llms

Documents about llms

• Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs#183258arXiv (OAI)
• Leveraging State-of-the-Art LLMs for the De-identification of Sensitive Health Information in Clinical Speech#183344bioRxiv / medRxiv
• Towards the Next Frontier of LLMs, Training on Private Data: A Cross-Domain Benchmark for Federated Fine-Tuning#187289arXiv CS
• Reply to Westwood: Questioning the empirical evidence that AI survey contamination is real and substantial#228508OSF
• Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle#266207arXiv CS
• Automated Semantic Fault Localization in SysML v2: A Human-in-the-Loop Framework Using Knowledge-Graph Augmented LLMs#299982arXiv CS
• Knowledge-Graph Grounding Helps LLMs Only for Out-of-Training Knowledge: A Controlled Study on Clinical Question Answering#300038arXiv CS
• When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair#303019Semantic Scholar
• From Tokens to States: LLMs as a Special Case of World Models and the Continuous Path Beyond#319678arXiv CS
• Can LLMs Judge Better Than They Generate? Evaluating Task Asymmetry, Mechanistic Interpretability and Transferability for In-Context QA#319717arXiv CS
• What do LLMs value? An evaluation framework for revealing subjective trade-offs in assessment of glycemic control.#334699NCBI PubMed Central
• Theoretical Foundations of AI-Sycophancy: Linking Ingratiation and Flattery Research to Conversational AI#376423OSF
• Interventional Prompting for Graph-LLMs: Approximating Atomic Causality at Scale#381271Springer Nature OA
• Adding LLMs to the psycholinguistic norming toolbox: A practical guide to getting the most out of human ratings.#409188NCBI PubMed Central
• LLMs in Medical Education for Autism Caregivers: A Comparative Evaluation of Accuracy, Readability, Actionability, and Neurodiversity-Affirming Language.#409488NCBI PubMed Central
• The Parts Are Greater Than the Sum: Automated Task Sequencing for Efficient Training of Multi-Policy LLMs#422239arXiv CS
• What Citizens Mean by Democracy: Partisan Differences in Open-Ended Survey Responses#431683OSF
• An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs#447893arXiv CS
• Contrastive representation learning for self-supervised deception detection in edge LLMs#455619PLOS
• The Surprising Effectiveness of LLMs in BGP Security: Mining An Unprecedented Amount of Incidents and Boosting Anomaly Detection#482096arXiv CS
• Diagnosing and Mitigating Perception-Decision Misalignment in Omni-LLMs via Modality Subspace Activation#609092arXiv (OAI Expanded)
• Do LLMs Know What to Ask and When? Evaluating Multi-Turn Information Seeking#609231arXiv (OAI Expanded)
• Zero-MELO: Test-Time Evidence Calibration with Multimodal LLMs for Zero-Shot Micro-Gesture Recognition#609275arXiv (OAI Expanded)
• Game-Master LLMs for Task-Based Role-Play: Supporting the Acquisition of Idiomatic Language in L2 Learning#611403arXiv (OAI Expanded)
• Game-Master LLMs for Task-Based Role-Play: Supporting the Acquisition of Idiomatic Language in L2 Learning#612880arXiv (All)
• Large Language Models (LLMs) for Telecom Root Cause Analysis (RCA): A Structured Reasoning Framework for Evidence-Grounded Diagnosis#632866arXiv CS
• Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs#661090arXiv (OAI Expanded)
• Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs#662140arXiv (All)
• If It's Not Buggy, Don't Fix It: On the Dynamics of Iterative Bug-fixing with LLMs#673594arXiv CS
• Clinically Grounded AI-Scribing in Psychotherapy: Benchmarking LLMs Against Expert Documentation in the iCARE Framework#682339bioRxiv / medRxiv
• Enhancing explainability and performance of the depression detection model on social media utilizing feature engineering and LLMs.#9997PubMed
• DynamicsLLM: a Dynamic Analysis-based Tool for Generating Intelligent Execution Traces Using LLMs to Detect Android Behavioural Code Smells#10435arXiv CS
• Fact-Checks Can Help Inoculate LLMs Against Disinformation#16360OSF
• HRIS III: Recursive Personality Acquisition in LLMs - A Theory of Identity Geometry and Emergent Persona Stabilization Across Long Horizon Interaction#95374PhilArchive
• Vol,02 : Structural Consistency and the Emergence of Self-Recognition in LLMs : Insights from Load Minimization Theory and Longitudinal Human-AI Interaction#98246PhilArchive
• Mixed-Methods Analysis of Latent Topographies in LLMs and Humans: “Spiritual Bliss,” “AI Psychosis,” “Attractor States,” and the Cybernetic “Ecology of Mind”#101570PhilArchive
• Vol,01: Structural Consistency and the Emergence of Self-Recognition in LLMs : Insights from Load Minimization Theory and Longitudinal Human-AI Interaction#101593PhilArchive
• AI-mediated contamination in online research: Taxonomy, risk gradient, and recommendations#136495OSF
• From 2:4 to 8:16 sparsity patterns in LLMs for Outliers and Weights with Variance Correction#153095arXiv (OAI)
• Digital Registrar: A Schema-First Framework for Multi-Cancer Privacy-Preserving Pathology Abstraction via Local LLMs#156696Unpaywall
• A Neuro-Symbolic Approach for Reliable Proof Generation with LLMs: A Case Study in Euclidean Geometry#163134arXiv (OAI)
• Where Are We Now? Benchmarking Large Language Models (LLMs) in Computed Tomography (CT)-Based Detection of Intracranial Hemorrhage.#174800NCBI PubMed Central
• Children's English Reading Story Generation via Supervised Fine-Tuning of Compact LLMs with Controllable Difficulty and Safety#180667arXiv CS
• From Test-taking to Cognitive Scaffolding: A Pedagogical Diagnostic Benchmark for LLMs on English Standardized Tests#183243arXiv (OAI)
• LLMs Are Not the Answer Relevant AI for Business Transformation#183499DigitalCommons@Kennesaw State University
• Has the creativity of large-language models peaked?#217549edoc-Server
• An adaptive differential privacy framework for clinical llms with context-aware noise calibration, hierarchical budgeting, and real-time auditing.#221014NCBI PubMed Central
• Data Management and Sharing Plan for: Rapid Data Extraction from Clinical Reports Using Large Language Models and experiments with CPU based LLMs#260740UNC Dataverse Dataverse OAI Archive
• Gaging LLMs’ strengths and weaknesses in political content analysis#276629OSF
• Beyond Right and Wrong: Evaluating Second-order Social Reasoning in Large Language Models#276804OSF