72 citations · 162 across the 19 of their papers we have counts for
9 papers · 1 filter
MIRA: Evidence-Verified Repair Memory for Text-to-SQL Correction
Yining Liu, Chenyu Yang, Boyan Li +2
Text-to-SQL agents still produce executable yet semantically incorrect SQL. A reliable SQL corrector must repair incorrect queries without corrupting correct ones. Confirmed correc…
SQLConductor: Search-to-Policy Learning for Step-wise Text-to-SQL Orchestration
Yizhang Zhu, Zhangyang Peng, Boyan Li +1
Text-to-SQL enables users to access relational databases via natural language, but real-world settings remain challenging due to coordinated reasoning over complex database environ…
DataMagic: Transforming Tabular Data into Data Insight Video
Yupeng Xie, Chen Ma, Zhenyang Wang +6
Data videos integrate dynamic charts, voice narration, and synchronized animations to communicate data insights as temporal narratives, making them an effective medium for improvin…
Adaptive Prompt Embedding Optimization for LLM Jailbreaking
Miles Q. Li, Benjamin C. M. Fung, Boyang Li +2
Existing white-box jailbreak attacks against aligned LLMs typically append discrete adversarial suffixes to the user prompt, which visibly alters the prompt and operates in a combi…
DPC: Training-Free Text-to-SQL Candidate Selection via Dual-Paradigm Consistency
Boyan Li, Ou Ocean Kun Hei, Yue Yu +1
While Large Language Models (LLMs) demonstrate impressive proficiency in generating SQL queries, they fundamentally lack the capability to self-evaluate correctness without an exec…
ROSE: An Intent-Centered Evaluation Metric for NL2SQL
Wenqi Pei, Shizheng Hou, Boyan Li +3
Execution Accuracy (EX), the widely used metric for evaluating the effectiveness of Natural Language to SQL (NL2SQL) solutions, is becoming increasingly unreliable. It is sensitive…
ToxiTrace: Gradient-Aligned Training for Explainable Chinese Toxicity Detection
Boyang Li, Hongzhe Shou, Yuanyuan Liang +2
Existing Chinese toxic content detection methods mainly target sentence-level classification but often fail to provide readable and contiguous toxic evidence spans. We propose \tex…
DeepEye: A Steerable Self-driving Data Agent System
Boyan Li, Yiran Peng, Yupeng Xie +5
Large Language Models (LLMs) have revolutionized natural language interaction with data. The "holy grail" of data analytics is to build autonomous Data Agents that can self-drive c…
FinMCP-Bench: Benchmarking LLM Agents for Real-World Financial Tool Use under the Model Context Protocol
Jie Zhu, Yimin Tian, Boyang Li +8
This paper introduces \textbf{FinMCP-Bench}, a novel benchmark for evaluating large language models (LLMs) in solving real-world financial problems through tool invocation of finan…