arXiv AI
Jun 9
Emergent alignment and the projectability of ethical personas
arXiv:2606. 09475v1 Announce Type: new Abstract: Work on `emergent misalignment' shows that finetuning LLMs on narrow tasks can induce broadly misaligned behavior.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv Machine Learning
Jun 9
Generalizing Fair Top-$k$ Selection: An Integrative Approach
arXiv:2603. 04689v3 Announce Type: replace-cross Abstract: Fair top-$k$ selection, which ensures appropriate proportional representation of members from minority or historically disadvantaged groups among the top-$k$ selected candidates, has drawn significant attention.
arXiv Machine Learning
Jun 9
Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior
arXiv:2606. 08454v1 Announce Type: new Abstract: Activation steering provides a lightweight inference-time mechanism for controlling large language models (LLMs) by modifying their internal activation vectors toward desired behaviors.
arXiv Machine Learning
Jun 9
Beyond Homophily: Towards Generalized Graph Reconstruction Attack and Defense
arXiv:2606. 08067v1 Announce Type: new Abstract: Graph neural networks (GNNs) are widely deployed on relational data, yet they can leak sensitive or proprietary information about the training graph adjacency, e.
arXiv AI
Jun 9
A Comparative Study of Student Perspectives on Technical Writing Feedback Quality: Evaluating LLMs, SLMs, and Humans in Computer Science Topics
arXiv:2601. 11541v2 Announce Type: replace-cross Abstract: To address the scalability of feedback in computer science while mitigating the privacy and cost limitations of commercial Large Language Models (LLMs), this study evaluates a locally hosted Small Language Model (SLM).
arXiv AI
Jun 9
Constrained Paraphrase Consistency for LLM Hallucination Detection
arXiv:2606. 08158v1 Announce Type: cross Abstract: Large language models (LLMs) can generate factually inconsistent claims, motivating accurate and scalable hallucination detectors.
arXiv AI
Jun 9
Vision Language Model Helps Private Information De-Identification in Vision Data
arXiv:2606. 09132v1 Announce Type: new Abstract: Visual Language Models (VLMs) have gained significant popularity due to their remarkable ability.
arXiv AI
Jun 9
Hybrid E-Assessment in Higher Education: Semi-Automated Grading of Paper-Based Written Examinations
arXiv:2606. 08855v1 Announce Type: new Abstract: This paper examines the limitations of fully digital and partially digital e-assessment approaches in summative examinations in higher education.
arXiv Machine Learning
Jun 9
Information-Theoretic Requirements for Gradient-Based Task Affinity Estimation in Multi-Task Learning
arXiv:2604. 07848v2 Announce Type: replace Abstract: Multi-task learning shows strikingly inconsistent results -- sometimes joint training helps substantially, sometimes it actively harms performance -- yet the field lacks a principled framework for predicting these outcomes.
arXiv AI
Jun 9
Hybrid Robustness Verification for Spatio-Temporal Neural Networks
arXiv:2606. 09746v1 Announce Type: cross Abstract: With AI increasingly deployed in safety-critical systems, providing formal robustness guarantees for the underlying models is essential.
arXiv AI
Jun 9
Revisiting the shutdown problem
arXiv:2606. 08296v1 Announce Type: new Abstract: A key premise in leading arguments for existential risk from artificial intelligence is that malfunctioning artificial agents could not be easily shut down.
arXiv AI
Jun 9
Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO
arXiv:2606. 09701v1 Announce Type: cross Abstract: AI red teaming must continually adapt to evolving attackers and defenders.
arXiv AI
Jun 9
Single-Cell Cross-Modal Transfer by Adversarial Fine-Tuning of Foundation Models
arXiv:2606. 07676v1 Announce Type: cross Abstract: Spatial transcriptomics (ST) is a powerful tool for exploring biological properties dependent on structure, proximity, and interaction in tissue.
arXiv AI
Jun 9
Scaling Neural Network Verification with Tensor Parallelism and Fully Sharded Data Parallelism
arXiv:2606. 09377v1 Announce Type: cross Abstract: Formal neural network verification -- proving that a network satisfies safety properties for \emph{all} inputs in a specified domain -- is bounded in practice by GPU memory: standard implementations of bound-propagation algorithms (IBP, CROWN, $\alpha$-CROWN) require weight and relaxation-coefficient matrices to reside entirely on one accelerator.
arXiv Machine Learning
Jun 9
Privacy-Enhanced Zero-Order Federated Learning via xMK-CKKS over Wireless Channels
arXiv:2605. 30123v2 Announce Type: replace-cross Abstract: Homomorphic encryption (HE) enables privacy-preserving aggregation in federated learning (FL) by allowing the server to operate on encrypted data without decryption.
arXiv Machine Learning
Jun 9
SwAIther-Precip: Lead-Time-Aware Bias Correction Enables Kilometer-Scale Downscaling of Global AI Precipitation Forecasts over Switzerland
arXiv:2605. 16163v2 Announce Type: replace-cross Abstract: Skillful medium-range precipitation forecasting at kilometer scale remains challenging over complex terrain because precipitation arises from multiscale nonlinear processes that global models cannot explicitly resolve at affordable cost.
arXiv Machine Learning
Jun 9
Robust Koopman Control Barrier Filters for Safe Actor-Critic Reinforcement Learning
arXiv:2605. 26452v2 Announce Type: replace-cross Abstract: Safe reinforcement learning (RL) for robotic systems requires policies that improve task performance while satisfying state and input constraints during both training and deployment.
arXiv AI
Jun 9
PathoSage: Towards Multi-Source Evidence Adjudication in Pathology via Experience-Aware Agentic Workflow
arXiv:2606. 07549v1 Announce Type: new Abstract: Recent advances in Multimodal Large Language Models (MLLMs) and agent workflows have shown strong promise for computational pathology, yet reliable patch-level reasoning remains challenging.
arXiv Machine Learning
Jun 9
Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregation
arXiv:2604. 07125v2 Announce Type: replace-cross Abstract: This article presents DDP-SA, a scalable privacy-preserving federated learning framework that jointly leverages client-side local differential privacy (LDP) and full-threshold additive secret sharing (ASS) for secure aggregation.
arXiv Machine Learning
Jun 9
Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents
arXiv:2602. 16346v4 Announce Type: replace-cross Abstract: LLM-based agents execute real-world workflows via tools and memory.