Search arXiv⌕ Search

arXiv subjects

Murali Krishna Ramanathan

Publications and source records attributed to Murali Krishna Ramanathan.

22 records · Page 2Linked to original sources

Multi-lingual Evaluation of Code Generation Models

We present new benchmarks on evaluation code generation models: MBXP and Multilingual HumanEval, and MathQA-X. These datasets cover over 10 programming languages and are generated using a scalable conversion framework that transpiles prompts and test cases from the original Python datasets into the corresponding data in the target language. Using these benchmarks, we are able to assess the performance of code generation models in a multi-lingual fashion, and discovered generalization ability of language models on out-of-domain languages, advantages of multi-lingual models over mono-lingual, the ability of few-shot prompting to teach the model new languages, and zero-shot translation abilities even on mono-lingual settings. Furthermore, we use our code generation model to perform large-scale bootstrapping to obtain synthetic canonical solutions in several languages, which can be used for other code-related evaluations such as code insertion, robustness, or summarization tasks. Overall, our benchmarks represents a significant step towards a deeper understanding of language models' code generation abilities. We publicly release our code and datasets at https://github.com/amazon-research/mxeval.

cs.LG↗

Greener yet Powerful: Taming Large Code Generation Models with Quantization

ML-powered code generation aims to assist developers to write code in a more productive manner, by intelligently generating code blocks based on natural language prompts. Recently, large pretrained deep learning models have substantially pushed the boundary of code generation and achieved impressive performance. Despite their great power, the huge number of model parameters poses a significant threat to adapting them in a regular software development environment, where a developer might use a standard laptop or mid-size server to develop her code. Such large models incur significant resource usage (in terms of memory, latency, and dollars) as well as carbon footprint. Model compression is a promising approach to address these challenges. Several techniques are proposed to compress large pretrained models typically used for vision or textual data. Out of many available compression techniques, we identified that quantization is mostly applicable for code generation task as it does not require significant retraining cost. As quantization represents model parameters with lower-bit integer (e.g., int8), the model size and runtime latency would both benefit from such int representation. We extensively study the impact of quantized model on code generation tasks across different dimension: (i) resource usage and carbon footprint, (ii) accuracy, and (iii) robustness. To this end, through systematic experiments we find a recipe of quantization technique that could run even a $6$B model in a regular laptop without significant accuracy or robustness degradation. We further found the recipe is readily applicable to code summarization task as well.

cs.LG↗

ReCode: Robustness Evaluation of Code Generation Models

Code generation models have achieved impressive performance. However, they tend to be brittle as slight edits to a prompt could lead to very different generations; these robustness properties, critical for user experience when deployed in real-life applications, are not well understood. Most existing works on robustness in text or code tasks have focused on classification, while robustness in generation tasks is an uncharted area and to date there is no comprehensive benchmark for robustness in code generation. In this paper, we propose ReCode, a comprehensive robustness evaluation benchmark for code generation models. We customize over 30 transformations specifically for code on docstrings, function and variable names, code syntax, and code format. They are carefully designed to be natural in real-life coding practice, preserve the original semantic meaning, and thus provide multifaceted assessments of a model's robustness performance. With human annotators, we verified that over 90% of the perturbed prompts do not alter the semantic meaning of the original prompt. In addition, we define robustness metrics for code generation models considering the worst-case behavior under each type of perturbation, taking advantage of the fact that executing the generated code can serve as objective evaluation. We demonstrate ReCode on SOTA models using HumanEval, MBPP, as well as function completion tasks derived from them. Interesting observations include: better robustness for CodeGen over InCoder and GPT-J; models are most sensitive to syntax perturbations; more challenging robustness evaluation on MBPP over HumanEval.

cs.LG↗

A Study of Real-World Data Races in Golang

The concurrent programming literature is rich with tools and techniques for data race detection. Less, however, has been known about real-world, industry-scale deployment, experience, and insights about data races. Golang (Go for short) is a modern programming language that makes concurrency a first-class citizen. Go offers both message passing and shared memory for communicating among concurrent threads. Go is gaining popularity in modern microservice-based systems. Data races in Go stand in the face of its emerging popularity. In this paper, using our industrial codebase as an example, we demonstrate that Go developers embrace concurrency and show how the abundance of concurrency alongside language idioms and nuances make Go programs highly susceptible to data races. Google's Go distribution ships with a built-in dynamic data race detector based on ThreadSanitizer. However, dynamic race detectors pose scalability and flakiness challenges; we discuss various software engineering trade-offs to make this detector work effectively at scale. We have deployed this detector in Uber's 46 million lines of Go codebase hosting 2100 distinct microservices, found over 2000 data races, and fixed over 1000 data races, spanning 790 distinct code patches submitted by 210 unique developers over a six-month period. Based on a detailed investigation of these data race patterns in Go, we make seven high-level observations relating to the complex interplay between the Go language paradigm and data races.

cs.DC↗