LLM-Based Data Science Agents: A Survey of Capabilities, Challenges, and Future Directions

Documenti analoghi

• Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?
  di: Laskar, Md Tahmid Rahman, et al.
  Pubblicazione: (2025)
• Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization
  di: Rahman, Mizanur, et al.
  Pubblicazione: (2026)
• From Charts to Fair Narratives: Uncovering and Mitigating Geo-Economic Biases in Chart-to-Text
  di: Mahbub, Ridwan, et al.
  Pubblicazione: (2025)
• Text2Vis: A Challenging and Diverse Benchmark for Generating Multimodal Visualizations from Text
  di: Rahman, Mizanur, et al.
  Pubblicazione: (2025)
• Deploying Tiny LVLM Judges for Real-World Evaluation of Chart Models: Lessons Learned and Best Practices
  di: Laskar, Md Tahmid Rahman, et al.
  Pubblicazione: (2025)