11 accepted papers
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 an…
We introduce jqBench, a new benchmark for evaluating language models on JSON querying and transformation tasks, where the intent can be given specified using natural language and/or examples. Whereas jqBench is mainly aimed at using the `jq` tool, it can be used to evaluate other programming languag…
Large language models (LLMs) can be leveraged to help write formulas in spreadsheets, but formula data resources 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 another model to generate syntheti…
Large language models (LLMs) can generate code from examples without being limited to a DSL, but they lack search, as sampled programs are independent. In this paper, we use an LLM as a policy that generates lines of code and then join these lines of code to let the LLM implicitly estimate the value…
Tools that help with email folder management are limited, as users have to manually write rules to assign emails to folders. We present EMFORE, an iterative learning system that automatically learns and updates such rules from observations. EMFORE is fast enough to suggest and update rules in real t…
Spreadsheets are a vital tool for end-user data management. Using large language models for formula authoring assistance in these environments can be difficult, as these models are expensive to train and challenging to deploy due to their size (up to billions of parameters). We present FLAME, a tran…
MBPP is a popular dataset for evaluating the task of code generation from natural language. Despite its popularity, there are three problems: (1) it relies on providing test cases to generate the right signature, (2) there is poor alignment between instruction and evaluation test cases, and (3) cont…
Language models struggle in generating code for low-resource programming languages, since these are underrepresented in training data. Either examples or documentation are commonly used for improved code generation. We propose to use both types of information together and present retrieval augmented…
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 g…
Most programmers make mistakes when writing code. Some of these mistakes are small and require few edits to the original program – a class of errors recently termed last mile mistakes. These errors break the flow for experienced developers and can stump novice programmers. Existing automated repair…
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…