Related papers: In harmony with gpt-oss
Machine learning practitioners often fine-tune generative pre-trained models like GPT-3 to improve model performance at specific tasks. Previous works, however, suggest that fine-tuned machine learning models memorize and emit sensitive…
Trust is one of the most important factors shaping whether and how people adopt and rely on artificial intelligence (AI). Yet most existing studies measure trust in terms of functionality, focusing on whether a system is reliable, accurate,…
In this paper, we address the problem of using sentiment analysis tools 'off-the-shelf,' that is when a gold standard is not available for retraining. We evaluate the performance of four SE-specific tools in a cross-platform setting, i.e.,…
The exponential growth in user acquisition and popularity of OpenAIs ChatGPT, an artificial intelligence(AI) powered chatbot, was accompanied by widespread mainstream media coverage. This article presents a quantitative data analysis of the…
Students learning programming exercise agency in deciding when and how to use GenAI tools like ChatGPT. However, this agency is often implicit and shaped by deadline pressure and peer behavior rather than explicit and conscious learning…
Generative adversarial networks have seen rapid development in recent years and have led to remarkable improvements in generative modelling of images. However, their application in the audio domain has received limited attention, and…
AI Collaborator, powered by OpenAI's GPT-4, is a groundbreaking tool designed for human-AI collaboration research. Its standout feature is the ability for researchers to create customized AI personas for diverse experimental setups using a…
Voice agents increasingly require reliable tool use from speech, whereas prominent tool-calling benchmarks remain text-based. We study whether verified text benchmarks can be converted into controlled audio-based tool calling evaluations…
This paper presents a new tool learning dataset Seal-Tools, which contains self-instruct API-like tools. Seal-Tools not only offers a large number of tools, but also includes instances which demonstrate the practical application of tools.…
LLM agents have begun to find real security vulnerabilities that human auditors and automated fuzzers missed for decades, in source-available targets where the analyst can build and instrument the code. In practice the work is split among…
Modern natural language models such as the GPT-2/GPT-3 contain tremendous amounts of information about human belief in a consistently testable form. If these models could be shown to accurately reflect the underlying beliefs of the human…
Millions of users leverage generative pretrained transformer (GPT)-based language models developed by leading model providers for a wide range of tasks. To support enhanced user interaction and customization, many platforms-such as…
We propose a method for knowledge transfer between semantically related classes in ImageNet. By transferring knowledge from the images that have bounding-box annotations to the others, our method is capable of automatically populating…
When large language models (LLMs) are consulted as forecasting tools, the independence of individual errors -- the foundation of collective intelligence -- may collapse. We test three conditions necessary for this "epistemic monoculture" to…
This study investigates perceptions and use of generative artificial intelligence (GenAI) tools among students and faculty in statistics and data science at a historically Black college or university. Survey data from 119 valid student…
Context: This paper provides an in-depth examination of the generation and evaluation of Metamorphic Relations (MRs) using GPT models developed by OpenAI, with a particular focus on the capabilities of GPT-4 in software testing…
Creating large-scale verifiable training datasets for issue-resolving tasks is a critical yet notoriously difficult challenge. Existing methods on automating the Gym environment setup process for real-world issues suffer from low success…
Reproducibility in reinforcement learning is challenging: uncontrolled stochasticity from many sources, such as the learning algorithm, the learned policy, and the environment itself have led researchers to report the performance of learned…
Automated essay scoring (AES) to evaluate second language (L2) proficiency has been a firmly established technology used in educational contexts for decades. Although holistic scoring has seen advancements in AES that match or even exceed…
Generative AI (genAI) tools, such as ChatGPT or Copilot, are advertised to improve developer productivity and are being integrated into software development. However, misaligned trust, skepticism, and usability concerns can impede the…