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.
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.
Imagine a developer who can only change their last line of code, how often would they have to start writing a function from scratch before it is correct? Auto-regressive models for code generation from natural language have a similar limitation: they do not easily allow reconsidering earlier tokens generated. We introduce CodeFusion, a pre-trained diffusion code generation model that addresses this limitation by iteratively denoising a complete program conditioned on the encoded natural language. We evaluate CodeFusion on the task of natural language to code generation for Bash, Python, and Microsoft Excel conditional formatting (CF) rules. Experiments show that CodeFusion (75M parameters) performs on par with state-of-the-art auto-regressive systems (350M-175B parameters) in top-1 accuracy and outperforms them in top-3 and top-5 accuracy due to its better balance in diversity versus quality.
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.
Large language models (LLMs) are increasingly applied for tabular tasks using in-context learning. The prompt representation for a table may play a role in the LLMs ability to process the table. Inspired by prior work, we generate a collection of self-supervised structural tasks (e.g. navigate to a cell and row; transpose the table) and evaluate the performance differences when using 8 formats. In contrast to past work, we introduce 8 noise operations inspired by real-world messy data and adversarial inputs, and show that such operations can impact LLM performance across formats for different structural understanding tasks.
Generative AI and large language models hold great promise in enhancing programming education by automatically generating individualized feedback for students. We investigate the role of generative AI models in providing human tutor-style programming hints to help students resolve errors in their buggy programs. Recent works have benchmarked state-of-the-art models for various feedback generation scenarios; however, their overall quality is still inferior to human tutors and not yet ready for real-world deployment. In this paper, we seek to push the limits of generative AI models toward providing high-quality programming hints and develop a novel technique, GPT4Hints-GPT3.5Val. As a first step, our technique leverages GPT-4 as a ``tutor'' model to generate hints -- it boosts the generative quality by using symbolic information of failing test cases and fixes in prompts. As a next step, our technique leverages GPT-3.5, a weaker model, as a ``student'' model to further validate the hint quality -- it performs an automatic quality validation by simulating the potential utility of providing this feedback. We show the efficacy of our technique via extensive evaluation using three real-world datasets of Python programs covering a variety of concepts ranging from basic algorithms to regular expressions and data analysis using pandas library.
Users are increasingly being warned to check AI-generated content for correctness. Still, as LLMs (and other generative models) generate more complex output, such as summaries, tables, or code, it becomes harder for the user to audit or evaluate the output for quality or correctness. Hence, we are seeing the emergence of tool-assisted experiences to help the user double-check a piece of AI-generated content. We refer to these as co-audit tools. Co-audit tools complement prompt engineering techniques: one helps the user construct the input prompt, while the other helps them check the output response. As a specific example, this paper describes recent research on co-audit tools for spreadsheet computations powered by generative models. We explain why co-audit experiences are essential for any application of generative AI where quality is important and errors are consequential (as is common in spreadsheet computations). We propose a preliminary list of principles for co-audit, and outline research challenges.
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. Systems that successfully clean such string data can have a significant impact on real users. While prior work has explored errors in string data, proposed approaches have often been limited to error detection or require that the user provide annotations, examples, or constraints to fix the errors. Furthermore, these systems have focused 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 patterns as data errors. DataVinci can automatically derive edits to the data error based on the majority patterns and constraints learned over other columns without the need for further user interaction. To handle strings with both syntactic and semantic substrings, DataVinci uses an LLM to abstract (and re-concretize) portions of strings that are semantic prior to learning majority patterns and deriving edits. Because not all data can result in majority patterns, DataVinci leverages execution information from an existing program (which reads the target data) to identify and correct data repairs that would not otherwise be identified. DataVinci outperforms 7 baselines on both error detection and repair when evaluated on 4 existing and new benchmarks.
Generative AI and large language models hold great promise in enhancing computing education by powering next-generation educational technologies for introductory programming. Recent works have studied these models for different scenarios relevant to programming education; however, these works are limited for several reasons, as they typically consider already outdated models or only specific scenario(s). Consequently, there is a lack of a systematic study that benchmarks state-of-the-art models for a comprehensive set of programming education scenarios. In our work, we systematically evaluate two models, ChatGPT (based on GPT-3.5) and GPT-4, and compare their performance with human tutors for a variety of scenarios. We evaluate using five introductory Python programming problems and real-world buggy programs from an online platform, and assess performance using expert-based annotations. Our results show that GPT-4 drastically outperforms ChatGPT (based on GPT-3.5) and comes close to human tutors' performance for several scenarios. These results also highlight settings where GPT-4 still struggles, providing exciting future directions on developing techniques to improve the performance of these models.
The widespread use of spreadsheet environments by billions of users presents a unique opportunity for formula-authoring assistance. Although large language models, such as Codex, can assist in general-purpose languages, they are expensive to train and challenging to deploy due to their large model sizes (up to billions of parameters). Moreover, they require hundreds of gigabytes of training data. We present FLAME, a T5-based model trained on Excel formulas that leverages domain insights to achieve competitive performance with a substantially smaller model (60M parameters) and two orders of magnitude less training data. We curate a training dataset using sketch deduplication, introduce an Excel-specific formula tokenizer for our model, and use domain-specific versions of masked span prediction and noisy auto-encoding as pretraining objectives. We evaluate FLAME on formula repair, formula auto-completion, and a novel task called syntax reconstruction. FLAME (60M) can outperform much larger models, such as Codex-Davinci (175B), Codex-Cushman (12B), and CodeT5 (220M), in 6 out of 10 settings.