Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs arXiv:2508.19432v1 Announce Type: new Abstract: Quantization enables efficient deployment of large language models (LLMs) in resource-constrained environments by significantly reducing memory and computation costs. While quantized LLMs often maintain performance…
AI-Powered Detection of Inappropriate Language in Medical School Curricula arXiv:2508.19883v1 Announce Type: cross Abstract: The use of inappropriate language — such as outdated, exclusionary, or non-patient-centered terms — medical instructional materials can significantly influence clinical training, patient interactions, and health…
Instructional Agents: LLM Agents on Automated Course Material Generation for Teaching Faculties arXiv:2508.19611v1 Announce Type: new Abstract: Preparing high-quality instructional materials remains a labor-intensive process that often requires extensive coordination among teaching faculty, instructional designers, and teaching assistants. In this…
MathBuddy: A Multimodal System for Affective Math Tutoring arXiv:2508.19993v1 Announce Type: cross Abstract: The rapid adoption of LLM-based conversational systems is already transforming the landscape of educational technology. However, the current state-of-the-art learning models do not take into account the…
InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning arXiv:2508.19679v1 Announce Type: new Abstract: Recent advances in Vision-Language Models (VLMs) have enabled mobile agents to perceive and interact with real-world mobile environments based on human instructions. However,…
Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation? arXiv:2508.19827v1 Announce Type: new Abstract: Recent work has demonstrated that Chain-of-Thought (CoT) often yields limited gains for soft-reasoning problems such as analytical and commonsense reasoning. CoT can also be…
Understanding Fairness-Accuracy Trade-offs in Machine Learning Models: Does Promoting Fairness Undermine Performance? arXiv:2411.17374v2 Announce Type: replace-cross Abstract: Fairness in both Machine Learning (ML) predictions and human decision-making is essential, yet both are susceptible to different forms of bias, such as…
Tracking World States with Language Models: State-Based Evaluation Using Chess arXiv:2508.19851v1 Announce Type: new Abstract: Large Language Models (LLMs) exhibit emergent capabilities in structured domains, suggesting they may implicitly internalize high-fidelity representations of world models. While probing techniques have shown…
EnvInjection: Environmental Prompt Injection Attack to Multi-modal Web Agents arXiv:2505.11717v2 Announce Type: replace-cross Abstract: Multi-modal large language model (MLLM)-based web agents interact with webpage environments by generating actions based on screenshots of the webpages. Environmental prompt injection attacks manipulate the…
CASE: An Agentic AI Framework for Enhancing Scam Intelligence in Digital Payments arXiv:2508.19932v1 Announce Type: new Abstract: The proliferation of digital payment platforms has transformed commerce, offering unmatched convenience and accessibility globally. However, this growth has also attracted malicious actors,…
