arXiv subjects

Vu Le

Publications and source records attributed to Vu Le.

At least 19 recordsLinked to original sources

arXiv2026

Back to the Future: A workbook time machine for spread sheet creation benchmarks

We introduce the workbook time machine, a pipeline that automatically creates benchmarks evaluating the ability of language models to create derived objects in spreadsheets (formulas, charts, pivot tables, and conditional formatting). Applied to public workbook corpora, it produces wtmcorpus--a collection of (input workbook, output workbook, query) triples spanning four artifact types and varying complexity. From this corpus we curate wtmbench, a 150-task evaluation benchmark with queries at three levels of specificity. We evaluate existing spreadsheet manipulation agents and baselines on wtmbench across artifact types, step complexity, and instruction granularity. Our evaluations show that query specificity, agent orchestration, and interface API used to control spreadsheets play a big role in LLM performance on Excel tasks.

cs.AI↗

arXiv2026

A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets

Predictive code completion greatly accelerates how quickly developers work. In spreadsheets, despite being much more common, such auto-completion features are virtually non-existent. To address this gap, we introduce a benchmark for systems that observe a sequence of user actions in a spreadsheet and predict future actions. Two challenges are (1) the absence of edit histories in public spreadsheet corpora and (2) the complex space of spreadsheet actions (spatial, temporal, composite). To address (1), we manually curate 52 sequences of 12K actions that recreate spreadsheets from public corpora, seeded by parametrized heuristics and LLM refinement. To address (2), we propose an online evaluation that expects a prediction after each user action, accepts or rejects that prediction, updates the future actions upon acceptance, and repeats this until the target spreadsheet is obtained. We use multiple baseline predictors (including zero-shot LLMs, fine-tuned SLMs, and classical models) and analyze different properties that our benchmark teaches us, including but not limited to: properties of saved actions and false positives, efficiency, effect of user profiles, effect of triggers, and effect of context.

cs.SE↗

arXiv2026

Applying Formal Methods Tools to an Electronic Warfare Codebase (Experience report)

While using formal methods offers advantages over unit testing, their steep learning curve can be daunting to developers and can be a major impediment to widespread adoption. To support integration into an industrial software engineering workflow, a tool must provide useful information and must be usable with relatively minimal user effort. In this paper, we discuss our experiences associated with identifying and applying formal methods tools on an electronic warfare (EW) system with stringent safety requirements and present perspectives on formal methods tools from EW software engineers who are proficient in development yet lack formal methods training. In addition to a difference in mindset between formal methods and unit testing approaches, some formal methods tools use terminology or annotations that differ from their target programming language, creating another barrier to adoption. Input/output contracts, objects in memory affected by a function, and loop invariants can be difficult to grasp and use. In addition to usability, our findings include a comparison of vulnerabilities detected by different tools. Finally, we present suggestions for improving formal methods usability including better documentation of capabilities, decreased manual effort, and improved handling of library code.

cs.LO↗

arXiv2025

Supporting Patients in Managing Electronic Health Records and Biospecimens Consent for Research: Insights from a Mixed-Methods Usability Evaluation of the iAGREE Portal

De-identified health data are frequently used in research. As AI advances heighten the risk of re-identification, it is important to respond to concerns about transparency, data privacy, and patient preferences. However, few practical and user-friendly solutions exist. We developed iAGREE, a patient-centered electronic consent management portal that allows patients to set granular preferences for sharing electronic health records and biospecimens with researchers. To refine the iAGREE portal, we conducted a mixed-methods usability evaluation with 40 participants from three U.S. health systems. Our results show that the portal received highly positive usability feedback. Moreover, participants identified areas for improvement, suggested actionable enhancements, and proposed additional features to better support informed granular consent while reducing patient burden. Insights from this study may inform further improvements to iAGREE and provide practical guidance for designing patient-centered consent management tools.

cs.HC↗

arXiv2025

The Invisible Mentor: Inferring User Actions from Screen Recordings to Recommend Better Workflows

