Real-Time Evaluation Models for RAG: Who Detects Hallucinations Best?
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912312662687744 |
|---|---|
| author | Sardana, Ashish |
| author_facet | Sardana, Ashish |
| contents | This article surveys Evaluation models to automatically detect hallucinations in Retrieval-Augmented Generation (RAG), and presents a comprehensive benchmark of their performance across six RAG applications. Methods included in our study include: LLM-as-a-Judge, Prometheus, Lynx, the Hughes Hallucination Evaluation Model (HHEM), and the Trustworthy Language Model (TLM). These approaches are all reference-free, requiring no ground-truth answers/labels to catch incorrect LLM responses. Our study reveals that, across diverse RAG applications, some of these approaches consistently detect incorrect RAG responses with high precision/recall. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21157 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Real-Time Evaluation Models for RAG: Who Detects Hallucinations Best? Sardana, Ashish Machine Learning This article surveys Evaluation models to automatically detect hallucinations in Retrieval-Augmented Generation (RAG), and presents a comprehensive benchmark of their performance across six RAG applications. Methods included in our study include: LLM-as-a-Judge, Prometheus, Lynx, the Hughes Hallucination Evaluation Model (HHEM), and the Trustworthy Language Model (TLM). These approaches are all reference-free, requiring no ground-truth answers/labels to catch incorrect LLM responses. Our study reveals that, across diverse RAG applications, some of these approaches consistently detect incorrect RAG responses with high precision/recall. |
| title | Real-Time Evaluation Models for RAG: Who Detects Hallucinations Best? |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2503.21157 |