Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608.29092v1 Announce Type: new Abstract: Large vision-language models (LVLMs) frequently generate content unsupported by visual inputs. Preliminary experiments show that visual evidence is pri...
arXiv:2608.29118v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) on narrowly harmful datasets can lead to misalignment broadly, a phenomenon known as emergent misalignment (EM...
arXiv:2608.29128v1 Announce Type: new Abstract: Tool-using agents are commonly evaluated by a single bit: whether an end-to-end workflow completed. This metric fails to distinguish failures that matt...
arXiv:2608.29198v1 Announce Type: new Abstract: As Large Language Models (LLMs) increasingly encourage users to disclose personal profiles for tailored assistance, measuring their political alignment...
arXiv:2608.29223v1 Announce Type: new Abstract: Accurate through-thickness measurement of subsurface delamination depth in Carbon Fiber Reinforced Polymer (CFRP) is important for structural assessmen...
arXiv:2608.29263v1 Announce Type: new Abstract: Large Language Models (LLMs) often suffer from hallucination and struggle with complex reasoning tasks requiring multi-hop domain knowledge. While inte...
arXiv:2608.29286v1 Announce Type: new Abstract: As Multimodal Large Language Models (MLLMs) evolve into sophisticated interactive assistants, their reliability depends not only on following instructi...
arXiv:2608.29301v1 Announce Type: new Abstract: Predicting future organ dysfunction in Intensive Care Unit (ICU) patients is critical for early clinical intervention, yet existing machine learning ap...
arXiv:2608.29589v1 Announce Type: new Abstract: Text-to-image (T2I) safety guardrails fail to generalize equitably to non-standard dialects. Evaluating 23,080 paired prompts across five English diale...
arXiv:2608.29880v1 Announce Type: new Abstract: Open-world geo-localization requires models to reason over ambiguous visual cues through multi-step reasoning and external knowledge grounding. While r...
arXiv:2608.30025v1 Announce Type: new Abstract: Large language models (LLMs) frequently generate source code containing vulnerabilities, yet little work studies the internal mechanisms that distingui...
arXiv:2608.30050v1 Announce Type: new Abstract: Building a blockchain digital twin largely requires translating domain knowledge and specific system descriptions into a simulator architecture, calibr...
arXiv:2608.30226v1 Announce Type: new Abstract: Modular compression has enabled considerable parameter reduction in LLMs while preserving strong language understanding and downstream task accuracy. H...
arXiv:2608.30429v1 Announce Type: new Abstract: LLM-based agent systems increasingly adopt skill-based architectures to reduce repetitive reasoning costs and improve stable, efficient task execution....
arXiv:2608.30676v1 Announce Type: new Abstract: When medical AI systems hallucinate clinical reasoning, the consequences extend beyond incorrect answers: fabricated justifications that superficially...
arXiv:2608.30846v1 Announce Type: new Abstract: Fairness audits in clinical Artificial Intelligence convert continuous fairness metrics into binary pass-or-fail verdicts against operational threshold...
arXiv:2608.31137v1 Announce Type: new Abstract: Ontology alignment (OA) has evolved through several methodological paradigms, ranging from lexical and structural aligners to knowledge graph embedding...
arXiv:2608.28691v1 Announce Type: cross Abstract: Wearable VLM pipelines promise continuous multimodal assistance from egocentric visual capture: a user asks a task-driven question about the surround...
arXiv:2608.29096v1 Announce Type: cross Abstract: The ongoing changes in software engineering requirements have created a substantial need for automated tools which can create secure source code from...
arXiv:2608.29307v1 Announce Type: cross Abstract: Language models increasingly answer questions by consulting retrieved documents rather than memory alone, a design now common in search assistants an...