8 papers
Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework
Yuchen He, Peizhi Ying, Liqi Cheng +4
Chart data extraction, which reverse-engineers data tables from chart images, is essential for reproducibility, analysis, retrieval, and redesign. Existing interactive tools are re…
PV-SQL: Synergizing Database Probing and Rule-based Verification for Text-to-SQL Agents
Yuan Tian, Tianyi Zhang
Text-to-SQL systems often struggle with deep contextual understanding, particularly for complex queries with subtle requirements. We present PV-SQL, an agentic framework that addre…
FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models
Zixuan Weng, Jinghuai Zhang, Kunlin Cai +3
Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offers a cost-effective way to adju…
How Developers Adopt, Use, and Evolve CI/CD Caching: An Empirical Study on GitHub Actions
Kazi Amit Hasan, Yuan Tian, Safwat Hassan +1
Continuous Integration/Continuous Delivery (CI/CD) caching is widely used to reduce repeated computation and improve CI/CD efficiency, yet maintaining effective caching requires on…
When LLMs Lag Behind: Knowledge Conflicts from Evolving APIs in Code Generation
Ahmed Nusayer Ashik, Shaowei Wang, Tse-Hsun Chen +2
The rapid evolution of software libraries creates a significant challenge for Large Language Models (LLMs), whose static parametric knowledge often becomes stale post-training. Whi…
From Docs to Descriptions: Smell-Aware Evaluation of MCP Server Descriptions
Peiran Wang, Ying Li, Yuqiang Sun +3
The Model Context Protocol (MCP) has rapidly become a de facto standard for connecting LLM-based agents with external tools via reusable MCP servers. In practice, however, server s…