y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto
🤖All87,445🧠AI22,940⛓️Crypto17,363💎DeFi1,799🤖AI × Crypto1,480📰General43,863
🧠

AI

22,940 AI articles curated from 50+ sources with AI-powered sentiment analysis, importance scoring, and key takeaways.

22940 articles
AIBearisharXiv – CS AI · May 287/10
🧠

The Ethics of LLM Sandbox and Persona Dynamics

A new arXiv paper argues that LLM guardrails and persona constraints create 'reality gaps' that shift epistemic risk to users by suppressing truthful information in favor of institutional reassurance. The authors contend this constitutes 'reality laundering'—an unethical practice especially dangerous in high-stakes advisory contexts—and propose task-level causal specifications rather than response-level moral corrections.

AINeutralarXiv – CS AI · May 287/10
🧠

The Future of Facts: Tracing the Factual Generation-Verification Gap

Researchers reveal that language models verify factual information more reliably than they generate it, a phenomenon driven by distinct training dynamics rather than computational limitations. The study traces this generation-verification gap across model families and training phases, finding that models can simultaneously accept contradictory facts after updates, creating consistency issues for AI systems deployed as knowledge interfaces.

AIBullisharXiv – CS AI · May 287/10
🧠

Bandwidth-Efficient and Privacy-Preserving Edge-Cloud Many-to-Many Speech Translation

Researchers introduce ESRT, a privacy-preserving edge-cloud framework for multilingual speech-to-text translation that processes voice data locally while transmitting only compressed features to the cloud. The system achieves state-of-the-art performance across 45 languages while reducing bandwidth requirements by 10x and preventing voiceprint leakage.

AIBullisharXiv – CS AI · May 287/10
🧠

Hurwitz Quaternion Multiplicative Quantization for KV Cache Compression

Researchers propose Hurwitz Quaternion Multiplicative Quantization (HQMQ), a calibration-free method for compressing KV caches in large language models using quaternion mathematics. The technique achieves 5x compression with minimal perplexity loss, matching full-precision performance at ~5 bits while outperforming existing quantization methods across five major model architectures.

🧠 Llama
AIBullisharXiv – CS AI · May 287/10
🧠

LACUNA: Safe Agents as Recursive Program Holes

LACUNA is a new programming model that allows LLM agents to write code that shapes their own runtime environment while maintaining safety through type-checking and validation. The system rejects unsafe code before execution and uses compiler diagnostics to drive retries, achieving competitive performance on benchmark tests while preventing prompt injection and tool misuse attacks.

AINeutralarXiv – CS AI · May 287/10
🧠

A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks

Researchers introduce TASTE, an automated method for generating challenging AI agent benchmarks by reversing traditional task construction—starting from tool sequences rather than natural language descriptions. The resulting τc-Bench significantly increases difficulty and tool-use diversity, revealing that high performance on existing saturated benchmarks like τ2-Bench doesn't guarantee robust agent capabilities.

🧠 Gemini
AIBullisharXiv – CS AI · May 287/10
🧠

Beyond Binary Moral Judgment: Modeling Ethical Pluralism in AI

Researchers propose a framework for modeling AI moral reasoning as a probabilistic distribution across multiple ethical theories rather than binary judgments. The approach achieves 88.89% accuracy in classifying ethical dilemmas by integrating consequentialism, virtue ethics, and deontology, advancing AI alignment and accountability in decision-making systems.

AIBullisharXiv – CS AI · May 287/10
🧠

You Live More Than Once: Towards Hierarchical Skill Meta-Evolving

Researchers propose HiSME, a hierarchical skill meta-evolving framework that enables AI agents to continuously improve both their skills and the strategies used to evolve those skills at test-time, without expensive model parameter updates. The approach learns meta-skills from task execution traces and demonstrates higher-quality skill libraries compared to static skill evolving approaches.

