FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs
Paper
•
2410.13210
•
Published
Ruixuan Tu
TURX
AI & ML interests
LLMs & NLP
Recent Activity
authored
a paper
about 2 months ago
FaithBench: A Diverse Hallucination Benchmark for Summarization by
Modern LLMs
authored
a paper
about 2 months ago
Is Semantic Chunking Worth the Computational Cost?
authored
a paper
about 2 months ago
DocAsRef: An Empirical Study on Repurposing Reference-Based Summary
Quality Metrics Reference-Freely
Organizations
None yet