4 papers
PAR-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering
Xingyu Li, Rongguang Wang, Yuying Wang +5
Large language models (LLMs) remain brittle on multi-hop question answering (MHQA), where answering requires combining evidence across documents through retrieval and reasoning. It…
LLM NL2SQL Robustness: Surface Noise vs. Linguistic Variation in Traditional and Agentic Settings
Lifu Tu, Rongguang Wang, Tao Sheng +2
Robustness evaluation for Natural Language to SQL (NL2SQL) systems is essential because real-world database environments are dynamic, noisy, and continuously evolving, whereas conv…
Deep Learning Framework Testing via Model Mutation: How Far Are We?
Yanzhou Mu, Rong Wang, Juan Zhai +7
Deep Learning (DL) frameworks are a fundamental component of DL development. Therefore, the detection of DL framework defects is important and challenging. As one of the most widel…
Understanding LLM-Centric Challenges for Deep Learning Frameworks: An Empirical Analysis
Yanzhou Mu, Rong Wang, Juan Zhai +7
Large language models (LLMs) have driven significant progress across a wide range of real-world applications. Realizing such models requires substantial system-level support. Deep…