Related papers: Zero-Shot Confidence Estimation for Small LLMs: Wh…
This paper studies whether a lightweight supervised aggregator can combine diverse zero-shot large language model outputs into a stronger downstream signal for corporate disclosure classification. Zero-shot LLMs can read disclosures without…
Self-consistency (Wang et al., 2023) suggests that the most consistent answer obtained through large language models (LLMs) is more likely to be correct. In this paper, we challenge this argument and propose a nuanced correction. Our…
Overconfidence is a common issue for deep neural networks, limiting their deployment in real-world applications. To better estimate confidence, existing methods mostly focus on fully-supervised scenarios and rely on training labels. In this…
The conventional modus operandi for adapting pre-trained vision-language models (VLMs) during test-time involves tuning learnable prompts, ie, test-time prompt tuning. This paper introduces Test-Time Low-rank adaptation (TTL) as an…
Large language models (LLMs) are systematically overconfident: they routinely express high certainty on questions they often answer incorrectly. Existing calibration methods either require labeled validation data, degrade under distribution…
Large Language Models (LLMs) have become a focal point of research across various domains, including software engineering, where their capabilities are increasingly leveraged. Recent studies have explored the integration of LLMs into…
Strategic model selection and reasoning settings are more effective than ensembling for optimizing automated scoring with large language models (LLMs). We examined self-consistency (intra-model majority voting) and reasoning effort for…
Conventional commits provide a structured format for writing commit messages, which improves readability, software maintenance, and enables automation tools such as changelog generators and semantic versioning systems. Existing approaches…
This study investigates the use of large language models (LLMs) for story point estimation. Story points are unitless, project-specific effort estimates that help developers on the scrum team forecast which product backlog items they plan…
While deep learning, including Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), has significantly advanced classification performance, its typical reliance on extensive annotated datasets presents a major obstacle in…
In Self-Supervised Learning (SSL), pre-training and evaluation are resource intensive. In the speech domain, current indicators of the quality of SSL models during pre-training, such as the loss, do not correlate well with downstream…
Small language models (SLMs; 1-12B params, sometimes up to 20B) are sufficient and often superior for agentic workloads where the objective is schema- and API-constrained accuracy rather than open-ended generation. We synthesize recent…
The effectiveness of unlabeled data in Semi/Self-Supervised Learning (SSL) depends on appropriate assumptions for specific scenarios, thereby enabling the selection of beneficial unsupervised pretext tasks. However, existing research has…
This study evaluates the performance of Large Language Models (LLMs) on SemEval-2020 Task 4 dataset, focusing on commonsense validation and explanation. Our methodology involves evaluating multiple LLMs, including LLaMA3-70B, Gemma2-9B, and…
Semi-Supervised Learning (SSL) is a framework that utilizes both labeled and unlabeled data to enhance model performance. Conventional SSL methods operate under the assumption that labeled and unlabeled data share the same label space.…
Calibration is crucial as large language models (LLMs) are increasingly deployed to convert natural language queries into SQL for commercial databases. In this work, we investigate calibration techniques for assigning confidence to…
When using an LLM through an API provider, users expect the served model to remain consistent over time, a property crucial for the reliability of downstream applications and the reproducibility of research. Existing audit methods are too…
Requirements classification assigns natural language requirements to predefined classes, such as functional and non functional. Accurate classification reduces risk and improves software quality. Most existing models rely on supervised…
Large language models (LLMs) are known for their exceptional performance across a range of natural language processing tasks, but their deployment comes at a high computational and financial cost. On the other hand, smaller language models…
The emergence of large language models (LLMs), pre-trained on massive datasets, has demonstrated strong performance across a wide range of natural language processing (NLP) tasks, including text classification. While prior studies have…