Related papers: From Verification to Herding: Exploiting Software'…
As AI systems begin to automate complex tasks, supervision increasingly relies on weaker models or limited human oversight that cannot fully verify output quality. A model more capable than its supervisors could exploit this gap through…
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…
For many practical problems, the regression models follow the strong heredity property (also known as the marginality), which means they include parent main effects when a second-order effect is present. Existing methods rely mostly on…
Classifiers trained with Empirical Risk Minimization (ERM) tend to rely on attributes that have high spurious correlation with the target. This can degrade the performance on underrepresented (or 'minority') groups that lack these…
We analyze some voting models mimicking online evaluation systems intended to reduce the information overload. The minimum number of operations needed for a system to be effective is analytically estimated. When herding effects are present,…
We study the problem of crowdsourced PAC learning of threshold functions. This is a challenging problem and only recently have query-efficient algorithms been established under the assumption that a noticeable fraction of the workers are…
Performance verification is a nascent but promising tool for understanding the performance and limitations of heuristics under realistic assumptions. Bespoke performance verification tools have already demonstrated their value in settings…
Investigations of social influence in collective decision-making have become possible due to recent technologies and platforms that record interactions in far larger groups than could be studied before. Herding and its impact on…
Context: Software testing plays an essential role in product quality improvement. For this reason, several software testing models have been developed to support organizations. However, adoption of testing process models inside…
Regression Testing is exclusively executed to guarantee the desirable functionality of existing software after pursuing quite a few amendments or variations in it. Perhaps, it testifies the quality of the modified software by concealing the…
Zero-Shot Learning (ZSL) is an emerging research that aims to solve the classification problems with very few training data. The present works on ZSL mainly focus on the mapping of learning semantic space to visual space. It encounters many…
An important emerging application of coding agents is agent optimization: the iterative improvement of a target agent through edit-execute-evaluate cycles. Despite its relevance, the community lacks a systematic understanding of coding…
Herding is a deterministic algorithm used to generate data points that can be regarded as random samples satisfying input moment conditions. The algorithm is based on the complex behavior of a high-dimensional dynamical system and is…
Preference-based reinforcement learning (PbRL) has shown impressive capabilities in training agents without reward engineering. However, a notable limitation of PbRL is its dependency on substantial human feedback. This dependency stems…
Recent efforts in LLM alignment have focused on constructing large-scale preference datasets via human or Artificial Intelligence (AI) annotators. However, such approaches rely on instance-wise supervision, incurring substantial annotation…
Sentiment analysis in software engineering focuses on understanding emotions expressed in software artifacts. Previous research highlighted the limitations of applying general off-the-shelf sentiment analysis tools within the software…
This paper presents a simple, effective, and cost-efficient strategy to improve LLM performance by scaling test-time compute. Our strategy builds upon the repeated-sampling-then-voting framework, with a novel twist: incorporating multiple…
Sampling-based algorithms are widely used for motion planning in high-dimensional configuration spaces. However, due to low sampling efficiency, their performance often diminishes in complex configuration spaces with narrow corridors.…
Software performance testing requires a set of inputs that exercise different sections of the code to identify performance issues. However, running tests on a large set of inputs can be a very time-consuming process. It is even more…
Natural language prompts have been shown to facilitate cross-task generalization for large language models. However, with no or limited labeled examples, the cross-task performance is highly sensitive to the choice of prompts, while…