnsweringRe-RankingRetrievalTable ExtractionSimilar Papers 제목 키워드 기반
Multi-Agent Amodal Completion: Direct Synthesis with Fine-Grained Semantic Guidance
Amodal completion, generating invisible parts of occluded objects, is vital for applications like image editing and AR. Prior methods face challenges with data needs, generalization, or error accumulation in progressive …
Image EditingToward Expert Investment Teams:A Multi-Agent LLM System with Fine-Grained Trading Tasks
The advancement of large language models (LLMs) has accelerated the development of autonomous financial trading systems. While mainstream approaches deploy multi-agent systems mimicking analyst and manager roles, they of…
Portfolio OptimizationExplainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection
Large language model (LLM)-based multi-agent systems (MAS) have shown strong capabilities in solving complex tasks. As MAS become increasingly autonomous in various safety-critical tasks, detecting malicious agents has b…
Graph Anomaly DetectionCAFEEN: A Cooperative Approach for Energy Efficient NoCs with Multi-Agent Reinforcement Learning
In emerging high-performance Network-on-Chip (NoC) architectures, efficient power management is crucial to minimize energy consumption. We propose a novel framework called CAFEEN that employs both heuristic-based fine-gr…
ManagementMulti-agent Reinforcement LearningSeeing as Experts Do: A Knowledge-Augmented Agent for Open-Set Fine-Grained Visual Understanding
Fine-grained visual understanding is shifting from static classification to knowledge-augmented reasoning, where models must justify as well as recognise. Existing approaches remain limited by closed-set taxonomies and s…