arXiv:2509.04192v2 Announce Type: replace Abstract: A Markov logic network (MLN) $mathbbM$ determines a probability distribution $mathbbP_n^mathbbM$ on the set $mathbfW_n$ of structures, or “possible worlds”, with domain $1, ldots, n$. We study the properties of such distributions as $n$ tends to infinity. We show that with mild assumptions on an MLN $mathbbM$ with one soft […]
Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models
arXiv:2605.27997v1 Announce Type: cross Abstract: Large language models frequently generate toxic, hateful, or harmful content, yet existing mitigation methods rely on costly retraining or output-level filtering with no mechanistic insight into where toxicity originates internally. We introduce Meow2X and TRNE, two complementary retraining-free frameworks that localize toxicity to specific layers and neurons by analyzing activation […]
SmartIterator: Visual Analytics Workflows for Supervising Unsupervised Data Grouping
arXiv:2605.28219v1 Announce Type: cross Abstract: Unsupervised learning methods — topic modeling, partition-based and density-based clustering — produce data groupings without human guidance, yet choosing and evaluating those groupings should not itself be unsupervised. We present emphSmartIterator~(SI), a visual analytics approach that treats the full sequence of grouping results across a parameter sweep as a first-class […]
Asking Is Not Enough: Protocol Sensitivity in LLM Confidence Calibration
arXiv:2605.27752v1 Announce Type: new Abstract: LLM confidence calibration is often evaluated by comparing two signals: token-probability scores and verbalized confidence. These signals are sometimes treated as direct readouts of model uncertainty, but their comparison depends on measurement choices that are rarely made explicit. In the main analysis, we hold the verbalized-confidence elicitation fixed: a single […]
Planning a Community Approach to Diabetes Care in Low- and Middle-Income Countries Using Optimization
arXiv:2305.06426v2 Announce Type: replace Abstract: Diabetes is a global health priority, especially in low- and-middle-income countries, where over 50% of premature deaths are attributed to high blood glucose. Community Health Worker (CHW) programs can provide affordable and culturally tailored solutions for early detection and management of diabetes. We introduce an optimization framework to determine personalized […]
Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit Compression
arXiv:2605.28567v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have become a central tool for interpreting language models. However, two key SAE analyses that remain difficult to scale are (1) matching semantically similar features across multi-layers and (2) compressing large feature circuits into interpretable supernodes. Although these have been treated as separate problems, we show that […]
DIG to Heal: Scaling General-purpose Agent Collaboration via Explainable Dynamic Decision Paths
arXiv:2603.00309v2 Announce Type: replace Abstract: The increasingly popular agentic AI paradigm promises to harness the power of multiple, general-purpose large language model (LLM) agents to collaboratively complete complex tasks. While many agentic AI systems reduce complexity through predefined workflows or fixed agent roles, the ideal is to support truly autonomous agents capable of emergent collaboration […]
Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring
arXiv:2502.05242v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are becoming increasingly capable, but the mechanisms of their thinking and decision-making processes remain unclear. Chain-of-thoughts (CoTs) have been commonly utilized to externalize LLMs’ thinking, but this strategy fails to accurately reflect LLMs’ thinking process. Techniques based on LLMs’ hidden representations provide an inner perspective to […]
UniMaia: Steering Chess Policies with Language for Human-like Play
arXiv:2605.27767v1 Announce Type: cross Abstract: Recent advances in large language models have enabled natural language to serve as a flexible interface for controlling complex systems, but often at the cost of large-scale multimodal training or weakened domain-specific inductive biases. In structured decision-making domains such as chess, specialized policy networks achieve strong performance but lack semantic […]
VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild
arXiv:2605.27882v1 Announce Type: cross Abstract: LLM-based agents score well on search benchmarks, yet real users consistently find results unsatisfying, revealing a persistent evaluation-experience gap. We attribute this gap to existing benchmarks’ reliance on over-specified queries, single-turn interactions, and fixed-schema evaluation, none of which reflect real search behavior where users and agents collaboratively refine vague intent […]
Misalignment Between Backpropagation and the Hierarchy of Brain Responses to Images
arXiv:2605.28693v1 Announce Type: new Abstract: Backpropagation is the core learning mechanism underlying deep learning. However, whether and how this algorithm is implemented in the brain remains highly debated. In particular, while forward activations of pretrained models reliably map onto the cortical hierarchy of visual processing, it is unknown whether backpropagated gradients exhibit a similar correspondence. […]
Informing AI Policy Assessment using Large-Scale Simulation of Interventions
arXiv:2605.27395v1 Announce Type: cross Abstract: As the rapid proliferation of AI systems and harms spurs efforts in AI governance around the world, prioritizing among competing policy options has become increasingly challenging for policymakers and researchers. We introduce a methodology for identifying viable policy options to mitigate specified AI harms, helping policymakers and researchers target areas […]