7 papers
COAL-SQL: Coverage-Guided Augmentation and Failure-Driven Learning for Text-to-SQL Post-Training
Qifeng Cai, Xuanguang Pan, Hao Liang +2
Text-to-SQL translates natural-language questions into executable SQL queries, but open-source large language models still require task-specific post-training for complex, real-wor…
Eliciting Chain-of-Thought in Base LLMs via Gradient-Based Representation Optimization
Zijian Wang, Yanxiang Ma, Chang Xu
Chain-of-Thought (CoT) reasoning is a critical capability for large language models (LLMs), enabling them to tackle com- plex multi-step tasks. While base LLMs, pre-trained on gene…
Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL
Qifeng Cai, Hao Liang, Chang Xu +3
The data-centric paradigm has emerged as a pivotal direction in artificial intelligence (AI), emphasizing the role of high-quality training data. This shift is especially critical…
ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representations
Zijian Wang, Chang Xu
This paper introduces ThoughtProbe, a novel inference time framework that leverages the hidden reasoning features of Large Language Models (LLMs) to improve their reasoning perform…
Functional Abstraction of Knowledge Recall in Large Language Models
Zijian Wang, Chang Xu
Pre-trained transformer large language models (LLMs) demonstrate strong knowledge recall capabilities. This paper investigates the knowledge recall mechanism in LLMs by abstracting…
ThoughtProbe: Classifier-Guided Thought Space Exploration Leveraging LLM Intrinsic Reasoning
Zijian Wang, Chang Xu
Pre-trained large language models (LLMs) have been demonstrated to possess intrinsic reasoning capabilities that can emerge naturally when expanding the response space. However, th…
Locating and Extracting Relational Concepts in Large Language Models
Zijian Wang, Britney White, Chang Xu
Relational concepts are indeed foundational to the structure of knowledge representation, as they facilitate the association between various entity concepts, allowing us to express…