CCFQA: A Benchmark for Cross-Lingual and Cross-Modal Speech and Text Factuality Evaluation
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_ | 1866908789427404800 |
|---|---|
| author | Du, Yexing Liu, Kaiyuan Pan, Youcheng Chu, Zheng Yang, Bo Feng, Xiaocheng Liu, Ming Xiang, Yang |
| author_facet | Du, Yexing Liu, Kaiyuan Pan, Youcheng Chu, Zheng Yang, Bo Feng, Xiaocheng Liu, Ming Xiang, Yang |
| contents | As Large Language Models (LLMs) are increasingly popularized in the multilingual world, ensuring hallucination-free factuality becomes markedly crucial. However, existing benchmarks for evaluating the reliability of Multimodal Large Language Models (MLLMs) predominantly focus on textual or visual modalities with a primary emphasis on English, which creates a gap in evaluation when processing multilingual input, especially in speech. To bridge this gap, we propose a novel Cross-lingual and Cross-modal Factuality benchmark (CCFQA). Specifically, the CCFQA benchmark contains parallel speech-text factual questions across 8 languages, designed to systematically evaluate MLLMs' cross-lingual and cross-modal factuality capabilities. Our experimental results demonstrate that current MLLMs still face substantial challenges on the CCFQA benchmark. Furthermore, we propose a few-shot transfer learning strategy that effectively transfers the Question Answering (QA) capabilities of LLMs in English to multilingual Spoken Question Answering (SQA) tasks, achieving competitive performance with GPT-4o-mini-Audio using just 5-shot training. We release CCFQA as a foundational research resource to promote the development of MLLMs with more robust and reliable speech understanding capabilities. Our code and dataset are available at https://github.com/yxduir/ccfqa. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_07295 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CCFQA: A Benchmark for Cross-Lingual and Cross-Modal Speech and Text Factuality Evaluation Du, Yexing Liu, Kaiyuan Pan, Youcheng Chu, Zheng Yang, Bo Feng, Xiaocheng Liu, Ming Xiang, Yang Computation and Language As Large Language Models (LLMs) are increasingly popularized in the multilingual world, ensuring hallucination-free factuality becomes markedly crucial. However, existing benchmarks for evaluating the reliability of Multimodal Large Language Models (MLLMs) predominantly focus on textual or visual modalities with a primary emphasis on English, which creates a gap in evaluation when processing multilingual input, especially in speech. To bridge this gap, we propose a novel Cross-lingual and Cross-modal Factuality benchmark (CCFQA). Specifically, the CCFQA benchmark contains parallel speech-text factual questions across 8 languages, designed to systematically evaluate MLLMs' cross-lingual and cross-modal factuality capabilities. Our experimental results demonstrate that current MLLMs still face substantial challenges on the CCFQA benchmark. Furthermore, we propose a few-shot transfer learning strategy that effectively transfers the Question Answering (QA) capabilities of LLMs in English to multilingual Spoken Question Answering (SQA) tasks, achieving competitive performance with GPT-4o-mini-Audio using just 5-shot training. We release CCFQA as a foundational research resource to promote the development of MLLMs with more robust and reliable speech understanding capabilities. Our code and dataset are available at https://github.com/yxduir/ccfqa. |
| title | CCFQA: A Benchmark for Cross-Lingual and Cross-Modal Speech and Text Factuality Evaluation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2508.07295 |