Many users struggle to notice when a more efficient workflow exists in feature-rich tools like Excel. Existing AI assistants offer help only after users describe their goals or problems, which can be effortful and imprecise. We present InvisibleMentor, a system that turns screen recordings of task completion into vision-grounded reflections on tasks. It detects issues such as repetitive edits and recommends more efficient alternatives based on observed behavior. Unlike prior systems that rely on logs, APIs, or user prompts, InvisibleMentor operates directly on screen recordings. It uses a two-stage pipeline: a vision-language model reconstructs actions and context, and a language model generates structured, high-fidelity suggestions. In evaluation, InvisibleMentor accurately identified inefficient workflows, and participants found its suggestions more actionable, tailored, and more helpful for learning and improvement compared to a prompt-based spreadsheet assistant.

cs.HC↗

arXiv2025

Diffusion is a code repair operator and generator

Code diffusion models generate code by iteratively removing noise from the latent representation of a code snippet. During later steps of the diffusion process, when the code snippet has almost converged, differences between discrete representations of these snippets look like last-mile repairs applied to broken or incomplete code. We evaluate the extent to which this resemblance can be exploited to leverage pre-trained code diffusion models for the problem of last-mile repair by considering two applications with significant potential. First, we can leverage the diffusion model for last-mile repair by adding noise to a broken code snippet and resuming the diffusion process. Second, we can leverage the diffusion model to generate arbitrary amount of training data for last-mile repair tasks (that are computationally more efficient) by sampling an intermediate program (input) and the final program (output) from the diffusion process. We perform experiments on 3 domains (Python, Excel and PowerShell) to evaluate applications, as well as analyze properties.

cs.SE↗

arXiv2025

Tabularis Formatus: Predictive Formatting for Tables

Spreadsheet manipulation software are widely used for data management and analysis of tabular data, yet the creation of conditional formatting (CF) rules remains a complex task requiring technical knowledge and experience with specific platforms. In this paper we present TaFo, a neuro-symbolic approach to generating CF suggestions for tables, addressing common challenges such as user unawareness, difficulty in rule creation, and inadequate user interfaces. TaFo takes inspiration from component based synthesis systems and extends them with semantic knowledge of language models and a diversity preserving rule ranking.Unlike previous methods focused on structural formatting, TaFo uniquely incorporates value-based formatting, automatically learning both the rule trigger and the associated visual formatting properties for CF rules. By removing the dependency on user specification used by existing techniques in the form of formatted examples or natural language instruction, TaFo makes formatting completely predictive and automated for the user. To evaluate TaFo, we use a corpus of 1.8 Million public workbooks with CF and manual formatting. We compare TaFo against a diverse set of symbolic and neural systems designed for or adapted for the task of table formatting. Our results show that TaFo generates more accurate, diverse and complete formatting suggestions than current systems and outperforms these by 15.6\%--26.5\% on matching user added ground truth rules in tables.

cs.DB↗

arXiv2025

Benchmark Dataset Generation and Evaluation for Excel Formula Repair with LLMs

Excel is a pervasive yet often complex tool, particularly for novice users, where runtime errors arising from logical mistakes or misinterpretations of functions pose a significant challenge. While large language models (LLMs) offer promising assistance by explaining formula errors, the automated correction of these semantic runtime errors remains an open problem. A primary challenge to advancing models for such scenarios is the severe lack of high-quality, comprehensive datasets for training and rigorous evaluation. This paper addresses this gap by introducing a novel approach for constructing a benchmark dataset specifically designed for Excel formula repair. We propose a data generation pipeline, which leverages a small set of curated seed samples from online forums to synthetically expand the dataset. Our pipeline integrates few-shot prompting with LLMs and employs a robust \textit{LLM-as-a-Judge} validation framework, combined with execution-based checks to ensure the correctness and semantic fidelity of the generated data. This process produced a benchmark dataset of 618 high-quality samples, covering common runtime errors. Furthermore, we propose a context-aware baseline technique for Excel formula repair that utilizes LLMs to leverage both the faulty formula, and relevant spreadsheet context. We evaluate the performance of various LLMs (GPT-4o, GPT-4.1, Phi-3, Mistral) on our newly generated benchmark using execution-based metrics. Our analysis demonstrates the dataset's quality through manual annotation and provides insights into error and function distributions. The proposed generation methodology is highly scalable and can be readily adapted to create evaluation benchmarks for similar code repair tasks in other low-resource programming languages.

