i-2-7

Documents about i-2-7

• Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation#819159arXiv (All)
• HiveTraceGuard-Pro: A Compact Generative Guardrail for Prompt Injection, Jailbreaks, and Adversarial Obfuscation#821033arXiv (All)
• The Double Measurement Confound in Agent Benchmarks: De-Scaffolding, Ground-Truth Scoring, and Reliability Beyond the Mean#986988arXiv (All)
• The Limits of BPE Tokenization in Polish: Segmentation-Flexional Forms, Grammatical Anchoring, and First-Person Stability in Inflectional Language Models#1011287arXiv (All)
• When Is Graph Structure Worth Its Cost? The Case for Structure Pricing in Retrieval-Augmented Generation#1011798arXiv (All)
• Reusing Latent Speech Representations for Query-Conditioned Topic Localization in Transcripts#1036233arXiv (All)
• Auditing Political Alignment in LLM Assistants: Engagement, Stance, and User Identity#1048434arXiv (All)
• When Who You Are Can Change the Code You Get: A Study of Persona-Induced Bias in LLM Code Generation#1036786arXiv (All)
• Ensembling LLMs for AI-Augmented Cybersecurity Software Requirements Generation#997208arXiv (All)
• LLAMADRS: Evaluating Open-Source LLMs on Real Clinical Interviews--To Reason or Not to Reason?#158657arXiv (OAI)
• Toward Auto-Research: Mining Falsifiable Research Ideas from Paper Knowledge Graphs with Categorical Structure#656806arXiv (OAI Expanded)
• When Do LLMs Replace Fine-Tuned NLU? A Decision Framework for Intent Detection in Production Conversational Systems#656814arXiv (OAI Expanded)
• Toward Auto-Research: Mining Falsifiable Research Ideas from Paper Knowledge Graphs with Categorical Structure#658942arXiv (All)
• When Do LLMs Replace Fine-Tuned NLU? A Decision Framework for Intent Detection in Production Conversational Systems#658950arXiv (All)
• MasterSet: A Large-Scale Benchmark for Must-Cite Citation Recommendation in the AI/ML Literature#664219arXiv (OAI Expanded)
• MasterSet: A Large-Scale Benchmark for Must-Cite Citation Recommendation in the AI/ML Literature#665719arXiv (All)
• Nested Byte-Level Vocabularies Are Cheap to Deploy and Expensive to Share: A Pre-Registered Negative Result#783315arXiv (OAI Expanded)
• Nested Byte-Level Vocabularies Are Cheap to Deploy and Expensive to Share: A Pre-Registered Negative Result#784905arXiv (All)
• Recognition Without Enforcement: Configuration-Dependent Failures in LLM Agent Instruction Arbitration and External Control#788503arXiv (OAI Expanded)
• Recognition Without Enforcement: Configuration-Dependent Failures in LLM Agent Instruction Arbitration and External Control#792503arXiv (All)
• Emulate or Estimate? The Divergent Strengths of Base and Post-Trained Language Models for Opinion Simulation#800123arXiv (All)
• Interpretable Symptom Vectors for Depression in a Large Language Model#822255arXiv (All)
• Second-order consistency for learning chaotic dynamics via randomized Jacobian matching#927334arXiv (All)
• Moral Entropy: Auditing Bias and Uncertainty in Moral Judgment#1036380arXiv (All)
• Therapy as an NLP Task: Comparing LLMs and Human Peers Behaviors in CBT Sessions#1051409arXiv (All)
• Structured Prediction for Scalable Spreadsheet Table Understanding: From Cell Types to Table Ranges (Extended Version)#618673arXiv (OAI Expanded)
• Structured Prediction for Scalable Spreadsheet Table Understanding: From Cell Types to Table Ranges (Extended Version)#620352arXiv (All)
• Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agents#628166arXiv (OAI Expanded)
• Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agents#630028arXiv (All)
• Inhibitory Attention for Clinical Long-Context Reasoning: Characterizing and Mitigating Lost-in-the-Middle Effects in EHR Processing#656793arXiv (OAI Expanded)
• Edge-Based Agentic Retrieval-Augmented Generation for Autonomous FHWA Bridge Inspection Compliance#656815arXiv (OAI Expanded)
• Inhibitory Attention for Clinical Long-Context Reasoning: Characterizing and Mitigating Lost-in-the-Middle Effects in EHR Processing#658929arXiv (All)
• Edge-Based Agentic Retrieval-Augmented Generation for Autonomous FHWA Bridge Inspection Compliance#658951arXiv (All)
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems#664319arXiv (OAI Expanded)
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems#665819arXiv (All)
• GreenBench: Benchmarking Energy Efficiency and Carbon Footprint of Open-Source LLM Inference on Apple Silicon#788912arXiv (OAI Expanded)
• GreenBench: Benchmarking Energy Efficiency and Carbon Footprint of Open-Source LLM Inference on Apple Silicon#792916arXiv (All)
• Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts#809789arXiv (OAI Expanded)
• Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts#819785arXiv (All)
• Gauge dependence and structured-output corruption in sign-branched repetition penalties: measurements across models, inference stacks, and alternative repetition controls#821944arXiv (All)
• Does the Selected Object Reach the Reader? Auditing Identity Handoffs in Grounded Language-Model Pipelines#984262arXiv (All)
• Enhancing Extubation Failure Prediction with LLM-Derived Features from Respiratory Therapy Clinical Notes#1011266arXiv (All)
• The "Curse of Knowledge" in LLM Query Simulation: Concept Provenance for Tracing Answer-Side Intrusion#1013670arXiv (All)
• Morpho-VITS: Variational Inference with Morphological Modeling for End-to-End Speech Synthesis of a Tonal Bantu Language#1050491arXiv (All)
• Specification-first convergence with an AI coding agent: a case study of dismantling a core architectural invariant across 189 files in a 717k-line codebase with no test oracle and no human code review#608987arXiv (OAI Expanded)
• Specification-first convergence with an AI coding agent: a case study of dismantling a core architectural invariant across 189 files in a 717k-line codebase with no test oracle and no human code review#610049arXiv (All)
• Recall Before Rerank: Benchmarking Deep Learning Models for Large-Scale Code-to-Code Retrieval#1035538arXiv (All)
• Does generative AI supersede supervised XMLC? A Benchmark Study on Automated Subject Indexing with German Scientific Literature#618694arXiv (OAI Expanded)
• Does generative AI supersede supervised XMLC? A Benchmark Study on Automated Subject Indexing with German Scientific Literature#620373arXiv (All)
• Ghost Echoes: Semantic Erasure Failure in Retrieval-Backed Applications#656797arXiv (OAI Expanded)