Related papers: Context-Specific Instruction: A Longitudinal Study…
This paper investigates context stickiness in in-context learning (ICL), a phenomenon where earlier examples in a prompt interfere with a transformer's ability to adapt to later tasks. Using synthetic regression tasks over linear and…
The quality of AI-generated output is often attributed to prompting technique, but extensive empirical observation suggests that context completeness may be more strongly associated with output quality. This paper introduces Context…
Contextual information plays a vital role for software developers when understanding and fixing a bug. Consequently, deep learning-based program repair techniques leverage context for bug fixes. However, existing techniques treat context in…
Concurrency bugs, caused by improper synchronization of shared resources in multi-threaded or distributed systems, are notoriously hard to detect and thus compromise software reliability and security. The existing deep learning methods face…
Detecting and fixing bugs are two of the most important yet frustrating parts of the software development cycle. Existing bug detection tools are based mainly on static analyzers, which rely on mathematical logic and symbolic reasoning…
We study the sequential batch learning problem in linear contextual bandits with finite action sets, where the decision maker is constrained to split incoming individuals into (at most) a fixed number of batches and can only observe…
Background and context: Debugging is a significant and often frustrating challenge for beginner programmers. Understanding students' debugging behaviours and strategies can help to identify common difficulties and inform approaches for…
Debugging physical computing projects provides a rich context to understand cross-disciplinary problem solving that integrates multiple domains of computing and engineering. Yet understanding and assessing students' learning of debugging…
Background and Context: While debugging is recognized as an essential practice, for many students, encountering bugs can generate emotional responses such as fear and anxiety that can lead to disengagement and the avoidance of computer…
Software bugs cost the global economy billions of dollars annually and claim ~50\% of the programming time from software developers. Locating these bugs is crucial for their resolution but challenging. It is even more challenging in…
Fault localization has been determined as a major resource factor in the software development life cycle. Academic fault localization techniques are mostly unknown and unused in professional environments. Although manual debugging…
Debugging, finding and fixing bugs in code, is a heterogeneous process that shapes novice learners' self-beliefs and motivation in computing. Our Debugging by Design intervention (DbD) provocatively puts students in control over bugs by…
Researchers have developed numerous debugging approaches to help programmers in the debugging process, but these approaches are rarely used in practice. In this paper, we investigate how programmers debug their code and what researchers…
Long-context modelling for large language models (LLMs) has been a key area of recent research because many real world use cases require reasoning over longer inputs such as documents. The focus of research into modelling long context has…
Automated issue fixing is a critical task in software debugging and has recently garnered significant attention from academia and industry. However, existing fixing techniques predominantly focus on the repair phase, often overlooking the…
Fault localization is a critical step in software maintenance. Yet, many existing techniques, such as Spectrum-Based Fault Localization (SBFL), rely heavily on the availability of fault-triggering tests to be effective. In practice,…
With the rapid development of large language models (LLMs), distributed training and inference frameworks like DeepSpeed have become essential for scaling model training and inference across multiple GPUs or nodes. However, the increasing…
The validation process for microprocessors is a very complex task that consumes substantial engineering time during the design process. Bugs that degrade overall system performance, without affecting its functional correctness, are…
Many research areas in software engineering, such as mutation testing, automatic repair, fault localization, and fault injection, rely on empirical knowledge about recurring bug-fixing code changes. Previous studies in this field focus on…
We introduce MetaICL (Meta-training for In-Context Learning), a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learning on a large set of training tasks. This meta-training…