llm

Documents about llm

• RTP-LLM: High-Performance Alibaba LLM Inference Engine#241592arXiv CS
• OWASP Top 10 for LLM Applications 2025#2418OWASP
• Topic modeling methods comparison against LLM#14409HAL (France)
• EduRobust: Multilingual Robustness of System Prompt Restrictions in Educational LLM Deployments#136491OSF
• LLM-ReSum: A Framework for LLM Reflective Summarization through Self-Evaluation#141540arXiv CS
• LLM-Redactor: An Empirical Evaluation of Eight Techniques for Privacy-Preserving LLM Requests#13036arXiv CS
• On the Detectability of LLM-Generated Text: What Exactly Is LLM-Generated Text?#100654PhilArchive
• LLM-Emu: Native Runtime Emulation of LLM Inference via Profile-Driven Sampling#155264arXiv CS
• GAS-Leak-LLM: Genetic Algorithm-Based Suffix Optimization for Black-Box LLM Jailbreaking#280132arXiv CS
• LLM-Rosetta: A Hub-and-Spoke Intermediate Representation for Cross-Provider LLM API Translation#6010arXiv CS
• emotional-memory: Affective Field Theory for LLM Memory#28996DataCite
• emotional-memory: Affective Field Theory for LLM Memory#28997DataCite
• emotional-memory: Affective Field Theory for LLM Memory#29004DataCite
• emotional-memory: Affective Field Theory for LLM Memory#29005DataCite
• chatRater: Validating LLM-Generated Psycholinguistic Norms with Probability-Weighted Scoring#192060OSF
• Consistency-aware and LLM-assisted methods for named entity recognition#274580Iowa State University Digital Repository
• Your "Pro" LLM Subscription May Actually Be "Free": Exposing Fingerprint Spoofing Risks in LLM Inference Services#280121arXiv CS
• SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills#280126arXiv CS
• Aligning Dense Retrievers with LLM Utility via DistillationAligning Dense Retrievers with LLM Utility via Distillation#134533arXiv CS
• CES-CORE: A Deterministic Execution Discipline for LLM-Assisted Engineering#126967DataCite
• CES-CORE: A Deterministic Execution Discipline for LLM-Assisted Engineering#126968DataCite
• Understanding the Human-LLM Dynamic: A Literature Survey of LLM Use in Programming Tasks#189212arXiv (OAI)
• TheoTeach: An LLM-Powered Socratic Tutoring System for Teaching Theoretical Computer Science Topics#16027OSF
• FastTTS: accelerating test-time scaling for edge LLM reasoning#248596Spiral
• Interaction Schema and LLM Tool Replacement#122430PhilArchive
• From Program Slices to Causal Clarity: Evaluating Faithful, Actionable LLM-Generated Failure Explanations via Context Partitioning and LLM-as-a-Judge#120576arXiv CS
• BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook#128418arXiv (OAI)
• Comparative LLM Analysis: Benchmarking Language Model Performance#80755PhilArchive
• LLM Outputs as Stochascript#170061PhilArchive
• Between the Embedding and the Prompt: Systematic Design Effects in LLM-based Occupation Coding#203504OSF
• When LLM Signals Hurt: A Coverage-Density Analysis of LLM-Augmented Reinforcement Learning for Stock Trading#181083OSF
• From, Within and Beyond: Paradox, Creativity and LLM#89081PhilArchive
• Cost-Aware LLM Serving: Optimizing AI Infrastructure Economics#102893PhilArchive
• Exception Handling Mining and LLM Analysis Framework#195191Zenodo
• Comparing the Ethical Frameworks of Leading LLM Chatbots#228691PhilArchive
• ChatBDI: Think BDI, Talk LLM#262344IRIS
• ShellGames: Speculative LLM-Driven SSH Deception#282722arXiv CS
• Can "consciousness" be observed from large language model (LLM) internal states? Dissecting LLM representations obtained from Theory of Mind test with Integrated Information Theory and Span Representation analysis#87701PhilArchive
• Multilayer Psychographic Analysis of a Personal Facebook Audience: An LLM-Assisted Pipeline with Reliability Assessment#276894OSF
• LLM+Graph@VLDB'2025 Workshop Summary#2767arXiv CS
• LLM-Guided Prompt Evolution for Password Guessing#13015arXiv CS
• Policy-Invisible Violations in LLM-Based Agents#13033arXiv CS
• Can we Watermark Low-Entropy LLM Outputs?#13037arXiv CS
• Personalizing LLM-Based Conversational Programming Assistants#13158arXiv CS
• LLM-Driven Large-Scale Spectrum Access#13994arXiv CS
• The Problem of Generics in LLM Training#73894PhilArchive
• Elaboration Drift: How Human–LLM Interaction Erodes Epistemic Traction#91604PhilArchive
• What it's like to be an LLM#108296PhilArchive
• Benchmarking LLM-Driven Network Configuration Repair#134517arXiv CS
• Uncertainty Propagation in LLM-Based Systems#139014arXiv CS

Related topics