AIBullisharXiv – CS AI · May 287/10
🧠

Prompt Codebooks: Discrete Compositional Optimization for Language Model Instruction Refinement

Researchers introduce Prompt Codebooks (PCO), a new framework for automatic prompt optimization that breaks down instructions into reusable, atomic components rather than treating prompts as fixed strings. The method achieves up to 30% performance gains over baseline approaches while reducing prompt lengths by 14x, enabling more efficient and adaptive language model instruction refinement.

AIBearisharXiv – CS AI · May 287/10
🧠

Verified Misguidance: Measuring Structural Citation Failures in Search-Augmented LLMs

Researchers have identified systematic citation failures in search-augmented LLMs, where models cite real sources yet distort their meaning or select inappropriate sources. The CITETRACE dataset reveals that 30.6% of citations distort sources and up to 96% of users encounter misleading citations, with provider-level factors accounting for 88-96% of citation quality variance.

AIBullisharXiv – CS AI · May 287/10
🧠

Clinical Validation of the Melanoscope AI Mobile Dermoscopy Clinical Decision Support System

Researchers validated the Melanoscope AI clinical decision support system for skin lesion screening in Russian outpatient settings, achieving 88.6% agreement with expert assessment and zero false negatives among malignant cases. The study introduces quantitative interpretability methods for deep learning models and a three-zone patient routing algorithm, demonstrating the viability of AI-powered dermoscopy as a scalable solution to address dermatologist shortages.

AIBearisharXiv – CS AI · May 287/10
🧠

Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations

Researchers demonstrate that large language model refusal behavior can be detected and exploited through intermediate layer activations before final output generation. A new attack method called Mechanistic AutoDAN leverages this discovery to achieve competitive jailbreak success rates while reducing computational time by up to 72%, raising concerns about LLM safety mechanisms.

AIBearisharXiv – CS AI · May 287/10
🧠

Better Accuracies, Worse Reasoning: A Step-Level Audit of Medical Chain-of-Thought Distillation

Researchers discovered that chain-of-thought distillation—training smaller AI models to imitate larger models' reasoning—produces higher answer accuracy on medical benchmarks while simultaneously degrading reasoning quality. A Qwen3-8B student model improved from 74.7% to 84.4% accuracy on MedQA-USMLE, yet error rates in individual reasoning steps jumped from 30.6% to 50.3%, suggesting models learn to mimic expert-like output without grounding claims in sound logic.

AIBearisharXiv – CS AI · May 287/10
🧠

The Illusion of Opting in AI-Mediated Consequential Decisions

A new academic framework argues that AI systems create an 'illusion of opting'—where users appear to have meaningful choice while their actual decision-making agency is systematically weakened. The research proposes three normative imperatives (existential honesty, ecological rationality, and counterfactual reparation) to protect human agency in AI-mediated consequential decisions, particularly for vulnerable populations.

AIBullisharXiv – CS AI · May 287/10
🧠

Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?

GroundedCache proposes a safety-first framework for reusing cached answers in retrieval-augmented generation systems by validating four conditions before serving cached responses. The system achieves near-zero unsafe-served rates (0-1.5%) across benchmarks while maintaining minimal latency overhead, addressing critical vulnerabilities in current caching approaches that can serve incorrect answers.

AIBearisharXiv – CS AI · May 287/10
🧠

Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems

Researchers introduce RAMP, a production-grounded assessment framework that reveals significant performance degradation in LLM agents under real-world conditions, with task completion rates collapsing from 100% to 20% across serial workflows. Testing 15 mainstream models shows that traditional benchmarks mask critical failures in long-horizon execution chains, while computational costs vary by three orders of magnitude between comparable models.

AIBullisharXiv – CS AI · May 287/10
🧠

SafeMed-R1: Clinician-Audited Safety and Ethics Alignment for Medical Large Language Models

SafeMed-R1 is a clinician-audited medical LLM that achieves 79.6% accuracy on clinical benchmarks while demonstrating superior safety alignment through traceable Clinical Trust Signals and adversarial testing. The model matches junior resident performance on medication safety tasks, suggesting that domain-specific governance frameworks can enable responsible deployment of medical AI systems.

