Related papers: The Compliance Paradox: Semantic-Instruction Decou…

Large Multimodal Models (LMMs) have demonstrated impressive capabilities in video reasoning via Chain-of-Thought (CoT). However, the robustness of their reasoning chains remains questionable. In this paper, we identify a critical failure…

Frontier Large language models (LLMs) like ChatGPT and Gemini can decipher cryptic compiler errors for novice programmers, but their computational scale, cost, and tendency to over-assist make them problematic for widespread pedagogical…

This paper presents a hybrid methodology that enhances the training process of deep learning (DL) models by embedding domain expert knowledge using ontologies and answer set programming (ASP). By integrating these symbolic AI methods, we…

While most AI alignment research focuses on preventing models from generating explicitly harmful content, a more subtle risk is emerging: capability-oriented training induced exploitation. We investigate whether language models, when…

As large language models (LLMs) achieve strong performance on traditional benchmarks, there is an urgent need for more challenging evaluation frameworks that probe deeper aspects of semantic understanding. We introduce SAGE (Semantic…

Automatic Short Answer Grading (ASAG) with generative large language models (LLMs) has recently demonstrated strong performance without task-specific fine-tuning, while also enabling the generation of synthetic feedback for educational…

As machine learning models are increasingly fine-tuned on synthetic data, there is a critical risk of subtle misalignments spreading through interconnected AI systems. This paper investigates subliminal corruption, which we define as…

As Large Language Models (LLMs) transition from code completion tools to autonomous system architects, their impact on long-term software maintainability remains unquantified. While existing research benchmarks functional correctness…

The reasoning, writing, text-editing, and retrieval capabilities of proprietary large language models (LLMs) have advanced rapidly, providing users with an ever-expanding set of functionalities. However, this growing utility has also led to…

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Automated detection of software vulnerabilities is critical for enhancing security, yet existing methods often struggle with the complexity and diversity of modern codebases. In this paper, we introduce EnStack, a novel ensemble stacking…

Large Language Models (LLMs) are increasingly deployed in high-risk domains. However, state-of-the-art LLMs often exhibit hallucinations, raising serious concerns about their reliability. Prior work has explored adversarial attacks to…

End-to-end Large Speech Language Models (LSLMs) have demonstrated impressive conversational generation abilities, yet consistently fall short of traditional pipeline systems on semantic understanding benchmarks. In this work, we reveal…

LLM-assisted defect discovery has a precision crisis: plausible-but-wrong reports overwhelm maintainers and degrade credibility for real findings. We present Refute-or-Promote, an inference-time reliability pattern combining Stratified…

Large language models (LLMs) are being rapidly integrated into decision-support tools, automation workflows, and AI-enabled software systems. However, their behavior in production environments remains poorly understood, and their failure…

The adoption of Large Language Models (LLMs) as automated evaluators (LLM-as-a-judge) has revealed critical inconsistencies in current evaluation frameworks. We identify two fundamental types of inconsistencies: (1) Score-Comparison…

Although Large Language Models (LLMs) are becoming increasingly powerful, they still exhibit significant but subtle weaknesses, such as mistakes in instruction-following or coding tasks. As these unexpected errors could lead to severe…

Large language models (LLMs) are increasingly trained on massive, heterogeneous text corpora, raising serious concerns about the unauthorised use of proprietary or personal data during model training. In this work, we address the problem of…

Aligned large language models (LLMs) are vulnerable to jailbreaking attacks, which bypass the safeguards of targeted LLMs and fool them into generating objectionable content. While initial defenses show promise against token-based threat…

Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts safety guarantees from single-pass inference to the…