cs.SE↗

arXiv2025

LLM-Guided Compositional Program Synthesis

Program synthesis from input-output examples, also called programming by example (PBE), has had tremendous impact on automating end-user tasks. Large language models (LLMs) have the ability to solve PBE tasks by generating code in different target languages, but they can fail unpredictably. To recover for failure, most approaches, such as self-reflection, use the LLM to solve the same task, but with a richer context. We introduce a novel technique that recovers from failure by constructing simpler subtasks for the LLM to solve. Our approach performs compositional program synthesis using LLMs, where LLM not only guides the decomposition of the PBE task into subtasks, but also solves the subtasks. We present different strategies for decomposing the original task. We experimentally show that our approach can solve challenging task instances that are not solved by self-reflection alone.

cs.PL↗

arXiv2025

TableTalk: Scaffolding Spreadsheet Development with a Language Agent

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.

cs.SE↗

arXiv2024

Evaluating the Evaluator: Measuring LLMs' Adherence to Task Evaluation Instructions

LLMs-as-a-judge is a recently popularized method which replaces human judgements in task evaluation (Zheng et al. 2024) with automatic evaluation using LLMs. Due to widespread use of RLHF (Reinforcement Learning from Human Feedback), state-of-the-art LLMs like GPT4 and Llama3 are expected to have strong alignment with human preferences when prompted for a quality judgement, such as the coherence of a text. While this seems beneficial, it is not clear whether the assessments by an LLM-as-a-judge constitute only an evaluation based on the instructions in the prompts, or reflect its preference for high-quality data similar to its fine-tune data. To investigate how much influence prompting the LLMs-as-a-judge has on the alignment of AI judgements to human judgements, we analyze prompts with increasing levels of instructions about the target quality of an evaluation, for several LLMs-as-a-judge. Further, we compare to a prompt-free method using model perplexity as a quality measure instead. We aggregate a taxonomy of quality criteria commonly used across state-of-the-art evaluations with LLMs and provide this as a rigorous benchmark of models as judges. Overall, we show that the LLMs-as-a-judge benefit only little from highly detailed instructions in prompts and that perplexity can sometimes align better with human judgements than prompting, especially on textual quality.

cs.AI↗

arXiv2024

An Empirical Study of Validating Synthetic Data for Formula Generation

Large language models (LLMs) can be leveraged to help with writing formulas in spreadsheets, but resources on these formulas are scarce, impacting both the base performance of pre-trained models and limiting the ability to fine-tune them. Given a corpus of formulas, we can use a(nother) model to generate synthetic natural language utterances for fine-tuning. However, it is important to validate whether the NL generated by the LLM is indeed accurate to be beneficial for fine-tuning. In this paper, we provide empirical results on the impact of validating these synthetic training examples with surrogate objectives that evaluate the accuracy of the synthetic annotations. We demonstrate that validation improves performance over raw data across four models (2 open and 2 closed weight). Interestingly, we show that although validation tends to prune more challenging examples, it increases the complexity of problems that models can solve after being fine-tuned on validated data.

cs.CL↗

arXiv2024

Semantically Aligned Question and Code Generation for Automated Insight Generation

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.

cs.SE↗

arXiv2024

Solving Data-centric Tasks using Large Language Models

Large language models (LLMs) are rapidly replacing help forums like StackOverflow, and are especially helpful for non-professional programmers and end users. These users are often interested in data-centric tasks, such as spreadsheet manipulation and data wrangling, which are hard to solve if the intent is only communicated using a natural-language description, without including the data. But how do we decide how much data and which data to include in the prompt? This paper makes two contributions towards answering this question. First, we create a dataset of real-world NL-to-code tasks manipulating tabular data, mined from StackOverflow posts. Second, we introduce a cluster-then-select prompting technique, which adds the most representative rows from the input data to the LLM prompt. Our experiments show that LLM performance is indeed sensitive to the amount of data passed in the prompt, and that for tasks with a lot of syntactic variation in the input table, our cluster-then-select technique outperforms a random selection baseline.