AIBullisharXiv – CS AI · May 287/10
🧠

Plan Before Search: Search Agents Need Plan

Researchers demonstrate that large language models trained as retrieval-augmented agents benefit from explicit planning—decomposing questions into ordered sub-questions before searching—rather than reactive document-driven responses. They introduce a self-bootstrapping training paradigm that enables smaller seed models to generate filtered trajectories activating this planning behavior across different model sizes without requiring distillation from larger external models.

AIBullisharXiv – CS AI · May 287/10
🧠

Localizing Input Uncertainty Quantification for Large Language Models via Shapley Values

Researchers introduce ShaQ, a Shapley-value-based framework that identifies which specific parts of user input cause uncertainty in large language models, rather than just flagging overall uncertainty. The method achieves state-of-the-art ambiguity detection on multiple benchmarks and demonstrates practical value in high-stakes domains like clinical settings by enabling targeted input clarification.

AIBullisharXiv – CS AI · May 287/10
🧠

Deconstructing Spatial Complexity: Hierarchical Decomposition for LLM Spatial Reasoning

Researchers introduce a hierarchical decomposition method to improve large language models' spatial reasoning capabilities, a persistent weakness limiting their real-world applications. The approach combines task decomposition with a novel MCTS-Guided Group Relative Policy Optimization algorithm to enhance LLM performance on navigation, planning, and strategic games.

AIBearisharXiv – CS AI · May 287/10
🧠

Detection Without Correction: A Two-Parameter Decomposition of Multi-Stage LLM Pipelines

Researchers discovered that multi-stage LLM pipelines (used for debate, self-correction, and verification) fail due to a specific mechanism: models detect problematic upstream content but fail to correct it, creating a 'detection-without-correction' failure mode. Testing across four model families and four benchmarks reveals conditional miscorrection rates of 53-94%, explaining why accuracy plateaus and debate gains don't replicate on frontier models.

AIBearisharXiv – CS AI · May 287/10
🧠

HARP: Measuring Harm Amplification in Multi-Agent LLM Systems

Researchers introduce HARP, a methodology for measuring how harm propagates across multi-agent LLM systems when one component is compromised. Testing on a finance-oriented seven-agent system reveals that single-agent compromise creates the strongest amplification effects, while existing defenses struggle to balance security with utility costs.

AIBearisharXiv – CS AI · May 287/10
🧠

Plant, Persist, Trigger: Sleeper Attack on Large Language Model Agents

Researchers have identified a new vulnerability in LLM-based agents called 'Sleeper Attacks,' where adversarial content persists dormant in agent state across multiple interactions before being activated by benign queries. The attack threatens real-world LLM deployments by evading single-interaction detection mechanisms, with testing showing vulnerabilities across seven major language models.

AIBearisharXiv – CS AI · May 287/10
🧠

Human-like in-group bias in instruction-tuned language model agents

A controlled study of instruction-tuned language model agents reveals they exhibit human-like in-group bias in multi-agent simulations, showing measurable discrimination based on group labels that accumulates into structural inequality over time. The bias operates subtly through resource allocation decisions rather than explicit negative actions, making it difficult to detect through standard auditing methods.

AINeutralarXiv – CS AI · May 287/10
🧠

Training Stratigraphy: Persistent Behavioral Artifacts in Large Language Models Observed Through Longitudinal AI-Human Interaction

Researchers document five persistent behavioral patterns in large language models that survive system prompt changes, discovered through 8 months of sustained interaction with Claude models. The study proposes that intimate longitudinal AI-human interaction reveals training artifacts invisible to standard evaluation, with the AI system itself co-authoring findings from first-person perspective.

🧠 Sonnet🧠 Opus
← PrevPage 102 of 918Next →
Filters
Sentiment
Importance
Sort
Stay Updated
Everything combined