i-2-7

Documents about i-2-7

• Empirical Evaluation of Membership Inference Attacks on NLP Text Classifiers: A Baseline Study on SST-2#998509arXiv (All)
• How AI Coders Discuss, Disagree, and Reach Consensus: Challenges and Opportunities for LLM-Based Qualitative Coding#998664arXiv (All)
• Moving the Mean Toward the Known Good, Not Beyond It: What Inference-Time Interventions and Weight Consolidation Buy in Open-Ended Generation#789116arXiv (OAI Expanded)
• Moving the Mean Toward the Known Good, Not Beyond It: What Inference-Time Interventions and Weight Consolidation Buy in Open-Ended Generation#793120arXiv (All)
• Inverse Theory of Mind Modeling for Content Recommendation: From Web Browsing to Dynamic Intelligent Interfaces#650996arXiv (OAI Expanded)
• Inverse Theory of Mind Modeling for Content Recommendation: From Web Browsing to Dynamic Intelligent Interfaces#652449arXiv (All)
• Distilled Rapid Embedding Transfer (DRET): Parameter-Efficient Biomedical Domain Adaptation via Priority-Based Embedding Transfer#921045arXiv (OAI Expanded)
• Distilled Rapid Embedding Transfer (DRET): Parameter-Efficient Biomedical Domain Adaptation via Priority-Based Embedding Transfer#925281arXiv (All)
• Sixteen models, fewer than two voices: measuring ensemble dispersion where no answer is uniquely correct#1035575arXiv (All)
• Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflows#800093arXiv (All)
• Architecting Conversational Data Systems for Stateless LLM APIs: The Hydration Proxy Pattern#822257arXiv (All)
• Evaluation of Phonetic Encoding Algorithms on Transcription Datasets#927684arXiv (All)
• CPC-CMS: Cognitive Pairwise Comparison Classification Model Selection Framework for Document-level Sentiment Analysis#661318arXiv (OAI Expanded)
• CPC-CMS: Cognitive Pairwise Comparison Classification Model Selection Framework for Document-level Sentiment Analysis#662368arXiv (All)
• Detectable Only Where It Is Confounded: What Verified Duplication Counts Say About Membership Evidence in Language Models#997811arXiv (All)
• The Internal Anatomy of Strategic Choice in Large Language Models#1012330arXiv (All)
• Beyond Accuracy: How Procedural Traces Shift the Decision Criterion of LLM Overseers#1011898arXiv (All)
• Synthia: Scalable Grounded Persona Generation from Social Media Data#153104arXiv (OAI)
• Center of Research Translation (CORT) Project 2#180275ClinicalTrials.gov
• Governance at the Boundary: How Agent Decomposition Degrades Policy Compliance#618677arXiv (OAI Expanded)
• Governance at the Boundary: How Agent Decomposition Degrades Policy Compliance#620356arXiv (All)
• The Curse of Multilinguality in Lexical Normalization#809788arXiv (OAI Expanded)
• The Curse of Multilinguality in Lexical Normalization#819784arXiv (All)
• MERGED: Multimodal Entity Resolution via Generated Expert Reasoning Distillation#822332arXiv (All)
• LexFlip: A Dissociation Diagnostic for Legal Meaning Preservation Metrics#972232arXiv (All)
• MedWER: A Reproducible, Model-Free Evaluation Protocol for Medical Speech Recognition#972776arXiv (All)
• Aslema at NADI 2026: Data Augmentation for Intent Recognition and Slot Filling#998338arXiv (All)
• Plans They Abandon, Reports They Author: The Narrative Layer of Autonomous Agents#1000169arXiv (All)
• CompAdapt: Adaptable Composite Motion Modeling for Physics-Consistent Text-to-Video Generation#1035857arXiv (All)
• Stop Removing Stopwords: How an Inherited Preprocessing Default Distorts Legal Text-as-Data#1013754arXiv (All)
• High-quality (PEA) 2 (FA)Pb 2 I 7 Ruddlesden–Popper hybrid perovskite single crystals: growth, structural and optical properties#796346HAL (France)
• Large Language Models as Implicit Sociological Models: Reconstructing Voting Behaviour from Sociodemographic Profiles#616501arXiv (OAI Expanded)
• Large Language Models as Implicit Sociological Models: Reconstructing Voting Behaviour from Sociodemographic Profiles#617001arXiv (All)
• Does Your Agent's Memory Survive a Model Upgrade? A Controlled Study of Memory Portability#972270arXiv (All)
• Strategic Doctrine Language Models (sdLM): A Learning-System Framework for Doctrinal Consistency and Geopolitical Forecasting#973039arXiv (All)
• A Content-Addressed Workflow for Reproducible DANTE Gravitational-Wave Anomaly Analysis#986025arXiv (All)
• Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement#1012248arXiv (All)
• BreakFun: Jailbreaking LLMs via Object Instantiation under Simulated Code Execution#1036590arXiv (All)
• Performance vs Consistency: Evaluating a Foundation Model in Lung-RADS Screening#1036964arXiv (All)
• Joint Communication Sensing Beamforming and Uplink Power Control for Network-Assisted Full-Duplex Cell-Free ISAC Systems#975068arXiv (All)
• 2 U.S.C. § 1921 — Repealed. Pub. L. 108–7, div. H, title I, § 1018(h)(2), Feb. 20, 2003, 117 Stat. 369#557947US Code (LII)
• Stay Focused: Problem Drift in Multi-Agent Debate#128350arXiv (OAI)
• Wildfire spread forecasting with Deep Learning#128397arXiv (OAI)
• MAP: A Benchmark on Multimodal Accessibility Planning for Real World Places#788395arXiv (OAI Expanded)
• MAP: A Benchmark on Multimodal Accessibility Planning for Real World Places#792395arXiv (All)
• What It Costs to Compose, Rebuild, and Correct Precomputed Memory#808711arXiv (OAI Expanded)
• What It Costs to Compose, Rebuild, and Correct Precomputed Memory#818703arXiv (All)
• Analyzing LLM Reasoning to Uncover Mental Health Stigma#999227arXiv (All)
• MemeLens: Multilingual Multitask VLMs for Memes#1035374arXiv (All)
• The Limits of Speculation: Bounding Speculative Decoding in Mixture-of-Experts#1036839arXiv (All)