Projects per year
Abstract
Large Multimodal Models (LMMs) have achieved great success recently, demonstrating a strong capability to understand multimodal information and to interact with human users. Despite the progress made, the challenge of detecting high-risk interactions in multimodal settings, and in particular in speech modality, remains largely unexplored. Conventional research on risk for speech modality primarily emphasises the content (e.g., what is captured as transcription). However, in speech-based interactions, paralinguistic cues in audio can significantly alter the intended meaning behind utterances. In this work, we propose a speech-specific risk taxonomy, covering 8 risk categories under hostility (malicious sarcasm and threats), malicious imitation (age, gender, ethnicity), and stereotypical biases (age, gender, ethnicity). Based on the taxonomy, we create a small-scale dataset for evaluating current LMMs capability in detecting these categories of risk. We observe even the latest models remain ineffective to detect various paralinguistic-specific risks in speech (e.g., Gemini 1.5 Pro is performing only slightly above random baseline). Warning: this paper contains biased and offensive examples.
Original language | English |
---|---|
Title of host publication | EMNLP 2024, The 2024 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference |
Editors | Yaser Al-Onaizan, Mohit Bansal, Yun-Nung (Vivian) Chen |
Place of Publication | Kerrville TX USA |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 10957–10973 |
Number of pages | 17 |
ISBN (Electronic) | 9798891761643 |
Publication status | Published - 2024 |
Event | Empirical Methods in Natural Language Processing 2024 - Hyatt Regency Miami Hotel, Miami, United States of America Duration: 12 Nov 2024 → 16 Nov 2024 https://aclanthology.org/volumes/2024.emnlp-main/ https://2024.emnlp.org/ https://aclanthology.org/events/emnlp-2024/#2024emnlp-main |
Conference
Conference | Empirical Methods in Natural Language Processing 2024 |
---|---|
Abbreviated title | EMNLP 2024 |
Country/Territory | United States of America |
City | Miami |
Period | 12/11/24 → 16/11/24 |
Internet address |
Projects
- 1 Active
-
Exploiting Context in Multilingual Understanding and Generation
Haffari, R. (Primary Chief Investigator (PCI))
Australian Research Council (ARC)
20/11/20 → 28/02/26
Project: Research