Claire Schlesinger

Claire Schlesinger

Auto-generated profile, based on publicly available information

Claire Schlesinger

Khoury College of Computer Sciences Northeastern University Boston Massachusetts USA

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 October 2024 in Proceedings of the ACM on Programming Languages
Verified
Journal Article
Open access
FCFederico Cassano
Federico Cassano
JGJohn Gouwar
John Gouwar
FLFrancesca Lucchetti
Francesca Lucchetti
CSClaire Schlesinger
Claire Schlesinger
AFAnders Freeman
Anders Freeman
AGArjun Guha
Arjun Guha
Over the past few years, Large Language Models of Code (Code LLMs) have started to have a significant impact on programming practice. Code LLMs are also emerging as building blocks for research in programming languages and software engineering. However, the quality of code produced by a Code LLM varies significantly by programming language. Code LLMs produce impressive results on high-resource programming languages that are well represented in their training data (e.g., Java, Python, or JavaScript), but struggle with low-resource languages that have limited training data available (e.g., OCaml, Racket, and several others). This paper presents an effective approach for boosting the performance of Code LLMs on low-resource languages using semi-synthetic data. Our approach, called M ulti PL-T, generates high-quality datasets for low-resource languages, which can then be used to fine-tune any pretrained Code LLM. M ulti PL-T translates training data from high-resource languages into training data for low-resource languages in the following way. 1) We use a Code LLM to synthesize unit tests for commented code from a high-resource source language, filtering out faulty tests and code with low test coverage. 2) We use a Code LLM to translate the code from the high-resource source language to a target low-resource language. This gives us a corpus of candidate training data in the target language, but many of these translations are wrong. 3) We use a lightweight compiler to compile the test cases generated in (1) from the source language to the target language, which allows us to filter our obviously wrong translations. The result is a training corpus in the target low-resource language where all items have been validated with test cases. We apply this approach to generate tens of thousands of new, validated training items for five low-resource languages: Julia, Lua, OCaml, R, and Racket, using Python as the source high-resource language. Furthermore, we use an open Code LLM (StarCoderBase) with open training data (The Stack), which allows us to decontaminate benchmarks, train models without violating licenses, and run experiments that could not otherwise be done. Using datasets generated with M ulti PL-T, we present fine-tuned versions of StarCoderBase and Code Llama for Julia, Lua, OCaml, R, and Racket that outperform other fine-tunes of these base models on the natural language to code task. We also present Racket fine-tunes for two very recent models, DeepSeek Coder and StarCoder2, to show that M ulti PL-T continues to outperform other fine-tuning approaches for low-resource languages. The M ulti PL-T approach is easy to apply to new languages, and is significantly more efficient and effective than alternatives such as training longer.

30 January 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
ZHZichao Hu
Zichao Hu
FLFrancesca Lucchetti
Francesca Lucchetti
CSClaire Schlesinger
Claire Schlesinger
YSYash Saxena
Yash Saxena
AFAnders Freeman
Anders Freeman
JBJoydeep Biswas
Joydeep Biswas
Recent advancements in large language models (LLMs) have spurred interest in using them for generating robot programs from natural language, with promising initial results. We investigate the use of LLMs to generate programs for service mobile robots leveraging mobility, perception, and human interaction skills, and where accurate sequencing and ordering of actions is crucial for success. We contribute CodeBotler , an open-source robot-agnostic tool to program service mobile robots from natural language, and RoboEval , a benchmark for evaluating LLMs' capabilities of generating programs to complete service robot tasks. CodeBotler performs program generation via few-shot prompting of LLMs with an embedded domain-specific language (eDSL) in Python, and leverages skill abstractions to deploy generated programs on any general-purpose mobile robot. RoboEval evaluates the correctness of generated programs by checking execution traces starting with multiple initial states, and checking whether the traces satisfy temporal logic properties that encode correctness for each task. RoboEval also includes multiple prompts per task to test for the robustness of program generation. We evaluate several popular state-of-the-art LLMs with the RoboEval benchmark, and perform a thorough analysis of the modes of failures, resulting in a taxonomy that highlights common pitfalls of LLMs at generating robot programs. We release our code and benchmark at https://amrl.cs.utexas.edu/codebotler/

31 December 2025 in Advanced Intelligent Discovery
Verified
Journal Article
Open access
CHCirce Hsu
Circe Hsu
CSClaire Schlesinger
Claire Schlesinger
KMKaran Mudaliar
Karan Mudaliar
JLJordan Leung
Jordan Leung
RWRobin Walters
Robin Walters
PSPeter Schindler
Peter Schindler
The work function and cleavage energy of a surface are critical properties that determine the viability of materials in electronic emission applications, semiconductor devices, and heterogeneous catalysis. While first‐principles calculations are accurate in predicting these properties, their computational expense, combined with the vast search space of surfaces, makes a comprehensive screening approach with density functional theory (DFT) infeasible. Here, we introduce FIRE‐GNN (Force‐Informed, Relaxed Equivariance Graph Neural Network), which integrates surface‐normal symmetry breaking and machine learning interatomic potential (MLIP)‐derived force information, achieving a twofold reduction in mean absolute error (down to 0.065 eV) over the previous state‐of‐the‐art for work function prediction. We additionally benchmark recent invariant and equivariant architectures, analyze the impact of symmetry breaking, and evaluate out‐of‐distribution generalization, demonstrating that FIRE‐GNN consistently outperforms competing models for work function predictions. This model enables accurate and rapid predictions of the work function and cleavage energy across a vast chemical space and facilitates the discovery of materials with tuned surface properties.