Why Is RLHF Alignment Shallow? A Gradient Analysis
arXiv:2603.04851v1 Announce Type: new Abstract: Why is safety alignment in LLMs shallow? We prove that gradient-based alignment inherently concentrates on positions where harm is decided and vanishes beyond. Using a martingale decomposition of sequence-level harm, we derive an exact characterization...
Differential Privacy in Two-Layer Networks: How DP-SGD Harms Fairness and Robustness
arXiv:2603.04881v1 Announce Type: new Abstract: Differentially private learning is essential for training models on sensitive data, but empirical studies consistently show that it can degrade performance, introduce fairness issues like disparate impact, and reduce adversarial robustness. The theoretical underpinnings of...
EVMbench: Evaluating AI Agents on Smart Contract Security
arXiv:2603.04915v1 Announce Type: new Abstract: Smart contracts on public blockchains now manage large amounts of value, and vulnerabilities in these systems can lead to substantial losses. As AI agents become more capable at reading, writing, and running code, it is...
Immigration Enforcement and Constraints on Information Commandeering
The debate over American immigration policy reflects deep moral divides over the meaning of American identity and the scope of fundamental individual rights like due process and the freedom of movement. Although the modern American immigration system no longer includes...
The Untold Story of the Proto-Smith Era: Justice O’Connor’s Papers and the Court’s Free Exercise Revolution
Justice O’Connor’s recently released Supreme Court papers reveal the untold story of how the Court systematically dismantled religious accommodation protections in the decade leading up to Employment Division v. Smith. While Smith’s abandonment of strict scrutiny for neutral, generally applicable...
Birthright citizenship: the exceptions provide the rule
The battle over birthright citizenship is a battle over its exceptions. The 14th Amendment’s first sentence proudly proclaims that “[a]ll persons born . . . in the United States, and subject to the jurisdiction […]The postBirthright citizenship: the exceptions provide...
Anthropic’s Pentagon deal is a cautionary tale for startups chasing federal contracts
The Pentagon has officially designated Anthropic a supply-chain risk after the two failed to agree on how much control the military should have over its AI models, including its use in autonomous weapons and mass domestic surveillance. As Anthropic’s $200...
Anthropic vs. the Pentagon, the SaaSpocalypse, and why competitions is good, actually
The Pentagon has officially designated Anthropic a supply-chain risk after the two failed to agree on how much control the military should have over its AI models, including its use in autonomous weapons and mass domestic surveillance. As Anthropic’s $200...
DiligenceSquared uses AI, voice agents to make M&A research affordable
Instead of relying on expensive management consultants, the startup uses AI voice agents to conduct interviews with customers of the companies the PE firms are considering buying.
From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG
arXiv:2603.03292v1 Announce Type: cross Abstract: Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering, but their tendency to produce hallucinations and outdated knowledge poses critical risks in healthcare fields. While Retrieval-Augmented Generation (RAG) mitigates these issues, existing methods...
TTSR: Test-Time Self-Reflection for Continual Reasoning Improvement
arXiv:2603.03297v1 Announce Type: cross Abstract: Test-time Training enables model adaptation using only test questions and offers a promising paradigm for improving the reasoning ability of large language models (LLMs). However, it faces two major challenges: test questions are often highly...
TATRA: Training-Free Instance-Adaptive Prompting Through Rephrasing and Aggregation
arXiv:2603.03298v1 Announce Type: cross Abstract: Large Language Models (LLMs) have improved substantially alignment, yet their behavior remains highly sensitive to prompt phrasing. This brittleness has motivated automated prompt engineering, but most existing methods (i) require a task-specific training set, (ii)...
From Exact Hits to Close Enough: Semantic Caching for LLM Embeddings
arXiv:2603.03301v1 Announce Type: cross Abstract: The rapid adoption of large language models (LLMs) has created demand for faster responses and lower costs. Semantic caching, reusing semantically similar requests via their embeddings, addresses this need but breaks classic cache assumptions and...
Developing an AI Assistant for Knowledge Management and Workforce Training in State DOTs
arXiv:2603.03302v1 Announce Type: cross Abstract: Effective knowledge management is critical for preserving institutional expertise and improving the efficiency of workforce training in state transportation agencies. Traditional approaches, such as static documentation, classroom-based instruction, and informal mentorship, often lead to fragmented...
Token-Oriented Object Notation vs JSON: A Benchmark of Plain and Constrained Decoding Generation
arXiv:2603.03306v1 Announce Type: cross Abstract: Recently presented Token-Oriented Object Notation (TOON) aims to replace JSON as a serialization format for passing structured data to LLMs with significantly reduced token usage. While showing solid accuracy in LLM comprehension, there is a...
Old Habits Die Hard: How Conversational History Geometrically Traps LLMs
arXiv:2603.03308v1 Announce Type: cross Abstract: How does the conversational past of large language models (LLMs) influence their future performance? Recent work suggests that LLMs are affected by their conversational history in unexpected ways. For instance, hallucinations in prior interactions may...
Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding
arXiv:2603.03312v1 Announce Type: cross Abstract: Decoding natural language from non-invasive EEG signals is a promising yet challenging task. However, current state-of-the-art models remain constrained by three fundamental limitations: Semantic Bias (mode collapse into generic templates), Signal Neglect (hallucination based on...
Can Large Language Models Derive New Knowledge? A Dynamic Benchmark for Biological Knowledge Discovery
arXiv:2603.03322v1 Announce Type: cross Abstract: Recent advancements in Large Language Model (LLM) agents have demonstrated remarkable potential in automatic knowledge discovery. However, rigorously evaluating an AI's capacity for knowledge discovery remains a critical challenge. Existing benchmarks predominantly rely on static...
Combating data scarcity in recommendation services: Integrating cognitive types of VARK and neural network technologies (LLM)
arXiv:2603.03309v1 Announce Type: new Abstract: Cold start scenarios present fundamental obstacles to effective recommendation generation, particularly when dealing with users lacking interaction history or items with sparse metadata. This research proposes an innovative hybrid framework that leverages Large Language Models...
PulseLM: A Foundation Dataset and Benchmark for PPG-Text Learning
arXiv:2603.03331v1 Announce Type: new Abstract: Photoplethysmography (PPG) is a widely used non-invasive sensing modality for continuous cardiovascular and physiological monitoring across clinical, laboratory, and wearable settings. While existing PPG datasets support a broad range of downstream tasks, they typically provide...
Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations
arXiv:2603.03332v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has emerged as a foundational technique for eliciting reasoning from Large Language Models (LLMs), yet the robustness of this approach to corruptions in intermediate reasoning steps remains poorly understood. This paper presents...
Training-free Dropout Sampling for Semantic Token Acceptance in Speculative Decoding
arXiv:2603.03333v1 Announce Type: new Abstract: Speculative decoding accelerates large language model inference by proposing tokens with a lightweight draft model and selectively accepting them using a target model. This work introduces DropMatch, a novel approach that matches draft tokens to...
Prompt-Dependent Ranking of Large Language Models with Uncertainty Quantification
arXiv:2603.03336v1 Announce Type: new Abstract: Rankings derived from pairwise comparisons are central to many economic and computational systems. In the context of large language models (LLMs), rankings are typically constructed from human preference data and presented as leaderboards that guide...
Tracing Pharmacological Knowledge In Large Language Models
arXiv:2603.03407v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong empirical performance across pharmacology and drug discovery tasks, yet the internal mechanisms by which they encode pharmacological knowledge remain poorly understood. In this work, we investigate how drug-group...
A theoretical model of dynamical grammatical gender shifting based on set-valued set function
arXiv:2603.03510v1 Announce Type: new Abstract: This study investigates the diverse characteristics of nouns, focusing on both semantic (e.g., countable/uncountable) and morphosyntactic (e.g., masculine/feminine) distinctions. We explore inter-word variations for gender markers in noun morphology. Grammatical gender shift is a widespread...
AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis
arXiv:2603.03378v1 Announce Type: new Abstract: Large language model (LLM) agents offer a promising data-driven approach to automating Site Reliability Engineering (SRE), yet their enterprise deployment is constrained by three challenges: restricted access to proprietary data, unsafe action execution under permission-governed...
When Small Variations Become Big Failures: Reliability Challenges in Compute-in-Memory Neural Accelerators
arXiv:2603.03491v1 Announce Type: new Abstract: Compute-in-memory (CiM) architectures promise significant improvements in energy efficiency and throughput for deep neural network acceleration by alleviating the von Neumann bottleneck. However, their reliance on emerging non-volatile memory devices introduces device-level non-idealities-such as write...
Q-Measure-Learning for Continuous State RL: Efficient Implementation and Convergence
arXiv:2603.03523v1 Announce Type: new Abstract: We study reinforcement learning in infinite-horizon discounted Markov decision processes with continuous state spaces, where data are generated online from a single trajectory under a Markovian behavior policy. To avoid maintaining an infinite-dimensional, function-valued estimate,...
mlx-snn: Spiking Neural Networks on Apple Silicon via MLX
arXiv:2603.03529v1 Announce Type: new Abstract: We introduce mlx-snn, the first spiking neural network (SNN) library built natively on Apple's MLX framework. As SNN research grows rapidly, all major libraries -- snnTorch, Norse, SpikingJelly, Lava -- target PyTorch or custom backends,...
Role-Aware Conditional Inference for Spatiotemporal Ecosystem Carbon Flux Prediction
arXiv:2603.03531v1 Announce Type: new Abstract: Accurate prediction of terrestrial ecosystem carbon fluxes (e.g., CO$_2$, GPP, and CH$_4$) is essential for understanding the global carbon cycle and managing its impacts. However, prediction remains challenging due to strong spatiotemporal heterogeneity: ecosystem flux...