HalluSearch at SemEval-2025 Task 3: A Search-Enhanced RAG Pipeline for Hallucination Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910910873862144 |
|---|---|
| author | Abdallah, Mohamed A. El-Beltagy, Samhaa R. |
| author_facet | Abdallah, Mohamed A. El-Beltagy, Samhaa R. |
| contents | In this paper, we present HalluSearch, a multilingual pipeline designed to detect fabricated text spans in Large Language Model (LLM) outputs. Developed as part of Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes, HalluSearch couples retrieval-augmented verification with fine-grained factual splitting to identify and localize hallucinations in fourteen different languages. Empirical evaluations show that HalluSearch performs competitively, placing fourth in both English (within the top ten percent) and Czech. While the system's retrieval-based strategy generally proves robust, it faces challenges in languages with limited online coverage, underscoring the need for further research to ensure consistent hallucination detection across diverse linguistic contexts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10168 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HalluSearch at SemEval-2025 Task 3: A Search-Enhanced RAG Pipeline for Hallucination Detection Abdallah, Mohamed A. El-Beltagy, Samhaa R. Computation and Language Artificial Intelligence In this paper, we present HalluSearch, a multilingual pipeline designed to detect fabricated text spans in Large Language Model (LLM) outputs. Developed as part of Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes, HalluSearch couples retrieval-augmented verification with fine-grained factual splitting to identify and localize hallucinations in fourteen different languages. Empirical evaluations show that HalluSearch performs competitively, placing fourth in both English (within the top ten percent) and Czech. While the system's retrieval-based strategy generally proves robust, it faces challenges in languages with limited online coverage, underscoring the need for further research to ensure consistent hallucination detection across diverse linguistic contexts. |
| title | HalluSearch at SemEval-2025 Task 3: A Search-Enhanced RAG Pipeline for Hallucination Detection |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2504.10168 |