Nan Tang

Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs

TuneAhead: Predicting Fine-tuning Performance Before Training Begins

From Ambiguous Feedback to Verifiable Repair via Formal Synthesis in Text-to-SQL

CycleIE: Robust Document Information Extraction through Iterative Verification and Refinement

InteractComp: Evaluating Search Agents With Ambiguous Queries

Structured Retrieval-Augmented Generation for Multi-Doc Multi-Entity Question Answering

EllieSQL: Cost-Efficient Text-to-SQL with Complexity-Aware Routing

AskChart: Universal Chart Understanding through Textual Enhancement

Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search

Detecting Out-of-Context Misinformation via Multi-Agent and Multi-Grained Retrieval

Retrieval Augmented Imputation using Data Lake Tables

Visual Question Answering with Fine-grained Knowledge Unit RAG and Multimodal LLMs

Harnessing the Wikipedia Graph for Effective Multi-Entity Question Answering

SketchFill: Sketch-Guided Code Generation for Imputing Derived Missing Values