Publications (11)
The Counterfeit Conundrum: Can Code Language Models Grasp the Nuances of Their Incorrect Generations?
Alex Gu, Wen-Ding Li, Naman Jain +4
While language models are increasingly more proficient at code generation, they still frequently generate incorrect programs. Many of these programs are obviously wrong, but others…
Refactoring Codebases through Library Design
Ziga Kovacic, Justin T. Chiu, Celine Lee +2
Maintainable and general software allows developers to build robust applications efficiently, yet achieving these qualities often requires refactoring specialized solutions into re…
Guess & Sketch: Language Model Guided Transpilation
Celine Lee, Abdulrahman Mahmoud, Michal Kurek +5
Maintaining legacy software requires many software and systems engineering hours. Assembly code programs, which demand low-level control over the computer machine state and have no…
Critical Thinking: Which Kinds of Complexity Govern Optimal Reasoning Length?
Celine Lee, Alexander M. Rush, Keyon Vafa
Large language models (LLMs) often benefit from verbalized reasoning at inference time, but it remains unclear which aspects of task difficulty these extra reasoning tokens address…
MP-CodeCheck: Evolving Logical Expression Code Anomaly Learning with Iterative Self-Supervision
Urs C. Muff, Celine Lee, Paul Gottschlich +1
Machine programming (MP) is concerned with automating software development. According to studies, software engineers spend upwards of 50% of their development time debugging softwa…
Toward Code Generation: A Survey and Lessons from Semantic Parsing
Celine Lee, Justin Gottschlich, Dan Roth
With the growth of natural language processing techniques and demand for improved software engineering efficiency, there is an emerging interest in translating intention from human…
Commit0: Library Generation from Scratch
Wenting Zhao, Nan Jiang, Celine Lee +4
With the goal of benchmarking generative systems beyond expert software development ability, we introduce Commit0, a benchmark that challenges AI agents to write libraries from scr…
Guaranteed Guess: A Language Modeling Approach for CISC-to-RISC Transpilation with Testing Guarantees
Ahmed Heakl, Sarim Hashmi, Chaimaa Abi +2
The hardware ecosystem is rapidly evolving, with increasing interest in translating low-level programs across different instruction set architectures (ISAs) in a quick, flexible, a…
Mixture of Soft Prompts for Controllable Data Generation
Derek Chen, Celine Lee, Yunan Lu +2
Large language models (LLMs) effectively generate fluent text when the target output follows natural language patterns. However, structured prediction tasks confine the output form…
The Efficiency Gap in Byte Modeling
Celine Lee, Jing Nathan Yan, Chen Liang +9
Modern language models have historically relied on two dominant design choices: subword tokenization and autoregressive (AR) ordering. These design decisions bake in priors that di…
On second order linear sequences of composite numbers
Dan Ismailescu, Adrienne Ko, Celine Lee +1
In this paper we present a new proof of the following 2010 result of Dubickas, Novikas, and Siurys: Let and let be the sequence defined by…