Related papers: Tortoise: Interactive System Configuration Repair

Good parameter settings are crucial to achieve high performance in many areas of artificial intelligence (AI), such as propositional satisfiability solving, AI planning, scheduling, and machine learning (in particular deep learning).…

ChatGPT has revolutionized many research and industrial fields. ChatGPT has shown great potential in software engineering to boost various traditional tasks such as program repair, code understanding, and code generation. However, whether…

Although pre-trained language models encode generic knowledge beneficial for planning and control, they may fail to generate appropriate control policies for domain-specific tasks. Existing fine-tuning methods use human feedback to address…

Large pre-trained language models such as GPT-3, Codex, and Google's language model are now capable of generating code from natural language specifications of programmer intent. We view these developments with a mixture of optimism and…

As software systems become more complex and configurable, more performance problems tend to arise from the configuration designs. This has caused some configuration options to unexpectedly degrade performance which deviates from their…

Although the dynamic type system of Python facilitates the developers in writing Python programs, it also brings type errors at run-time. There exist rule-based approaches for automatically repairing Python type errors. The approaches can…

The goal of machine learning is to provide solutions which are trained by data or by experience coming from the environment. Many training algorithms exist and some brilliant successes were achieved. But even in structured environments for…

Context: Software has become an innovative solution nowadays for many applications and methods in science and engineering. Ensuring the quality and correctness of software is challenging because each program has different configurations and…

Logic programs are a powerful approach for solving NP-Hard problems. However, due to their declarative nature, debugging logic programs poses significant challenges. Unlike procedural paradigms, which allow for step-by-step inspection of…

In network management, when it comes to security breaches, human error constitutes a dominant factor. We present our tool topoS which automatically synthesizes low-level network configurations from high-level security goals. The automation…

Large language models (LLMs) have become increasingly capable of following instructions and complex reasoning, making prompting a flexible interface for adapting models without parameter updates. Yet prompt design remains labor-intensive…

A self-healing application brings itself into a stable state after a failure put the software into an unstable state. For such self-healing software application, finding fix for a previously unseen fault is a grand challenge. Asking the…

In prompt tuning, a prefix or suffix text is added to the prompt, and the embeddings (soft prompts) or token indices (hard prompts) of the prefix/suffix are optimized to gain more control over language models for specific tasks. This…

Finding the optimally performing configuration of a software system for a given setting is often challenging. Recent approaches address this challenge by learning performance models based on a sample set of configurations. However, building…

Research shows that errors in natural language can be corrected by translating texts to another language and back using language models. We explore to what extent this latent correction capability extends to Automated Program Repair (APR)…

Sequence-to-sequence models have been used to transform erroneous programs into correct ones when trained with a large enough dataset. Some recent studies also demonstrated strong empirical evidence that code review could improve the…

Modern software systems are often equipped with hundreds to thousands of configuration options, many of which greatly affect performance. Unfortunately, properly setting these configurations is challenging for developers due to the complex…

State-of-the-art language model fine-tuning techniques, such as Direct Preference Optimization (DPO), restrict user control by hard-coding predefined behaviors into the model. To address this, we propose a novel method, Configurable Safety…

The combination of Large Language Models (LLMs), systematic evaluation, and evolutionary algorithms has enabled breakthroughs in combinatorial optimization and scientific discovery. We propose to extend this powerful combination to the…

Our goal is to build systems which write code automatically from the kinds of specifications humans can most easily provide, such as examples and natural language instruction. The key idea of this work is that a flexible combination of…