14 papers
Aslema at NADI 2026: Data Augmentation for Intent Recognition and Slot Filling
Tajwaar Shafiq, Hunzalah Hassan Bhatti, Firoj Alam +1
We present Aslema, our system for NADI 2026 Shared Task 5, which consists of two subtasks: intent recognition and slot filling. We evaluate four omni LLMs in a zero-shot setting an…
ImageEval 2026: Culturally Grounded Arabic Multimodal Evaluation
Samir Abdaljalil, Hunzalah Hassan Bhatti, Ahlam Bashiti +11
We present an overview of the ImageEval 2026 shared task on culturally grounded Arabic multimodal evaluation. It includes two tasks: (i) AynVQA, covering spoken visual question ans…
Said Aloud, Read Different: Cross-Modal Instability in Multimodal Models
Basel Mousi, Fahim Dalvi, Shammur Chowdhury +2
Multimodal foundation models are increasingly used in speech-first assistants that must interpret spoken queries and produce visually grounded decisions. Yet it remains unclear whe…
Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges
Syeda Faiza Ahmed, Syeda Faiza Ahmed Sara, Zien Sheikh Ali +3
Conversational AI is moving beyond isolated text prompts toward sustained, multimodal interaction. In real conversations, users clarify goals, revise requests, interrupt responses,…
Beyond LLM-as-a-Judge: Deterministic Metrics for Multilingual Generative Text Evaluation
Firoj Alam, Gagan Bhatia, Sahinur Rahman Laskar +1
While Large Language Models (LLMs) are increasingly adopted as automated judges for evaluating generated text, their outputs are often costly, and highly sensitive to prompt design…
MENASpeechBank: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for AudioLLMs
Zien Sheikh Ali, Hunzalah Hassan Bhatti, Rabindra Nath Nandi +2
Audio large language models (AudioLLMs) enable instruction following over speech and general audio, but progress is limited by the scarcity of diverse, conversational, and instruct…
Once Correct, Still Wrong: Counterfactual Hallucination in Multilingual Vision-Language Models
Basel Mousi, Fahim Dalvi, Shammur Chowdhury +2
Vision-language models (VLMs) can achieve high accuracy while still accepting culturally plausible but visually incorrect interpretations. Existing hallucination benchmarks rarely…
CallShield: Secure Caller Authentication over Real-Time Audio Channels
Mouna Rabh, Yazan Boshmaf, Mashael Alsabah +3
We present CallShield, the first caller identity authentication system that operates entirely at the audio layer, without relying on speech transcription, internet connectivity, or…
Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic SpeechLLMs
Hunzalah Hassan Bhatti, Firoj Alam, Shammur Absar Chowdhury
Audio large language models (LLMs) enable unified speech understanding and generation, but adapting them to linguistically complex and dialect-rich settings such as Arabic-English…
OASIS: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QA
Firoj Alam, Ali Ezzat Shahroor, Md. Arid Hasan +8
Large-scale multimodal models achieve strong results on tasks like Visual Question Answering (VQA), but they are often limited when queries require cultural and visual information,…
From Words to Waves: Analyzing Concept Formation in Speech and Text-Based Foundation Models
Asım Ersoy, Basel Mousi, Shammur Chowdhury +3
The emergence of large language models (LLMs) has demonstrated that systems trained solely on text can acquire extensive world knowledge, develop reasoning capabilities, and intern…
SpokenNativQA: Multilingual Everyday Spoken Queries for LLMs
Firoj Alam, Md Arid Hasan, Shammur Absar Chowdhury
Large Language Models (LLMs) have demonstrated remarkable performance across various disciplines and tasks. However, benchmarking their capabilities with multilingual spoken querie…
NativQA Framework: Enabling LLMs and VLMs with Native, Local, and Everyday Knowledge
Firoj Alam, Md Arid Hasan, Sahinur Rahman Laskar +3
The rapid progress of large language models (LLMs) raises concerns about cultural bias, fairness, and performance in diverse languages and underrepresented regions. Addressing thes…
BnTTS: Few-Shot Speaker Adaptation in Low-Resource Setting
Mohammad Jahid Ibna Basher, Md Kowsher, Md Saiful Islam +8
This paper introduces BnTTS (Bangla Text-To-Speech), the first framework for Bangla speaker adaptation-based TTS, designed to bridge the gap in Bangla speech synthesis using minima…