ScopeQA: A Framework for Generating Out-of-Scope Questions for RAGby Zhiyuan Peng, Jinming Nian, Alexandre Evfimievski,…
Real-time Fake News from Adversarial Feedbackby Sanxing Chen, Yukun Huang, Bhuwan DhingraFirst submitted to arxiv…
To Trust or Not to Trust? Enhancing Large Language Models’ Situated Faithfulness to External Contextsby…
MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systemsby Nandan Thakur, Suleman Kazi, Ge Luo,…
Integrating Temporal Representations for Dynamic Memory Retrieval and Management in Large Language Modelsby Yuki Hou,…
FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMsby Forrest Sheng Bao, Miaoran Li,…
Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanismby Yimin Tang, Yurong Xu,…
A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directionsby Shailja Gupta,…
Retrieval Augmented Spelling Correction for E-Commerce Applicationsby Xuan Guo, Rohit Patki, Dante Everaert, Christopher PottsFirst…
Athena: Retrieval-augmented Legal Judgment Prediction with Large Language Modelsby Xiao Peng, Liang ChenFirst submitted to…