Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2602. 19327v3 Announce Type: replace Abstract: A significant portion of recent research on Large Language Model (LLM) alignment focuses on developing new policy optimization methods based on Group Relative Policy Optimization (GRPO).
arXiv:2606. 05435v1 Announce Type: new Abstract: Differentially private stochastic gradient descent (DP-SGD) has become the standard framework for privacy-preserving machine learning, yet its reliance on a fixed gradient clipping threshold to limit sensitivity remains a significant practical limitation.
arXiv:2606. 05559v1 Announce Type: new Abstract: Deployed large language model agents must adapt to distribution shift in dynamic environments.
arXiv:2510. 04500v3 Announce Type: replace Abstract: This work demonstrates how increasing the number of neurons in a network without increasing its total number of non-zero parameters improves performance.
arXiv:2506. 19260v2 Announce Type: replace-cross Abstract: Federated learning transmits only model updates to protect client data, and differentially private SGD (DP-SGD) bounds content-level leakage through those updates.
arXiv:2602. 01607v3 Announce Type: replace-cross Abstract: Differentially private synthetic data enables the sharing and analysis of sensitive datasets while providing rigorous privacy guarantees for individual contributors.
arXiv:2606. 05781v1 Announce Type: new Abstract: Deploying frontier large language models (LLMs) for domain-specific structured evaluation tasks often incurs substantial latency, cost, and data privacy overhead.
arXiv:2511. 21338v2 Announce Type: replace Abstract: Masked Diffusion Language Models (MDLMs) have recently emerged as a promising alternative to Autoregressive Language Models (ARLMs), leveraging a denoising objective that, in principle, should enable more uniform context utilisation.
arXiv:2606. 06333v1 Announce Type: new Abstract: Sparse Autoencoders (SAEs) are widely used for mechanistic interpretability in large language models, yet their formulation assigns each latent feature a single decoder direction, implicitly assuming features to be one-dimensional.
arXiv:2605. 10807v4 Announce Type: replace-cross Abstract: The integration of Large Language Models (LLMs) into Electronic Design Automation (EDA) and hardware security is rapidly reshaping the semiconductor industry.
A long-standing finding in the causal learning literature is that adults struggle to identify conjunctive causal rules, where an effect requires the simultaneous presence of multiple causes, while performing better in disjunctive settings. However, most demonstrations of this ``conjunctive handicap'' rely on passive observation paradigms with limited evidence, where learners have no control over evidence generation.
Modelling individual decision-making during infectious disease outbreaks is crucial for understanding behavioural dynamics and informing effective public health interventions. Prior work has shown that large language models can simulate realistic human behaviour by generating agent decisions based on demographic prompts and situational context.
Language-model agents act through repeated cycles of observation, reasoning, and action selection, making safety monitoring depend on both internal model state and environment context. We study reward-hacking monitors in ReAct-style agents acting in Gameable ALFWorld and WebShop.
We introduce pVR, a topological machine learning framework for alignment-free genomic sequence classification that combines $p$-adic numbers with topological data analysis. Each DNA sequence is encoded along two complementary axes: a $p$-adic distance on $k$-mer prefixes, which captures hierarchical positional structure, and a compositional $L_1$ distance on $k$-mer frequencies, which captures local sequence content.
Despite generating increasingly photorealistic images, text-to-image (T2I) models still exhibit localized, subtle, and structurally complex failures. Diagnosing these failures requires instance-level feedback that answers where a defect occurs, what type it is, why it is defective, and its importance to overall image quality.
Whether Large Language Models (LLMs) exhibit covert psychological manipulation in complex human-AI interactions has garnered increasing safety concerns. However, existing AI safety benchmarks remain largely restricted to explicit rule compliance and static prompts, failing to capture the dynamic and covert nature of manipulative strategies in multi-turn dialogues.
In this work, we propose an agentic gamification framework for hazard-informed learning of robot safety policies through synthetic scenarios. We model scenario generation as an adversarial game between two agents: a Red Team that explores the space of potential failures by constructing hazardous situations, and a Blue Team that incrementally refines safety policies to prevent them.
We investigate the extent to which the language processing of LLMs resembles human cognitive processes, focusing on a human cognitive bias called the $\textit{neglect-zero effect}$. This effect refers to the human tendency to ignore $\textit{zero-models}$, which are configurations that render a proposition vacuously true by virtue of an empty set.
Metasurfaces enable precise manipulation of electromagnetic waves for applications such as beam steering, sensing, and stealth technology. However, inverse design of metasurfaces with targeted EM responses remains challenging due to the computational expense of iterative full wave simulation driven optimization and the limited conditioning fidelity and diversity of existing generative approaches.