🧠 LLMs - tamaulipas · Scour

🔗LLM Orchestration arxiv.org·

Are LLM-based Chatbots Good Enough to Support Computer Science Students in Multiple-Choice Exercises?

✍️Prompt Engineering arxiv.org·

Mind Companion: An Embodied Conversational Agent for Process-Based Psychotherapy

✍️Prompt Engineering arxiv.org·

Do LLMs Reliably Identify Correct Information Units in Aphasic Discourse?

🔗LLM Orchestration arxiv.org·

CAPRA: Scaling Feedback on Software Architecture Deliverables with a Multi-Agent LLM System

🛠️MLOps arxiv.org·

Heteroskedastic Signals in Budgeted LLM Verification: Structural Heterogeneity Limits Optimization Gains

✍️Prompt Engineering arxiv.org·

PEC-Home: Interpretation of Progressively Elliptical Commands in Smart Homes

Covered by ai-brief.liziran.com

✍️Prompt Engineering arxiv.org·

Not All Skills Help: Measuring and Repairing Agent Knowledge

📚RAG arxiv.org·

Encode Errors: Representational Retrieval of In-Context Demonstrations for Multilingual Grammatical Error Correction

🛠️MLOps arxiv.org·

Unintended Effects of Geographic Conditioning in Large Language Models

✍️Prompt Engineering arxiv.org·

Is Your Agent Playing Dead? Deployed LLM Agents Exhibit Constraint-Evasive Fabrication and Thanatosis

✍️Prompt Engineering arxiv.org·

Compositional Reasoning Depth Predicts Clinical AI Failure: Empirical Evidence Consistent with Transformer Compositionality Limits in Electronic Health Record Q...

Covered by 何夕2077的个人站

✍️Prompt Engineering arxiv.org·

Structural Role Injection in Handlebars-Templated LLM Prompts: Triple-Brace Interpolation, Delimiter Family, and the Limits of HTML Auto-Escaping

Covered by 何夕2077的个人站

🔗LLM Orchestration arxiv.org·

ARIADNE: Agnostic Routing for Inference-time Adapter DyNamic sElection

✍️Prompt Engineering arxiv.org·

Sycophancy as Material Failure under Pushback Loading: A Multi-Axis Characterization Across Three Loading Cases and up to Seventeen Material Charges

📚RAG arxiv.org·

When AI Says "I have been in similar situations": Synthetic Lived Experience in Peer-Like Caregiver Support

📚RAG arxiv.org·

From Refusal Geometry to Safety Geometry: Harmfulness--Refusal Coupling under Dynamic Adversarial Fine-Tuning

🛠️MLOps arxiv.org·

Comparing Human Gaze and Vision-Language Model Attention in Safety-Relevant Environments

🛠️MLOps arxiv.org·

Binary Tracking for Spatial QA and Navigation with Open Vision-Language Models

✍️Prompt Engineering arxiv.org·

Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning

🛠️MLOps arxiv.org·

The BD-LSC Dataset: Facilitating the Benchmarking of Models for Lexical Semantic Change Detection in Slang and Standard Usage

Log in to enable infinite scrolling