arXiv AI

To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech

The paper introduces VeriSpeak, a benchmark of 3,879 spoken claims for evaluating fact verification in Large Audio Language Models (LALMs). It shows a clear modality gap: models that verify written claims well often fail on spoken versions, and retrieval alone offers limited improvement. Combining retrieval with explicit reasoning yields the best performance, reaching 86.1% accuracy and demonstrating the need for grounded reasoning over retrieved evidence in speech misinformation detection.

arXiv Computation and Language
Sep 7

TRILOGUE: A Trilingual Spoken Dialogue Fact-Checking Benchmark with Evidence and Paired Audio

TRILOGUE is a new trilingual benchmark for spoken dialogue fact‑checking, covering English, Russian, and Kazakh. It includes almost 12,000 dialogues, 187,000 turns, and 390 hours of paired audio with ASR transcripts and word‑level timestamps, as well as nearly 5,000 human‑recorded Russian and Kazakh files. The dataset supports tasks such as claim check‑worthiness detection, evidence retrieval, and claim verification under various input conditions, and baseline experiments reveal challenges with ASR errors and cross‑lingual transfer, especially for Kazakh.

By Chaewan Chun, Meruyert Aristombayeva, Jiyoung Choi, Mahjabin Nahar, Delvin Ce Zhang, Dongwon Lee
arXiv AI
Aug 28

When Text Misleads: Inconsistent-Aware Reasoning for Audio-Grounded Dialogue

The paper introduces ContraTalk, a benchmark that tests whether dialogue models truly use acoustic cues or rely on transcript shortcuts. It formalizes cross‑modal disagreement, creates conflict and consistent QA examples, and proposes an Audio Twin representation to expose acoustic evidence to models. Experiments show that while text‑only LLMs perform well on consistent cases, they falter on conflict cases, and AudioLLMs only partially mitigate this issue.

By Yen-Ju Lu, Yuzhe Wang, Yaohan Guan, Xiluo He, Jiarui Hai, Mingrui Liang, Kaavya Chaparala, Thomas Thebaud, Laureano Moro-Velazquez, Najim Dehak, Jesus Villalba
arXiv AI
Jun 10

Linguistically Augmented Audio Speech Data (LinguAS)

arXiv:2606. 10246v1 Announce Type: cross Abstract: Maliciously-created fake speech, including deepfaked and spoofed audio, is proliferating at an alarming rate, and detection models are racing to stay ahead of the curve.

By Ashley R. Keaton, Zahra Khanjani, Christine Mallinson, Vandana P. Janeja
arXiv Computation and Language
6d ago

Context-Aware Multimodal Claim Verification in Spoken Dialogues

The paper introduces MAD2, a synthetic benchmark of 1,000 two‑speaker dialogues with about 10 hours of audio and 1,230 check‑worthy sentence annotations for spoken claim verification. It proposes a calibrated multimodal fusion approach that combines a context‑aware audio encoder with a dialogue‑aware text model. Experiments show that adding dialogue context improves verification performance, though the gains differ across scenarios, and that fusion offers the largest advantage when full‑dialogue context is available, though it does not consistently outperform text alone.

By Chaewan Chun, Delvin Ce Zhang, Dongwon Lee
arXiv AI
Sep 10

Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation

The paper introduces Fact-Ablated Evaluation (FAE), a framework that iteratively removes cited evidence to test whether large language models (LLMs) adjust their fact‑checking predictions accordingly. Experiments reveal that many off‑the‑shelf LLMs rely more on internal knowledge than on the provided evidence. To address this, the authors propose REAL, a training method that uses counterfactual evidence supervision to encourage LLMs to base veracity judgments on evidence, achieving better evidence‑dependent performance across four datasets.

By Xingyu Deng, Mingzi Cao, Nikolaos Aletras, Xi Wang, Mark Stevenson
arXiv Computation and Language
Sep 23

ARAFA: An LLM-Generated Arabic Fact-Checking Dataset

A new large-scale Arabic fact‑checking dataset called Arafa has been created using an automated pipeline that generates claims from Arabic Wikipedia, mutates them into counterfactuals, and validates them against supporting or refuting evidence. The dataset contains 181,976 claim‑evidence pairs labeled as supported, refuted, or not enough information, and human evaluation shows high inter‑annotator agreement and strong validation accuracy. Fine‑tuned transformer models on Arafa achieve a Macro F1‑score of 77%, demonstrating its usefulness for Arabic fact‑checking tasks.

By Christophe Khalil, Shady Elbassuoni, Rida Assaf