🌀 Hallucination - inarcissuss · Scour

🤖ai 应用 arXiv·

The Token Tax of Epistemic Accuracy: Comparing RAG and Long-Context Architectures for Document-Grounded Generative AI Applications

🧠LLM Apps arXiv·

Diagnosing and Mitigating Compounding Failures in Agentic Persuasion via Taxonomic Strategy Retrieval

🧠LLM Apps arXiv·

When Confidence Takes the Wrong Path: Diagnosing Retrieval-State Lock-In in RAG

🗣️LLMs arXiv·

Graph-Enhanced Large Language Models for Spatial Search

🧠Context Engineering arXiv·

Tracing Target Answers in Poisoned Retrieval Corpora via Token Influence Attribution

🤖AI Development arXiv·

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems

🔓Vulnerability Research arXiv·

RAVEN: Agentic RAG for Automated Vulnerability Repair

🗣️LLMs arXiv·

Failure Modes of Large Language Models on Research-Level Mathematics: A Taxonomy and an Empirical Characterisation

🧠LLM Apps arXiv·

ChartWalker: Benchmarking the Cross-Chart RAG Task

🤖ai 应用 arXiv·

Poisoned Playbooks: Demystifying Knowledge Poisoning Effects on AI Security Agents

🤖ai 应用 arXiv·

Less is More: Lightweight Prompt Compression for Question Answering Applications on Edge Devices

🧠LLM Apps arXiv·

Ground Then Rank: Revisiting Knowledge-Based VQA with Training-Free Entity Identification

🧠LLM Apps arXiv·

Fixed RAG Compression Collapses Measured Reader Scaling

🗣️LLMs arXiv·

LLM-assisted gNB Parameter Configuration for Radio Access Network

🧠LLM Apps arXiv·

Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B Model

🧠LLM arXiv·

A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots

🤖ai 应用 arXiv·

AI Economist Agent: An Agentic Framework for Model-Grounded Economic Analysis with RAG, Knowledge Graphs, and Large Language Models

🗣️LLMs arXiv·

BioHarness: Substrate-Aware Evidence Assembly for Biomedical Question Answering across Literature, Knowledge Bases, and Biological Atlases

🧠LLM arXiv·

Qiskit Code Migration with LLMs

💭Context Management arXiv·

Fail-RAG : A Retrieval Augmented Generation Informed Framework for Robot Failure Identification

Log in to enable infinite scrolling