ASDA: Automated Skill Distillation and Adaptation for Financial Reasoning
arXiv:2603.16112v1 Announce Type: new Abstract: Adapting large language models (LLMs) to specialized financial reasoning typically requires expensive fine-tuning that produces model-locked expertise. Training-free alternatives have emerged, yet our experiments show that leading methods (GEPA and ACE) achieve only marginal gains...
More Rounds, More Noise: Why Multi-Turn Review Fails to Improve Cross-Context Verification
arXiv:2603.16244v1 Announce Type: new Abstract: Cross-Context Review (CCR) improves LLM verification by separating production and review into independent sessions. A natural extension is multi-turn review: letting the reviewer ask follow-up questions, receive author responses, and review again. We call this...
Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing
arXiv:2603.15647v1 Announce Type: new Abstract: Large language models (LLMs) are typically governed by post-training alignment (e.g., RLHF or DPO), which yields a largely static policy during deployment and inference. However, real-world safety is a full-lifecycle problem: static defenses degrade against...
How to Achieve Prototypical Birth and Death for OOD Detection?
arXiv:2603.15650v1 Announce Type: new Abstract: Out-of-Distribution (OOD) detection is crucial for the secure deployment of machine learning models, and prototype-based learning methods are among the mainstream strategies for achieving OOD detection. Existing prototype-based learning methods generally rely on a fixed...
Evidential Domain Adaptation for Remaining Useful Life Prediction with Incomplete Degradation
arXiv:2603.15687v1 Announce Type: new Abstract: Accurate Remaining Useful Life (RUL) prediction without labeled target domain data is a critical challenge, and domain adaptation (DA) has been widely adopted to address it by transferring knowledge from a labeled source domain to...
Residual Stream Duality in Modern Transformer Architectures
arXiv:2603.16039v1 Announce Type: new Abstract: Recent work has made clear that the residual pathway is not mere optimization plumbing; it is part of the model's representational machinery. We agree, but argue that the cleanest way to organize this design space...
Adaptive regularization parameter selection for high-dimensional inverse problems: A Bayesian approach with Tucker low-rank constraints
arXiv:2603.16066v1 Announce Type: new Abstract: This paper introduces a novel variational Bayesian method that integrates Tucker decomposition for efficient high-dimensional inverse problem solving. The method reduces computational complexity by transforming variational inference from a high-dimensional space to a lower-dimensional core...
The Supreme Court of Canada
Welcome to SCOTUSblog’s recurring series in which we interview experts on different supreme courts around the world and how they compare to our own. For our debut column, we covered […]The postThe Supreme Court of Canadaappeared first onSCOTUSblog.
The biggest names on the briefs
Empirical SCOTUS is a recurring series by Adam Feldman that looks at Supreme Court data, primarily in the form of opinions and oral arguments, to provide insights into the justices’ decision making and […]The postThe biggest names on the briefsappeared...
Benchmarking Large Language Models on Reference Extraction and Parsing in the Social Sciences and Humanities
arXiv:2603.13651v1 Announce Type: new Abstract: Bibliographic reference extraction and parsing are foundational for citation indexing, linking, and downstream scholarly knowledge-graph construction. However, most established evaluations focus on clean, English, end-of-document bibliographies, and therefore underrepresent the Social Sciences and Humanities (SSH),...
StatePlane: A Cognitive State Plane for Long-Horizon AI Systems Under Bounded Context
arXiv:2603.13644v1 Announce Type: new Abstract: Large language models (LLMs) and small language models (SLMs) operate under strict context window and key-value (KV) cache constraints, fundamentally limiting their ability to reason coherently over long interaction horizons. Existing approaches -- extended context...
Why Grokking Takes So Long: A First-Principles Theory of Representational Phase Transitions
arXiv:2603.13331v1 Announce Type: new Abstract: Grokking is the sudden generalization that appears long after a model has perfectly memorized its training data. Although this phenomenon has been widely observed, there is still no quantitative theory explaining the length of the...
GroupGuard: A Framework for Modeling and Defending Collusive Attacks in Multi-Agent Systems
arXiv:2603.13940v1 Announce Type: new Abstract: While large language model-based agents demonstrate great potential in collaborative tasks, their interactivity also introduces security vulnerabilities. In this paper, we propose and model group collusive attacks, a highly destructive threat in which multiple agents...
Automating Document Intelligence in Statutory City Planning
arXiv:2603.13245v1 Announce Type: new Abstract: UK planning authorities face a legislative conflict between the Planning Act, which mandates public access to application documents, and the Data Protection Act, which requires protection of personal information. This situation creates a manually intensive...
The AI Fiction Paradox
arXiv:2603.13545v1 Announce Type: new Abstract: AI development has a fiction dependency problem: models are built on massive corpora of modern fiction and desperately need more of it, yet they struggle to generate it. I term this the AI-Fiction Paradox and...
When Alpha Breaks: Two-Level Uncertainty for Safe Deployment of Cross-Sectional Stock Rankers
arXiv:2603.13252v1 Announce Type: new Abstract: Cross-sectional ranking models are often deployed as if point predictions were sufficient: the model outputs scores and the portfolio follows the induced ordering. Under non-stationarity, rankers can fail during regime shifts. In the AI Stock...
