Large Language Model

NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering

Reducing Tool Hallucination via Reliability Alignment

Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows

Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?

CoE-SQL: In-Context Learning for Multi-Turn Text-to-SQL with Chain-of-Editions

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought

Mobile-Env: Building Qualified Evaluation Benchmarks for LLM-GUI Interaction