Vu Le

Vu Le

Auto-generated profile, based on publicly available information

Vu Le

Microsoft, Redmond, WA, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
29 April 2024 in Proceedings of the ACM on Programming Languages
Verified
Journal Article
Open access
JZJialu Zhang
Jialu Zhang
JCJosé Pablo Cambronero
José Pablo Cambronero
SGSumit Gulwani
Sumit Gulwani
VLVu Le
Vu Le
RPRuzica Piskac
Ruzica Piskac
GVGust Verbruggen
Gust Verbruggen
Students often make mistakes in their introductory programming assignments as part of their learning process. Unfortunately, providing custom repairs for these mistakes can require a substantial amount of time and effort from class instructors. Automated program repair (APR) techniques can be used to synthesize such fixes. Prior work has explored the use of symbolic and neural techniques for APR in the education domain. Both types of approaches require either substantial engineering efforts or large amounts of data and training. We propose to use a large language model trained on code, such as Codex (a version of GPT), to build an APR system -- PyDex -- for introductory Python programming assignments. Our system can fix both syntactic and semantic mistakes by combining multi-modal prompts, iterative querying, test-case-based selection of few-shots, and program chunking. We evaluate PyDex on 286 real student programs and compare to three baselines, including one that combines a state-of-the-art Python syntax repair engine, BIFI, and a state-of-the-art Python semantic repair engine for student assignments, Refactory. We find that PyDex can fix more programs and produce smaller patches on average.

9 January 2023 in Proceedings of the ACM on Programming Languages
Verified
Journal Article
Open access
JCJosé Cambronero
José Cambronero
SGSumit Gulwani
Sumit Gulwani
VLVu Le
Vu Le
DPDaniel Perelman
Daniel Perelman
ARArjun Radhakrishna
Arjun Radhakrishna
ATAshish Tiwari
Ashish Tiwari
Programming-by-Examples (PBE) involves synthesizing an "intended program" from a small set of user-provided input-output examples. A key PBE strategy has been to restrict the search to a carefully designed small domain-specific language (DSL) with "effectively-invertible" (EI) operators at the top and "effectively-enumerable" (EE) operators at the bottom. This facilitates an effective combination of top-down synthesis strategy (which backpropagates outputs over various paths in the DSL using inverse functions) with a bottom-up synthesis strategy (which propagates inputs over various paths in the DSL). We address the problem of scaling synthesis to large DSLs with several non-EI/EE operators. This is motivated by the need to support a richer class of transformations and the need for readable code generation. We propose a novel solution strategy that relies on propagating fewer values and over fewer paths. Our first key idea is that of "cut functions" that prune the set of values being propagated by using knowledge of the sub-DSL on the other side. Cuts can be designed to preserve completeness of synthesis; however, DSL designers may use incomplete cuts to have finer control over the kind of programs synthesized. In either case, cuts make search feasible for non-EI/EE operators and efficient for deep DSLs. Our second key idea is that of "guarded DSLs" that allow a precedence on DSL operators, which dynamically controls exploration of various paths in the DSL. This makes search efficient over grammars with large fanouts without losing recall. It also makes ranking simpler yet more effective in learning an intended program from very few examples. Both cuts and precedence provide a mechanism to the DSL designer to restrict search to a reasonable, and possibly incomplete, space of programs. Using cuts and gDSLs, we have built FlashFill++, an industrial-strength PBE engine for performing rich string transformations, including datetime and number manipulations. The FlashFill++ gDSL is designed to enable readable code generation in different target languages including Excel's formula language, PowerFx, and Python. We show FlashFill++ is more expressive, more performant, and generates better quality code than comparable existing PBE systems. FlashFill++ is being deployed in several mass-market products ranging from spreadsheet software to notebooks and business intelligence applications, each with millions of users.

