4 papers
Theory-Level Autoformalization: From Isolated Statements to Unified Formal Knowledge Bases
Marcus J. Min, Mike He, Zhaoyu Li +5
Autoformalization translates informal natural language into formal, machine-verifiable languages. While most work focuses on individual statements, real formalization efforts are i…
SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning
Yangruibo Ding, Jinjun Peng, Marcus J. Min +3
Code Large Language Models (Code LLMs) have excelled at tasks like code completion but often miss deeper semantics such as execution effects and dynamic states. This paper aims to…
CYCLE: Learning to Self-Refine the Code Generation
Yangruibo Ding, Marcus J. Min, Gail Kaiser +1
Pre-trained code language models have achieved promising performance in code generation and improved the programming efficiency of human developers. However, their self-refinement…
Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain
Marcus J. Min, Yangruibo Ding, Luca Buratti +4
Code Large Language Models (Code LLMs) are being increasingly employed in real-life applications, so evaluating them is critical. While the conventional accuracy evaluates the perf…