TheraAgent: Multi-Agent Framework with Self-Evolving Memory and Evidence-Calibrated Reasoning for PET Theranostics
arXiv:2603.13676v1 Announce Type: new Abstract: PET theranostics is transforming precision oncology, yet treatment response varies substantially; many patients receiving 177Lu-PSMA radioligand therapy (RLT) for metastatic castration-resistant prostate cancer (mCRPC) fail to respond, demanding reliable pre-therapy prediction. While LLM-based agents have...
Multi-Axis Trust Modeling for Interpretable Account Hijacking Detection
arXiv:2603.13246v1 Announce Type: new Abstract: This paper proposes a Hadith-inspired multi-axis trust modeling framework, motivated by a structurally analogous problem in classical Hadith scholarship: assessing the trustworthiness of information sources using interpretable, multidimensional criteria rather than a single anomaly score....
ICPRL: Acquiring Physical Intuition from Interactive Control
arXiv:2603.13295v1 Announce Type: new Abstract: VLMs excel at static perception but falter in interactive reasoning in dynamic physical environments, which demands planning and adaptation to dynamic outcomes. Existing physical reasoning methods often depend on abstract symbolic inputs or lack the...
RBF-Solver: A Multistep Sampler for Diffusion Probabilistic Models via Radial Basis Functions
arXiv:2603.13330v1 Announce Type: new Abstract: Diffusion probabilistic models (DPMs) are widely adopted for their outstanding generative fidelity, yet their sampling is computationally demanding. Polynomial-based multistep samplers mitigate this cost by accelerating inference; however, despite their theoretical accuracy guarantees, they generate...
Lipschitz-Based Robustness Certification Under Floating-Point Execution
arXiv:2603.13334v1 Announce Type: new Abstract: Sensitivity-based robustness certification has emerged as a practical approach for certifying neural network robustness, including in settings that require verifiable guarantees. A key advantage of these methods is that certification is performed by concrete numerical...
CSE-UOI at SemEval-2026 Task 6: A Two-Stage Heterogeneous Ensemble with Deliberative Complexity Gating for Political Evasion Detection
arXiv:2603.12453v1 Announce Type: new Abstract: This paper describes our system for SemEval-2026 Task 6, which classifies clarity of responses in political interviews into three categories: Clear Reply, Ambivalent, and Clear Non-Reply. We propose a heterogeneous dual large language model (LLM)...
NeuroLoRA: Context-Aware Neuromodulation for Parameter-Efficient Multi-Task Adaptation
arXiv:2603.12378v1 Announce Type: cross Abstract: Parameter-Efficient Fine-Tuning (PEFT) techniques, particularly Low-Rank Adaptation (LoRA), have become essential for adapting Large Language Models (LLMs) to downstream tasks. While the recent FlyLoRA framework successfully leverages bio-inspired sparse random projections to mitigate parameter interference,...
Adaptive Conditional Forest Sampling for Spectral Risk Optimisation under Decision-Dependent Uncertainty
arXiv:2603.12507v1 Announce Type: new Abstract: Minimising a spectral risk objective, defined as a convex combination of expected cost and Conditional Value-at-Risk (CVaR), is challenging when the uncertainty distribution is decision-dependent, making both surrogate modelling and simulation-based ranking sensitive to tail...
Does legislative history have a judicial future?
Major Questions is a recurring series by Adam White, which analyzes the court’s approach to administrative law, agencies, and the lower courts. Does legislative history have a future in judicial […]The postDoes legislative history have a judicial future?appeared first onSCOTUSblog.
Training Is Everything: Artificial Intelligence, Copyright, and Fair Training
To learn how to behave, the current revolutionary generation of AIs must be trained on vast quantities of published images, written works, and sounds, many of which fall within the core subject matter of copyright law. To some, the use...
AI Knows What's Wrong But Cannot Fix It: Helicoid Dynamics in Frontier LLMs Under High-Stakes Decisions
arXiv:2603.11559v1 Announce Type: new Abstract: Large language models perform reliably when their outputs can be checked: solving equations, writing code, retrieving facts. They perform differently when checking is impossible, as when a clinician chooses an irreversible treatment on incomplete data,...
When OpenClaw Meets Hospital: Toward an Agentic Operating System for Dynamic Clinical Workflows
arXiv:2603.11721v1 Announce Type: new Abstract: Large language model (LLM) agents extend conventional generative models by integrating reasoning, tool invocation, and persistent memory. Recent studies suggest that such agents may significantly improve clinical workflows by automating documentation, coordinating care processes, and...
GPT4o-Receipt: A Dataset and Human Study for AI-Generated Document Forensics
arXiv:2603.11442v1 Announce Type: new Abstract: Can humans detect AI-generated financial documents better than machines? We present GPT4o-Receipt, a benchmark of 1,235 receipt images pairing GPT-4o-generated receipts with authentic ones from established datasets, evaluated by five state-of-the-art multimodal LLMs and a...
Legal-DC: Benchmarking Retrieval-Augmented Generation for Legal Documents
arXiv:2603.11772v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has emerged as a promising technology for legal document consultation, yet its application in Chinese legal scenarios faces two key limitations: existing benchmarks lack specialized support for joint retriever-generator evaluation, and mainstream...