31 October 2022 in Proceedings of the ACM on Programming Languages
Verified
Journal Article
Open access
RBRohan Bavishi
Rohan Bavishi
HJHarshit Joshi
Harshit Joshi
JCJosé Cambronero
José Cambronero
AFAnna Fariha
Anna Fariha
SGSumit Gulwani
Sumit Gulwani
ATAshish Tiwari
Ashish Tiwari
Most users of low-code platforms, such as Excel and PowerApps, write programs in domain-specific formula languages to carry out nontrivial tasks. Often users can write most of the program they want, but introduce small mistakes that yield broken formulas. These mistakes, which can be both syntactic and semantic, are hard for low-code users to identify and fix, even though they can be resolved with just a few edits. We formalize the problem of producing such edits as the last-mile repair problem. To address this problem, we developed LaMirage, a LAst-MIle RepAir-engine GEnerator that combines symbolic and neural techniques to perform last-mile repair in low-code formula languages. LaMirage takes a grammar and a set of domain-specific constraints/rules, which jointly approximate the target language, and uses these to generate a repair engine that can fix formulas in that language. To tackle the challenges of localizing errors and ranking candidate repairs, LaMirage leverages neural techniques, whereas it relies on symbolic methods to generate candidate edits. This combination allows LaMirage to find repairs that satisfy the provided grammar and constraints, and then pick the most natural repair. We compare LaMirage to state-of-the-art neural and symbolic approaches on 400 real Excel and Power Fx formulas, where LaMirage outperforms all baselines. We release these benchmarks to encourage subsequent work in low-code domains.

9 December 2025 in ACM Transactions on Computer-Human Interaction
Verified
Journal Article
Open access
JLJenny T. Liang
Jenny T. Liang
AKAayush Kumar
Aayush Kumar
YBYasharth Bajpai
Yasharth Bajpai
SGSumit Gulwani
Sumit Gulwani
VLVu Le
Vu Le
GSGustavo Soares
Gustavo Soares
Spreadsheet programming is challenging. Programmers use spreadsheet programming knowledge (e.g., formulas) and problem-solving skills to combine actions into complex tasks. Advancements in large language models have introduced language agents that observe, plan, and perform tasks, showing promise for spreadsheet creation. We present TableTalk, a spreadsheet programming agent embodying three design principles—scaffolding, flexibility, and incrementality—derived from studies with seven spreadsheet programmers and 85 Excel templates. TableTalk guides programmers through structured plans based on professional workflows, generating three potential next steps to adapt plans to programmer needs. It uses pre-defined tools to generate spreadsheet components and incrementally build spreadsheets. In a study with 20 programmers, TableTalk produced higher-quality spreadsheets 2.3 times more likely to be preferred than the baseline. It reduced cognitive load and thinking time by 12.6%. From this, we derive design guidelines for agentic spreadsheet programming tools and discuss implications on spreadsheet programming, end-user programming, AI-assisted programming, and human-agent collaboration.

20 April 2024
Verified
Conference Paper
Open access
ASAnanya Singha
Ananya Singha
BCBhavya Chopra
Bhavya Chopra
AKAnirudh Khatry
Anirudh Khatry
SGSumit Gulwani
Sumit Gulwani
AHAustin Henley
Austin Henley
GVGust Verbruggen
Gust Verbruggen
Automated insight generation is a common tactic for helping knowledge workers, such as data scientists, to quickly understand the potential value of new and unfamiliar data. Unfortunately, automated insights produced by large-language models can generate code that does not correctly correspond (or align) to the insight. In this paper, we leverage the semantic knowledge of large language models to generate targeted and insightful questions about data and the corresponding code to answer those questions. Then through an empirical study on data from Open-WikiTable, we show that embeddings can be effectively used for filtering out semantically unaligned pairs of question and code. Additionally, we found that generating questions and code together yields more diverse questions.

10 February 2025 in Proceedings of the ACM on Management of Data
Verified
Journal Article
Open access
MSMukul Singh
Mukul Singh
JCJosé Cambronero
José Cambronero
SGSumit Gulwani
Sumit Gulwani
VLVu Le
Vu Le
CNCarina Negreanu
Carina Negreanu
GVGust Verbruggen
Gust Verbruggen
String data is common in real-world datasets: 67.6% of values in a sample of 1.8 million real Excel spreadsheets from the web were represented as text. Automatically cleaning such string data can have a significant impact on users. Previous approaches are limited to error detection, require that the user provides annotations, examples, or constraints to fix the errors, and focus independently on syntactic errors or semantic errors in strings, but ignore that strings often contain both syntactic and semantic substrings. We introduce DataVinci, a fully unsupervised string data error detection and repair system. DataVinci learns regular-expression-based patterns that cover a majority of values in a column and reports values that do not satisfy such majority patterns as data errors. DataVinci can automatically derive edits to the data error based on the majority patterns and using row tuples associated with majority values as examples. To handle strings with both syntactic and semantic substrings, DataVinci uses an LLM to abstract (and re-concretize) portions of strings that are semantic. Because not all data columns can result in majority patterns, when available, DataVinci can leverage execution information from an existing data program (which uses the target data as input) to identify and correct data repairs that would not otherwise be identified. DataVinci outperforms eleven baseline systems on both data error detection and repair as demonstrated on four existing and new benchmarks.