Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 00605v1 Announce Type: new Abstract: Transformers have achieved remarkable success across a wide range of applications, and a growing body of work suggests that part of their strength comes from their ability to learn and execute algorithmic procedures.
arXiv:2606. 01159v1 Announce Type: new Abstract: We study two-player zero-sum games (TPZSGs) with bandit feedback under fairness constraints requiring every action to be played with probability at least $\alpha/m$.
arXiv:2606. 00039v1 Announce Type: cross Abstract: Text-to-Image (T2I) models have shown promising utility across various domains.
arXiv:2606. 01890v1 Announce Type: new Abstract: Real-world domains often contain heterogeneous tables whose headers vary while their underlying attribute semantics are shared, making it difficult to induce domain-specialized semantics from table-local evidence alone.
arXiv:2606. 01695v1 Announce Type: new Abstract: Adversaries can implant latent harmful behavior by poisoning as few as 1% of fine-tuning examples.
arXiv:2606. 02267v1 Announce Type: new Abstract: The vulnerability of deep neural networks to adversarial examples poses a significant challenge for real-world deployment.
arXiv:2606. 01243v1 Announce Type: cross Abstract: Latent reasoning enables Large Language Models (LLMs) to perform multi-step inference within continuous hidden states, offering efficiency gains over explicit Chain-of-Thought (CoT).
arXiv:2605. 29107v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly rank products, documents, and recommendations for user queries, which makes manipulating these rankings a growing concern for fairness and information integrity.
arXiv:2606. 00801v1 Announce Type: cross Abstract: Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not scale, LLM-as-attacker methods exhibit mode collapse, and gradient-based approaches produce uninterpretable gibberish.
arXiv:2605. 23995v2 Announce Type: replace-cross Abstract: Self-supervised learning (SSL) has emerged as a promising paradigm for addressing the annotation bottleneck in medical imaging by learning representations from unlabeled data.
arXiv:2606. 01691v1 Announce Type: cross Abstract: Industrial Internet systems face increasing threats from sophisticated industrial control system (ICS) attacks, resulting in critical safety incidents.
arXiv:2605. 28850v2 Announce Type: replace Abstract: We study behavioral alignment and representation dynamics of large language model (LLM) agents in financial decision environments.
arXiv:2604. 10169v2 Announce Type: replace Abstract: Trajectory prediction is a key component of autonomous driving systems because future motions directly affect collision checking, behavior planning, and control.
arXiv:2606. 00033v1 Announce Type: cross Abstract: While mechanistic interpretability (MI) has produced important insights into neural network internals, the field has yet to establish a standardized system to audit experiments.
arXiv:2604. 01802v2 Announce Type: replace Abstract: Real-time inference of inaccessible interior physical fields from sparse boundary observations is a fundamental but unresolved problem in scientific machine learning, with direct relevance to safety-critical monitoring across many engineering applications.
arXiv:2606. 00027v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed across healthcare, yet existing benchmarks fail to capture model behavior under adversarial or ethically complex conditions common in clinical practice.
arXiv:2505. 17630v4 Announce Type: replace-cross Abstract: Circuit localization methods aim to identify the subset of model components responsible for specific behaviors in large language models, enabling detailed mechanistic analysis.
arXiv:2412. 03771v3 Announce Type: replace-cross Abstract: Zero-shot learning enables models to generalise to unseen classes by leveraging semantic information, bridging the gap between training and testing sets with non-overlapping classes.
arXiv:2605. 24583v3 Announce Type: replace Abstract: Comparing a model's internal activations before and after alignment is a natural way to ask what safety training changes: one forms the matrix of paired aligned-minus-base activations on safety-relevant inputs and reads off its effective rank or top direction.
arXiv:2606. 00020v1 Announce Type: cross Abstract: Large Language Model (LLM) based Chinese Grammatical Error Correction (CGEC) systems face two critical challenges: general-purpose models lack specialized linguistic priors for subtle grammatical distinctions, and Supervised Fine-Tuning (SFT) with Maximum Likelihood Estimation fails to optimize for precision-focused metrics, leading to systematic over-correction.