cs.PL↗

arXiv2023

Assessing GPT4-V on Structured Reasoning Tasks

Multi-modality promises to unlock further uses for large language models. Recently, the state-of-the-art language model GPT-4 was enhanced with vision capabilities. We carry out a prompting evaluation of GPT-4V and five other baselines on structured reasoning tasks, such as mathematical reasoning, visual data analysis, and code generation. We show that visual Chain-of-Thought, an extension of Chain-of-Thought to multi-modal LLMs, yields significant improvements over the vanilla model. We also present a categorized analysis of scenarios where these models perform well and where they struggle, highlighting challenges associated with coherent multimodal reasoning.

cs.CL↗

arXiv2023

Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformers

Most face identification approaches employ a Siamese neural network to compare two images at the image embedding level. Yet, this technique can be subject to occlusion (e.g. faces with masks or sunglasses) and out-of-distribution data. DeepFace-EMD (Phan et al. 2022) reaches state-of-the-art accuracy on out-of-distribution data by first comparing two images at the image level, and then at the patch level. Yet, its later patch-wise re-ranking stage admits a large $O(n^3 \log n)$ time complexity (for $n$ patches in an image) due to the optimal transport optimization. In this paper, we propose a novel, 2-image Vision Transformers (ViTs) that compares two images at the patch level using cross-attention. After training on 2M pairs of images on CASIA Webface (Yi et al. 2014), our model performs at a comparable accuracy as DeepFace-EMD on out-of-distribution data, yet at an inference speed more than twice as fast as DeepFace-EMD (Phan et al. 2022). In addition, via a human study, our model shows promising explainability through the visualization of cross-attention. We believe our work can inspire more explorations in using ViTs for face identification.

cs.CV↗

arXiv2023

TST$^\mathrm{R}$: Target Similarity Tuning Meets the Real World

Target similarity tuning (TST) is a method of selecting relevant examples in natural language (NL) to code generation through large language models (LLMs) to improve performance. Its goal is to adapt a sentence embedding model to have the similarity between two NL inputs match the similarity between their associated code outputs. In this paper, we propose different methods to apply and improve TST in the real world. First, we replace the sentence transformer with embeddings from a larger model, which reduces sensitivity to the language distribution and thus provides more flexibility in synthetic generation of examples, and we train a tiny model that transforms these embeddings to a space where embedding similarity matches code similarity, which allows the model to remain a black box and only requires a few matrix multiplications at inference time. Second, we show how to efficiently select a smaller number of training examples to train the TST model. Third, we introduce a ranking-based evaluation for TST that does not require end-to-end code generation experiments, which can be expensive to perform.

cs.AI↗

arXiv2023

FormaT5: Abstention and Examples for Conditional Table Formatting with Natural Language

Formatting is an important property in tables for visualization, presentation, and analysis. Spreadsheet software allows users to automatically format their tables by writing data-dependent conditional formatting (CF) rules. Writing such rules is often challenging for users as it requires them to understand and implement the underlying logic. We present FormaT5, a transformer-based model that can generate a CF rule given the target table and a natural language description of the desired formatting logic. We find that user descriptions for these tasks are often under-specified or ambiguous, making it harder for code generation systems to accurately learn the desired rule in a single step. To tackle this problem of under-specification and minimise argument errors, FormaT5 learns to predict placeholders though an abstention objective. These placeholders can then be filled by a second model or, when examples of rows that should be formatted are available, by a programming-by-example system. To evaluate FormaT5 on diverse and real scenarios, we create an extensive benchmark of 1053 CF tasks, containing real-world descriptions collected from four different sources. We release our benchmarks to encourage research in this area. Abstention and filling allow FormaT5 to outperform 8 different neural approaches on our benchmarks, both with and without examples. Our results illustrate the value of building domain-specific learning systems.

cs.AI↗