A Roadmap for Multilingual, Multimodal Domain Independent Deception Detection

TL;DR

This paper proposes a roadmap for deception detection that spans languages and modalities, aiming for domain independence. It argues that universal deception cues may exist across domains but current evidence is limited and data is unevenly distributed, especially for low-resource languages. The authors advocate a practical approach using multilingual, multimodal transformers and Retrieval-Augmented Generation (RAG) to build scalable, explainable deception detectors with zero-to-few-shot capabilities, anchored by vector stores like FAISS and multimodal models such as UnIVAL or Mistral. They discuss datasets, taxonomy, evaluation challenges, and system architecture to enable robust cross-domain detection in security, online moderation, and related areas. The roadmap highlights both methodological opportunities and governance considerations necessary to advance trustworthy automated deception detection.

Abstract

Deception, a prevalent aspect of human communication, has undergone a significant transformation in the digital age. With the globalization of online interactions, individuals are communicating in multiple languages and mixing languages on social media, with varied data becoming available in each language and dialect. At the same time, the techniques for detecting deception are similar across the board. Recent studies have shown the possibility of the existence of universal linguistic cues to deception across domains within the English language; however, the existence of such cues in other languages remains unknown. Furthermore, the practical task of deception detection in low-resource languages is not a well-studied problem due to the lack of labeled data. Another dimension of deception is multimodality. For example, a picture with an altered caption in fake news or disinformation may exist. This paper calls for a comprehensive investigation into the complexities of deceptive language across linguistic boundaries and modalities within the realm of computer security and natural language processing and the possibility of using multilingual transformer models and labeled data in various languages to universally address the task of deception detection.

Figures (1)

• Figure 1: High-level overview of a possible solution using RAG and a multi-modal in-context learner. The dashed line depicts the retrieval of context and its integration into the query.