Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 20515v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is critical for aligning Large Language Models (LLMs) with human preferences.
arXiv:2607. 20814v1 Announce Type: new Abstract: The electrocardiogram (ECG) is a cornerstone of cardiac as- sessment, yet clinical deployment of deep learning models remains con- strained by limited interpretability and the hallucination risk of large language models (LLMs).
arXiv:2607. 21412v1 Announce Type: new Abstract: Large Language Models (LLMs) excel at natural language understanding and generation but remain unreliable for multi-step logical reasoning, especially in safety-critical or compliance-sensitive domains.
arXiv:2607. 20492v1 Announce Type: cross Abstract: Language models in production do not write prose.
arXiv:2604. 01925v2 Announce Type: replace-cross Abstract: Large Language Models increasingly suppress biased outputs when demographic identity is stated explicitly, yet may still exhibit implicit biases when identity is conveyed indirectly.
arXiv:2607. 20465v1 Announce Type: new Abstract: The quality of training data fundamentally determines the capabilities of large language models (LLMs), yet no unified benchmark exists to measure how well LLMs, agents, and data-centric workflows actually prepare training data end to end.
arXiv:2607. 20596v1 Announce Type: new Abstract: Sparse autoencoder (SAE) features are used to interpret and steer large language models, yet whether a feature's causal role is stable across SAE families remains untested.
arXiv:2607. 20694v1 Announce Type: new Abstract: Personal and organizational planning systems maintain two records that drift apart: what was planned (a task's effort budget) and what was done (a logged action's duration and description).
arXiv:2603. 13026v2 Announce Type: replace Abstract: Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents.
arXiv:2607. 20485v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable performance on standard benchmarks, yet it remains largely unexplored whether they truly meet user expectations.
arXiv:2607. 20549v1 Announce Type: new Abstract: Trajectory datasets used in ADAS evaluation are heavily biased toward routine driving; genuine vehicle-to-vehicle conflict events are rare, and the rarer the event, the higher the cost when an ADAS system fails to handle it.
arXiv:2607. 20590v1 Announce Type: new Abstract: Neural network misclassifications exhibit characteristic spectral instability in internal activations that is invisible at the output layer.
arXiv:2607. 20700v1 Announce Type: cross Abstract: The operation of blockchain is governed by consensus algorithms (CA).
arXiv:2607. 20820v1 Announce Type: new Abstract: Body-based emotion recognition is important for real-time affective systems, but graph-based skeleton models can be computationally expensive.
arXiv:2607. 20547v1 Announce Type: new Abstract: Safe Advanced Air Mobility operations require aircraft to maintain separation when surveillance information is noisy, delayed, incomplete, or temporarily unavailable.
arXiv:2607. 20641v1 Announce Type: new Abstract: Federated learning (FL) enables multiple clinical institutions to collaboratively train a shared disease classifier without centralizing patient data.
arXiv:2607. 20529v1 Announce Type: cross Abstract: Large Language Model (LLM) ensembles are increasingly used to improve reliability by combining predictions from multiple LLMs.
arXiv:2504. 16318v3 Announce Type: replace Abstract: Cosine similarity is a standard comparison rule for learned representations in information retrieval, natural language processing, computer vision, and multimodal learning.
arXiv:2607. 21550v1 Announce Type: new Abstract: While large audio-language models have achieved remarkable progress in auditory perception, they still lag behind text-based large language models in deep logical reasoning, primarily due to the scarcity of high-quality audio reasoning data.
arXiv:2607. 20447v1 Announce Type: cross Abstract: This paper describes our system for the EEUCA 2026 Shared Task on toxicity classification in gaming chat.