Verbalizing LLM's Higher-order Uncertainty via Imprecise Probabilities
arXiv:2603.10396v1 Announce Type: new Abstract: Despite the growing demand for eliciting uncertainty from large language models (LLMs), empirical evidence suggests that LLM behavior is not always adequately captured by the elicitation techniques developed under the classical probabilistic uncertainty framework. This...
DeliberationBench: A Normative Benchmark for the Influence of Large Language Models on Users' Views
arXiv:2603.10018v1 Announce Type: cross Abstract: As large language models (LLMs) become pervasive as assistants and thought partners, it is important to characterize their persuasive influence on users' beliefs. However, a central challenge is to distinguish "beneficial" from "harmful" forms of...
Quantifying Hallucinations in Language Language Models on Medical Textbooks
arXiv:2603.09986v1 Announce Type: cross Abstract: Hallucinations, the tendency for large language models to provide responses with factually incorrect and unsupported claims, is a serious problem within natural language processing for which we do not yet have an effective solution to...
A Hybrid Knowledge-Grounded Framework for Safety and Traceability in Prescription Verification
arXiv:2603.10891v1 Announce Type: new Abstract: Medication errors pose a significant threat to patient safety, making pharmacist verification (PV) a critical, yet heavily burdened, final safeguard. The direct application of Large Language Models (LLMs) to this zero-tolerance domain is untenable due...
Assessing Cognitive Biases in LLMs for Judicial Decision Support: Virtuous Victim and Halo Effects
arXiv:2603.10016v1 Announce Type: cross Abstract: We investigate whether large language models (LLMs) display human-like cognitive biases, focusing on potential implications for assistance in judicial sentencing, a decision-making system where fairness is paramount. Two of the most relevant biases were chosen:...
The Dunning-Kruger Effect in Large Language Models: An Empirical Study of Confidence Calibration
arXiv:2603.09985v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, yet their ability to accurately assess their own confidence remains poorly understood. We present an empirical study investigating whether LLMs exhibit patterns reminiscent of...
AraModernBERT: Transtokenized Initialization and Long-Context Encoder Modeling for Arabic
arXiv:2603.09982v1 Announce Type: cross Abstract: Encoder-only transformer models remain widely used for discriminative NLP tasks, yet recent architectural advances have largely focused on English. In this work, we present AraModernBERT, an adaptation of the ModernBERT encoder architecture to Arabic, and...
A Retrieval-Augmented Language Assistant for Unmanned Aircraft Safety Assessment and Regulatory Compliance
arXiv:2603.09999v1 Announce Type: cross Abstract: This paper presents the design and validation of a retrieval-based assistant that supports safety assessment, certification activities, and regulatory compliance for unmanned aircraft systems. The work is motivated by the growing complexity of drone operations...
Fine-Tune, Don't Prompt, Your Language Model to Identify Biased Language in Clinical Notes
arXiv:2603.10004v1 Announce Type: new Abstract: Clinical documentation can contain emotionally charged language with stigmatizing or privileging valences. We present a framework for detecting and classifying such language as stigmatizing, privileging, or neutral. We constructed a curated lexicon of biased terms...
The Prediction-Measurement Gap: Toward Meaning Representations as Scientific Instruments
arXiv:2603.10130v1 Announce Type: new Abstract: Text embeddings have become central to computational social science and psychology, enabling scalable measurement of meaning and mixed-method inference. Yet most representation learning is optimized and evaluated for prediction and retrieval, yielding a prediction-measurement gap:...
Reason and Verify: A Framework for Faithful Retrieval-Augmented Generation
arXiv:2603.10143v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) significantly improves the factuality of Large Language Models (LLMs), yet standard pipelines often lack mechanisms to verify inter- mediate reasoning, leaving them vulnerable to hallucinations in high-stakes domains. To address this, we...
Sabi\'a-4 Technical Report
arXiv:2603.10213v1 Announce Type: new Abstract: This technical report presents Sabi\'a-4 and Sabiazinho-4, a new generation of Portuguese language models with a focus on Brazilian Portuguese language. The models were developed through a four-stage training pipeline: continued pre-training on Portuguese and...
S-GRADES -- Studying Generalization of Student Response Assessments in Diverse Evaluative Settings
arXiv:2603.10233v1 Announce Type: new Abstract: Evaluating student responses, from long essays to short factual answers, is a key challenge in educational NLP. Automated Essay Scoring (AES) focuses on holistic writing qualities such as coherence and argumentation, while Automatic Short Answer...
Revisiting Sharpness-Aware Minimization: A More Faithful and Effective Implementation
arXiv:2603.10048v1 Announce Type: new Abstract: Sharpness-Aware Minimization (SAM) enhances generalization by minimizing the maximum training loss within a predefined neighborhood around the parameters. However, its practical implementation approximates this as gradient ascent(s) followed by applying the gradient at the ascent...
KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization
arXiv:2603.10085v1 Announce Type: new Abstract: Improving GPU kernel efficiency is crucial for advancing AI systems. Recent work has explored leveraging large language models (LLMs) for GPU kernel generation and optimization. However, existing LLM-based kernel optimization pipelines typically rely on opaque,...
A Survey of Weight Space Learning: Understanding, Representation, and Generation
arXiv:2603.10090v1 Announce Type: new Abstract: Neural network weights are typically viewed as the end product of training, while most deep learning research focuses on data, features, and architectures. However, recent advances show that the set of all possible weight values...
Discovery of a Hematopoietic Manifold in scGPT Yields a Method for Extracting Performant Algorithms from Biological Foundation Model Internals
arXiv:2603.10261v1 Announce Type: new Abstract: We report the discovery and extraction of a compact hematopoietic algorithm from the single-cell foundation model scGPT, to our knowledge the first biologically useful, competitive algorithm extracted from a foundation model via mechanistic interpretability. We...
Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework
arXiv:2603.10281v1 Announce Type: new Abstract: While score-based generative models have emerged as powerful priors for solving inverse problems, directly integrating them into optimization algorithms such as ADMM remains nontrivial. Two central challenges arise: i) the mismatch between the noisy data...
Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning
arXiv:2603.10377v1 Announce Type: new Abstract: Sparse autoencoders can localize where concepts live in language models, but not how they interact during multi-step reasoning. We propose Causal Concept Graphs (CCG): a directed acyclic graph over sparse, interpretable latent features, where edges...
Graph-GRPO: Training Graph Flow Models with Reinforcement Learning
arXiv:2603.10395v1 Announce Type: new Abstract: Graph generation is a fundamental task with broad applications, such as drug discovery. Recently, discrete flow matching-based graph generation, \aka, graph flow model (GFM), has emerged due to its superior performance and flexible sampling. However,...
Trump administration urges Supreme Court to allow it to revoke protected status for Haitian nationals
The Trump administration on Wednesday asked the Supreme Court to pause a ruling by a federal judge in Washington, D.C., that barred the government from ending a program that allows […]The postTrump administration urges Supreme Court to allow it to...
SCOTUStoday for Wednesday, March 11
You’ve likely heard of AI bots being used improperly by lawyers, but what about lawsuits over AI bots practicing law without a license? Reuters reported on one such case last […]The postSCOTUStoday for Wednesday, March 11appeared first onSCOTUSblog.
Binance sues WSJ, panicked by gov’t probes into sanctioned crypto transfers
Binance’s lawsuit accusing WSJ of defamation unlikely to stall government probes.
Rivian spin-out Mind Robotics raises $500M for industrial AI-powered robots
The startup, which was created by Rivian founder RJ Scaringe, is looking to train on data from, and deploy in, Rivian's factory.
Making the Rules of the Rules of the Game: The Use, Misuse, and Disuse of the Rulemaking Grant in the Act of 1842
Introduction On August 23, 1842, Congress quietly and quickly conferred a broad grant of rulemaking authority on the Supreme Court. The Act of Aug....The postMaking the Rules of the Rules of the Game: The Use, Misuse, and Disuse of the...
Influencing LLM Multi-Agent Dialogue via Policy-Parameterized Prompts
arXiv:2603.09890v1 Announce Type: new Abstract: Large Language Models (LLMs) have emerged as a new paradigm for multi-agent systems. However, existing research on the behaviour of LLM-based multi-agents relies on ad hoc prompts and lacks a principled policy perspective. Different from...
Meissa: Multi-modal Medical Agentic Intelligence
arXiv:2603.09018v1 Announce Type: new Abstract: Multi-modal large language models (MM-LLMs) have shown strong performance in medical image understanding and clinical reasoning. Recent medical agent systems extend them with tool use and multi-agent collaboration, enabling complex decision-making. However, these systems rely...
Logics-Parsing-Omni Technical Report
arXiv:2603.09677v1 Announce Type: new Abstract: Addressing the challenges of fragmented task definitions and the heterogeneity of unstructured data in multimodal parsing, this paper proposes the Omni Parsing framework. This framework establishes a Unified Taxonomy covering documents, images, and audio-visual streams,...
LDP: An Identity-Aware Protocol for Multi-Agent LLM Systems
arXiv:2603.08852v1 Announce Type: new Abstract: As multi-agent AI systems grow in complexity, the protocols connecting them constrain their capabilities. Current protocols such as A2A and MCP do not expose model-level properties as first-class primitives, ignoring properties fundamental to effective delegation:...
Quantifying the Necessity of Chain of Thought through Opaque Serial Depth
arXiv:2603.09786v1 Announce Type: new Abstract: Large language models (LLMs) tend to externalize their reasoning in their chain of thought, making the chain of thought a good target for monitoring. This is partially an inherent feature of the Transformer architecture: sufficiently...