17 citations · 37 across the 16 of their papers we have counts for
20 papers
Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses
Huachi Zhou, Yujing Zhang, Jiahe Du +7
Large language model agents are increasingly deployed for data-intensive work, yet reliable data analysis requires more than general-purpose reasoning and ad hoc tool augmentation.…
Org-Agent: Beyond Personal Assistants Towards Organizational Agents
Luyao Zhuang, Yujing Zhang, Zijin Hong +2
Language model agents serving organizations must coordinate requests from multiple users while using knowledge distributed across their interactions. We identify two complementary…
CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented Generation
Jiacheng Cai, Zijin Hong, Zheng Yuan +3
Despite the strong capabilities of multimodal large language models (MLLMs), their parametric knowledge remains incomplete and difficult to update, motivating multimodal retrieval-…
Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift
Yujia Liu, Jiayan Lin, Zijin Hong +6
Recent advances in large language models (LLMs) have established conversational text-to-SQL as a practical interface between users and databases, often involving multiple turns of…
Are These Modules Worth Their Cost? A Paradigm-Level Accuracy-Cost Analysis of In-context Learning Text-to-SQL
Jiayan Lin, Yujia Liu, Zijin Hong +6
Recent advances in in-context learning (ICL) text-to-SQL have substantially improved execution accuracy on public benchmarks by assembling increasingly elaborate pipelines around t…
Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence
Yuyuan Feng, Zhishang Xiang, Chaobin Yang +32
LLMs have evolved from language generators to autonomous agents capable of complex, long-horizon tasks. This evolution has produced paradigms including Prompt Engineering to elicit…
Zero-Mem: Zero-Token Memory Operations for LLM Agents
Yilin Xiao, Zhehan Zhu, Yujing Zhang +8
LLM agents need memory to act consistently over long interactions, yet many systems use additional LLM calls to operate that memory. Generating intermediate records and mediating t…
ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement
Zijin Hong, Hao Chen, Zheng Yuan +6
Despite the remarkable performance of large language models (LLMs) in text-to-SQL (SQL generation), correctly producing SQL queries remains challenging during initial generation. T…
Graph-based Agent Memory: Taxonomy, Techniques, and Applications
Chang Yang, Chuang Zhou, Yilin Xiao +15
Memory emerges as the core module in the Large Language Model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), whe…
Macro Graph of Experts for Billion-Scale Multi-Task Recommendation
Hongyu Yao, Zijin Hong, Hao Chen +6
Graph-based multi-task learning at billion-scale presents a significant challenge, as different tasks correspond to distinct billion-scale graphs. Traditional multi-task learning m…
When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation
Zhishang Xiang, Chuanjie Wu, Qinggang Zhang +4
Graph retrieval-augmented generation (GraphRAG) has emerged as a powerful paradigm for enhancing large language models (LLMs) with external knowledge. It leverages graphs to model…
Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation
Zheng Yuan, Hao Chen, Zijin Hong +4
Generating SQLs from user queries is a long-standing challenge, where the accuracy of initial schema linking significantly impacts subsequent SQL generation performance. However, c…
A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models
Qinggang Zhang, Shengyuan Chen, Yuanchen Bei +9
Large language models (LLMs) have demonstrated remarkable capabilities in a wide range of tasks, yet their application to specialized domains remains challenging due to the need fo…
Benchmarking LLMs' Mathematical Reasoning with Unseen Random Variables Questions
Zijin Hong, Hao Wu, Su Dong +8
Recent studies have raised significant concerns regarding the reliability of current mathematics benchmarks, highlighting issues such as simplistic design and potential data contam…
HNCSE: Advancing Sentence Embeddings via Hybrid Contrastive Learning with Hard Negatives
Wenxiao Liu, Zihong Yang, Chaozhuo Li +5
Unsupervised sentence representation learning remains a critical challenge in modern natural language processing (NLP) research. Recently, contrastive learning techniques have achi…
CLR-Bench: Evaluating Large Language Models in College-level Reasoning
Junnan Dong, Zijin Hong, Yuanchen Bei +3
Large language models (LLMs) have demonstrated their remarkable performance across various language understanding tasks. While emerging benchmarks have been proposed to evaluate LL…
Unconstrained Model Merging for Enhanced LLM Reasoning
Yiming Zhang, Baoyi He, Shengyu Zhang +12
Recent advancements in building domain-specific large language models (LLMs) have shown remarkable success, especially in tasks requiring reasoning abilities like logical inference…
Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL
Zijin Hong, Zheng Yuan, Qinggang Zhang +4
Generating accurate SQL from users' natural language questions (text-to-SQL) remains a long-standing challenge due to the complexities involved in user question understanding, data…
Towards Better Question Generation in QA-based Event Extraction
Zijin Hong, Jian Liu
Event Extraction (EE) is an essential information extraction task that aims to extract event-related information from unstructured texts. The paradigm of this task has shifted from…
Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM
Zijin Hong, Zheng Yuan, Hao Chen +3
Generating accurate SQL queries for user questions (text-to-SQL) has been a long-standing challenge since it requires a deep understanding of both the user's question and the corre…