Related papers: CoGate-LSTM: Prototype-Guided Feature-Space Gating…

Current multimodal toxicity benchmarks typically use a single binary hatefulness label. This coarse approach conflates two fundamentally different characteristics of expression: tone and content. Drawing on communication science theory, we…

The recent emergence of multimodal large language models (LLMs) has introduced new opportunities for improving visual hazard recognition on construction sites. Unlike traditional computer vision models that rely on domain-specific training…

Detecting hateful content is a challenging and important problem. Automated tools, like machine-learning models, can help, but they require continuous training to adapt to the ever-changing landscape of social media. In this work, we…

In this paper, we introduce the Interpretable Cross-Examination Technique (ICE-T), a novel approach that leverages structured multi-prompt techniques with Large Language Models (LLMs) to improve classification performance over zero-shot and…

In the day and age of social media, users have become prone to online hate speech. Several attempts have been made to classify hate speech using machine learning but the state-of-the-art models are not robust enough for practical…

We introduce Lattice, a hybrid sequential prediction system that conditionally activates learned behavioral structure using binary confidence gating. The system clusters behavior windows into behavioral archetypes and uses binary confidence…

Few-shot Learning (FSL), which endeavors to develop the generalization ability for recognizing novel classes using only a few images, faces significant challenges due to data scarcity. Recent CLIP-like methods based on contrastive…

We propose a novel method that tackles the problem of unsupervised domain adaptation for semantic segmentation by maximizing the cosine similarity between the source and the target domain at the feature level. A segmentation network mainly…

Prompt engineering is an essential technique for enhancing the abilities of large language models (LLMs) by providing explicit and specific instructions. It enables LLMs to excel in various tasks, such as arithmetic reasoning, question…

Prompt injection and jailbreaking attacks pose persistent security challenges to large language model (LLM)-based systems. We present PromptScreen, an efficient and systematically evaluated defense architecture that mitigates these threats…

Urban systems are managed using complex textual documentation that need coding and analysis to set requirements and evaluate built environment performance. This paper contributes to the study of applying large-language models (LLM) to…

Feature discovery from complex unstructured data is fundamentally a reasoning problem: it requires identifying abstractions that are predictive of a target outcome while avoiding leakage, proxies, and post-outcome signals. With the…

End-to-end interpretation currently dominates the remote sensing fine-grained ship classification (RS-FGSC) task. However, the inference process remains uninterpretable, leading to criticisms of these models as "black box" systems. To…

In this study, we implement a novel BERT architecture for multitask fine-tuning on three downstream tasks: sentiment classification, paraphrase detection, and semantic textual similarity prediction. Our model, Multitask BERT, incorporates…

Streaming TTS that receives streaming text is essential for interactive systems, yet this scheme faces two major challenges: unnatural prosody due to missing lookahead and long-form collapse due to unbounded context. We propose a…

Researchers have investigated the potential of leveraging pre-trained language models, such as CodeBERT, to enhance source code-related tasks. Previous methodologies have relied on CodeBERT's '[CLS]' token as the embedding representation of…

Existing text representations such as embeddings and bag-of-words are not suitable for rule learning due to their high dimensionality and absent or questionable feature-level interpretability. This article explores whether large language…

Optimization-based adversarial suffixes can jailbreak aligned large language models (LLMs) while remaining fluent, weakening static and windowed perplexity-based detectors. We cast adversarial suffix detection as an online change-point…

Ensuring the safety and harmlessness of Large Language Models (LLMs) has become equally critical as their performance in applications. However, existing safety alignment methods typically suffer from safety-performance trade-offs and the…

Language-independent tokenisation (LIT) methods that do not require labelled language resources or lexicons have recently gained popularity because of their applicability in resource-poor languages. Moreover, they compactly represent a…