🧠 LLMs - cwensel · Scour

The Neutral Mask: How RLHF Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model

🔢Vector Databases Academic

Dominant-Layer ZO: A Single Layer Dominates Zeroth-Order Fine-Tuning of LLMs

⚙️MLOps Academic

Emergence of Context Characteristics Sensitivity in Large Language Models

📚RAG Academic

MolE-RAG: Molecular Structure-Enhanced Retrieval-Augmented Generation for Chemistry

📚RAG Academic

Empirical Evaluation of Large Language Models for Migration of Code Fragments to Post-Quantum Cryptography

⚙️MLOps Academic

Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)

📚RAG Academic

Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

⚙️MLOps Academic

Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs

⚙️MLOps Academic

Multilingual Fine-Tuning via Localized Gradient Conflict Resolution

⚙️MLOps Academic

Evidence Graph Consistency in Retrieval-Augmented Generation: A Model-Dependent Analysis of Hallucination Detection

📚RAG Academic

ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?

⚙️MLOps Academic

LLMs + Persona-Plug = Personalized LLMs

🔗LLM Workflows Academic

LLM-Guided Evolution for Medical Decision Pipelines

🔗LLM Workflows Academic

EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms

⚙️MLOps Academic

Language-Aware Token Boosting: LLM Language Confusion Reduction Without Tuning

⚙️MLOps Academic

TA-RAG: Tone-Aware Retrieval-Augmented Generation for Peer-Support Health Communication

📚RAG Academic

LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding

📚RAG Academic

Detection and Interpretability Analysis of Quotation Errors by Large Language Models

📚RAG Academic

Distilling Safe LLM Systems via Soft Prompts for On Device Settings

⚙️MLOps Academic

Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data

⚙️MLOps Academic

Log in to enable infinite scrolling