60 citations · 63 across the 10 of their papers we have counts for
10 papers
SkillMentor: LLM Agent Self-Evolution via Learning Blind-Spot Diagnosis
Xiaoyi Bao, Yuanzhen Xie, Yunzhi Tan +5
Agent self-evolution has primarily focused on learning how to act, while overlooking an equally important capability: learning to discover what an agent does not know. Existing app…
DCMM-SQL: Automated Data-Centric Pipeline and Multi-Model Collaboration Training for Text-to-SQL Model
Yuanzhen Xie, Liu Ye, Jiqun Chu +5
Text-to-SQL tasks have gained attractive improvements since the release of ChatGPT. Among them, agent-based frameworks have been widely used in this field. However, the impact of d…
Toward Structured Knowledge Reasoning: Contrastive Retrieval-Augmented Generation on Experience
Jiawei Gu, Ziting Xian, Yuanzhen Xie +7
Large language models (LLMs) achieve strong performance on plain text tasks but underperform on structured data like tables and databases. Potential challenges arise from their und…
PSM-SQL: Progressive Schema Learning with Multi-granularity Semantics for Text-to-SQL
Zhuopan Yang, Yuanzhen Xie, Ruichao Zhong +6
It is challenging to convert natural language (NL) questions into executable structured query language (SQL) queries for text-to-SQL tasks due to the vast number of database schema…
Solid-SQL: Enhanced Schema-linking based In-context Learning for Robust Text-to-SQL
Geling Liu, Yunzhi Tan, Ruichao Zhong +5
Recently, large language models (LLMs) have significantly improved the performance of text-to-SQL systems. Nevertheless, many state-of-the-art (SOTA) approaches have overlooked the…
L^2CL: Embarrassingly Simple Layer-to-Layer Contrastive Learning for Graph Collaborative Filtering
Xinzhou Jin, Jintang Li, Liang Chen +6
Graph neural networks (GNNs) have recently emerged as an effective approach to model neighborhood signals in collaborative filtering. Towards this research line, graph contrastive…
CTRL: Continuous-Time Representation Learning on Temporal Heterogeneous Information Network
Chenglin Li, Yuanzhen Xie, Chenyun Yu +4
Inductive representation learning on temporal heterogeneous graphs is crucial for scalable deep learning on heterogeneous information networks (HINs) which are time-varying, such a…
Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm
Yuanzhen Xie, Xinzhou Jin, Tao Xie +7
In-context learning of large-language models (LLMs) has achieved remarkable success in the field of natural language processing, while extensive case studies reveal that the single…
OlaGPT: Empowering LLMs With Human-like Problem-Solving Abilities
Yuanzhen Xie, Tao Xie, Mingxiong Lin +7
In most current research, large language models (LLMs) are able to perform reasoning tasks by generating chains of thought through the guidance of specific prompts. However, there…
One for All, All for One: Learning and Transferring User Embeddings for Cross-Domain Recommendation
Chenglin Li, Yuanzhen Xie, Chenyun Yu +5
Cross-domain recommendation is an important method to improve recommender system performance, especially when observations in target domains are sparse. However, most existing tech…