3 papers
cs.CL2025
Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards
Manveer Singh Tamber, Forrest Sheng Bao, Chenyu Xu +7
Retrieval-augmented generation (RAG) aims to reduce hallucinations by grounding responses in external context, yet large language models (LLMs) still frequently introduce unsupport…
cs.CL2024
FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs
Forrest Sheng Bao, Miaoran Li, Renyi Qu +13
Summarization is one of the most common tasks performed by large language models (LLMs), especially in applications like Retrieval-Augmented Generation (RAG). However, existing eva…
cs.CL2024
MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems
Nandan Thakur, Suleman Kazi, Ge Luo +2
Traditional retrieval-augmented generation (RAG) benchmarks evaluate systems using heuristic-based metrics, but these require human preferences as the ground truth for reference. I…