i-2-7

Documents about i-2-7

• Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity#793822arXiv (All)
• OBER+: Continuity-Aware Reporting and Traceable Continuous Improvement in Outcome-Based Education#926657arXiv (All)
• Auditable by Construction: An Ontology-Driven Framework for Trustworthy LLM Analytics in Enterprise Finance#657086arXiv (OAI Expanded)
• Auditable by Construction: An Ontology-Driven Framework for Trustworthy LLM Analytics in Enterprise Finance#659222arXiv (All)
• Accountable AI with Grounded, Faithful, Consistent, Actionable Rationales: A Case Study in Clinical Trial Matching with VERDICT#926291arXiv (All)
• Efficient Code Embeddings from Code Generation Models#617356arXiv (OAI Expanded)
• Efficient Code Embeddings from Code Generation Models#617856arXiv (All)
• Corrections of Zipf's and Heaps' Laws Derived from Hapax Rate Models#633171arXiv (OAI Expanded)
• Key Coverage Matters: Semi-Structured Extraction of OCR Clinical Reports#633479arXiv (OAI Expanded)
• Corrections of Zipf's and Heaps' Laws Derived from Hapax Rate Models#635520arXiv (All)
• Key Coverage Matters: Semi-Structured Extraction of OCR Clinical Reports#635828arXiv (All)
• ProRetrieval: Learning to Orchestrate Hybrid Search via Executable Program Synthesis#779392arXiv (OAI Expanded)
• ProRetrieval: Learning to Orchestrate Hybrid Search via Executable Program Synthesis#780767arXiv (All)
• WnW: Waxing-and-Waning KV Cache for Long-Form Speech LLMs#789877arXiv (OAI Expanded)
• WnW: Waxing-and-Waning KV Cache for Long-Form Speech LLMs#793896arXiv (All)
• A Robust Evaluation of Probe Robustness: Lessons for Reliable OOD Uncertainty Quantification#797433arXiv (OAI Expanded)
• A Robust Evaluation of Probe Robustness: Lessons for Reliable OOD Uncertainty Quantification#798847arXiv (All)
• Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding#809575arXiv (OAI Expanded)
• Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding#819571arXiv (All)
• TEIDAN: A Multilingual Multiparty Dialogue Corpus#820811arXiv (All)
• Door-in-the-Face Requests and Refusal Behaviour in Large Language Models#920610arXiv (OAI Expanded)
• Door-in-the-Face Requests and Refusal Behaviour in Large Language Models#924844arXiv (All)
• Measuring Harmfulness of Computer-Using Agents#925803arXiv (All)
• Revisiting Lossy Verification in Speculative Decoding: Mechanisms, Trade-offs, and Failure Modes#927402arXiv (All)
• Correction as Annotation: Bootstrapping a Dependency Parser for Documentary Medieval Latin#973857arXiv (All)
• Steering Under Compression: Dose-Response, Capability Cost, and Failure Asymmetry in Quantized LLMs#974048arXiv (All)
• Tracing Stereotypes from Representation to Output in Multilingual LLMs#985686arXiv (All)
• Exploring Climate-Related Anxiety Through Social Media Content#1000096arXiv (All)
• When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models#1014259arXiv (All)
• ANCHOR: LLM-driven Subject Conditioning for Text-to-Image Synthesis#172184arXiv Biology
• ANCHOR: LLM-driven Subject Conditioning for Text-to-Image Synthesis#173200arXiv (OAI)
• ANCHOR: LLM-driven Subject Conditioning for Text-to-Image Synthesis#173450arXiv (OAI Expanded)
• ANCHOR: LLM-driven Subject Conditioning for Text-to-Image Synthesis#174028arXiv
• Learning to Ground Before Reading: Unified PCB Engineering Drawing Parsing with Compact Vision-Language Models#790058arXiv (OAI Expanded)
• Learning to Ground Before Reading: Unified PCB Engineering Drawing Parsing with Compact Vision-Language Models#794077arXiv (All)
• DELUGE: Decomposed Entropy-coded Live Unstructured Geometry Exchange for Real-time Particle Streaming#1014337arXiv (All)
• Business Truth, not SQL Accuracy: A Rule-Gated 7B Analytics Agent Outperforms a Direct-Prompted 32B Baseline#618754arXiv (OAI Expanded)
• Business Truth, not SQL Accuracy: A Rule-Gated 7B Analytics Agent Outperforms a Direct-Prompted 32B Baseline#620433arXiv (All)
• Incident Memory: Training-Free Operational Memory through Sequential Pattern Mining and Velocity-Stratified Retrieval#822057arXiv (All)
• 2 U.S.C. § 58c-1 — Repealed. Pub. L. 105–55, title I, § 3(c)(1), Oct. 7, 1997, 111 Stat. 1180#559032US Code (LII)
• LLMBridge: An LLM Pipeline for End-to-end Referential Bridging Resolution in English#809386arXiv (OAI Expanded)
• LLMBridge: An LLM Pipeline for End-to-end Referential Bridging Resolution in English#819379arXiv (All)
• DeepTable: Structural Attention Biases and Tree Path Encoding for Hierarchical Table Understanding#984610arXiv (All)
• Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts#985608arXiv (All)
• Domain-Specific Hallucination Detection in Large Language Models#999557arXiv (All)
• Register Bias in Complexity-Based Large Language Model Routing#1011276arXiv (All)
• Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models#1012696arXiv (All)
• Weakening Neurons: An Input-Output Functionality in Transformers with Outsize Influence#1012788arXiv (All)
• PEARL: Structural Privacy-Utility Control in Human-Centric CPS via Personalized Early-Exit Deep Reinforcement Learning#999621arXiv (All)
• Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges#1035590arXiv (All)