Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909890405990400 |
|---|---|
| author | Tamber, Manveer Singh Bao, Forrest Sheng Xu, Chenyu Luo, Ge Kazi, Suleman Bae, Minseok Li, Miaoran Mendelevitch, Ofer Qu, Renyi Lin, Jimmy |
| author_facet | Tamber, Manveer Singh Bao, Forrest Sheng Xu, Chenyu Luo, Ge Kazi, Suleman Bae, Minseok Li, Miaoran Mendelevitch, Ofer Qu, Renyi Lin, Jimmy |
| contents | Retrieval-augmented generation (RAG) aims to reduce hallucinations by grounding responses in external context, yet large language models (LLMs) still frequently introduce unsupported information or contradictions even when provided with relevant context. This paper presents two complementary efforts at Vectara to measure and benchmark LLM faithfulness in RAG. First, we describe our original hallucination leaderboard, which has tracked hallucination rates for LLMs since 2023 using our HHEM hallucination detection model. Motivated by limitations observed in current hallucination detection methods, we introduce FaithJudge, an LLM-as-a-judge framework that leverages a pool of diverse human-annotated hallucination examples to substantially improve the automated hallucination evaluation of LLMs. We introduce an enhanced hallucination leaderboard centered on FaithJudge that benchmarks LLMs on RAG faithfulness in summarization, question-answering, and data-to-text generation tasks. FaithJudge enables a more reliable benchmarking of LLM hallucinations in RAG and supports the development of more trustworthy generative AI systems: https://github.com/vectara/FaithJudge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04847 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards Tamber, Manveer Singh Bao, Forrest Sheng Xu, Chenyu Luo, Ge Kazi, Suleman Bae, Minseok Li, Miaoran Mendelevitch, Ofer Qu, Renyi Lin, Jimmy Computation and Language Artificial Intelligence Retrieval-augmented generation (RAG) aims to reduce hallucinations by grounding responses in external context, yet large language models (LLMs) still frequently introduce unsupported information or contradictions even when provided with relevant context. This paper presents two complementary efforts at Vectara to measure and benchmark LLM faithfulness in RAG. First, we describe our original hallucination leaderboard, which has tracked hallucination rates for LLMs since 2023 using our HHEM hallucination detection model. Motivated by limitations observed in current hallucination detection methods, we introduce FaithJudge, an LLM-as-a-judge framework that leverages a pool of diverse human-annotated hallucination examples to substantially improve the automated hallucination evaluation of LLMs. We introduce an enhanced hallucination leaderboard centered on FaithJudge that benchmarks LLMs on RAG faithfulness in summarization, question-answering, and data-to-text generation tasks. FaithJudge enables a more reliable benchmarking of LLM hallucinations in RAG and supports the development of more trustworthy generative AI systems: https://github.com/vectara/FaithJudge. |
| title | Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2505.04847 |