most citedLearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models

1 citations · 1 across the 4 of their papers we have counts for

collaborators

9 papers

cs.AI2026

Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories

Tianlong Wang, Yuhang Wang, Weibin Liao +5

Current approaches to enhance Large Language Model (LLM) reasoning, such as Chain-of-Thought and "Wait" prompts, primarily encourage models to think more, yet often fail to guide t…

cs.CL20261 cited

LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models

Weibin Liao, Xin Gao, Tianyu Jia +6

Natural Language to SQL (NL2SQL) aims to translate natural language queries into executable SQL statements, offering non-expert users intuitive access to databases. While recent ap…

cs.DB2026

Database Context Compression for Text-to-SQL on Real-World Large Databases

Jingwen Liu, Weibin Liao, Xin Gao +2

Recent progress in Text-to-SQL has been driven by stronger language models and prompting strategies, yet performance on real enterprise benchmarks such as Spider 2.0 and BIRD remai…

cs.LG2026

EvoRubrics: Dynamic Rubrics as Rewards via Adversarial Co-Evolution for LLM Reinforcement Learning

Hongxin Ding, Baixiang Huang, Yue Fang +6

Rubric-based rewards offer interpretable and fine-grained optimization signals for reinforcement learning in open-ended tasks where verifiable answers are unavailable. However, pre…

cs.LG2026

GraphWalker: Patient Analogy Meets Information Gain for Clinical Reasoning with Large Language Models

Yue Fang, Weibin Liao, Yuxin Guo +8

Clinical reasoning over electronic health records (EHRs) is a fundamental yet challenging task in modern healthcare. While large language models (LLMs) offer a promising paradigm v…

cs.CL2026

The Tell-Tale Norm: Magnitude as a Signal for Reasoning Dynamics in Large Language Models

Jinyang Zhang, Hongxin Ding, Yue Fang +4

Recent work has sought to understand Large Language Models (LLMs) reasoning, yet a principled, model-intrinsic signal that captures its layer-wise reasoning dynamics remains undere…