相关论文: Indexed Labels for Loop Iteration Dependent Costs

We introduce the notion of identity coercions between non-indexed and indexed variants of inductive datatypes, such as lists and vectors. An identity coercion translates one type to another such that the coercion function definitionally…

Source code is usually formatted with elements like indentation and newlines to improve readability for human developers. However, these visual aids do not seem to be beneficial for large language models (LLMs) in the same way since the…

We tackle sequential learning under label noise in applications where a human supervisor can be queried to relabel suspicious examples. Existing approaches are flawed, in that they only relabel incoming examples that look "suspicious" to…

IR in low-resource languages remains limited by the scarcity of high-quality, task-specific annotated datasets. Manual annotation is expensive and difficult to scale, while using large language models (LLMs) as automated annotators…

Given the clinical notes written in electronic health records (EHRs), it is challenging to predict the diagnostic codes which is formulated as a multi-label classification task. The large set of labels, the hierarchical dependency, and the…

Data annotation often involves multiple sources with different cost-quality trade-offs, such as fast large language models (LLMs), slow reasoning models, and human experts. In this work, we study the problem of routing inputs to the most…

Accurate labels are critical for deriving robust machine learning models. Labels are used to train supervised learning models and to evaluate most machine learning paradigms. In this paper, we model the accuracy and cost of a common weak…

Text classification, a core component of task-oriented dialogue systems, attracts continuous research from both the research and industry community, and has resulted in tremendous progress. However, existing method does not consider the use…

The cost of labeling data often limits the performance of machine learning systems. In multi-task learning, related tasks provide information to each other and improve overall performance, but the label cost can vary among tasks. How should…

This paper introduces a novel crowdsourcing worker selection algorithm, enhancing annotation quality and reducing costs. Unlike previous studies targeting simpler tasks, this study contends with the complexities of label interdependencies…

Many success stories involving deep neural networks are instances of supervised learning, where available labels power gradient-based learning methods. Creating such labels, however, can be expensive and thus there is increasing interest in…

Compared with multi-class classification, multi-label classification that contains more than one class is more suitable in real life scenarios. Obtaining fully labeled high-quality datasets for multi-label classification problems, however,…

This work explores an unexpected application of Implicit Computational Complexity (ICC) to parallelize loops in imperative programs. Thanks to a lightweight dependency analysis, our algorithm allows splitting a loop into multiple loops that…

Learning with the \textit{instance-dependent} label noise is challenging, because it is hard to model such real-world noise. Note that there are psychological and physiological evidences showing that we humans perceive instances by…

Most machine learning and data analytics applications, including performance engineering in software systems, require a large number of annotations and labelled data, which might not be available in advance. Acquiring annotations often…

Label noise widely exists in large-scale datasets and significantly degenerates the performances of deep learning algorithms. Due to the non-identifiability of the instance-dependent noise transition matrix, most existing algorithms address…

While constructing supervised learning models, we require labelled examples to build a corpus and train a machine learning model. However, most studies have built the labelled dataset manually, which in many occasions is a daunting task. To…

The fundamental problem of weighted sampling involves sampling of satisfying assignments of Boolean formulas, which specify sampling sets, and according to distributions defined by pre-specified weight functions to weight functions. The…

Context: Various approaches aim to support program comprehension by automatically detecting algorithms in source code. However, no empirical evaluations of their helpfulness have been performed. Objective: To empirically evaluate how…

We propose a framework that amortizes the cost of inference-time reasoning by converting transient critiques into retrievable guidelines, through a file-based memory system and agent-controlled tool calls. We evaluate this method on the…