Usman Naseem

Do Large Language Models Reflect Demographic Pluralism in Safety? EACL 2026 Revealing the Truth with ConLLM for Detecting Multi-Modal Deepfakes EACL 2026 Do Clinical Question Answering Systems Really Need Specialised Medical Fine Tuning? EACL 2026 Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs EACL 2026 When the Model Said ‘No Comment’, We Knew Helpfulness Was Dead, Honesty Was Alive, and Safety Was Terrified EACL 2026 AlignCultura: Towards Culturally Aligned Large Language Models? ACL 2026 Framing Political Bias in Multilingual LLMs Across Pakistani Languages ACL 2026 LLM-Based Multi-Task Bangla Hate Speech Detection: Type, Severity, and Target ACL 2026 Beyond the Black Box: Demystifying Multi-Turn LLM Reasoning with VISTA AAAI 2026 MULSUM: A Multimodal Summarization System with Vis-Aligner and Diversity-Aware Image Selection EACL 2026 LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation AAAI 2026 MaiBERT: A Pre-training Corpus and Language Model for Low-Resourced Maithili Language EACL 2026 Are Large Language Models Economically Viable for Industry Deployment? ACL 2026 SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering ACL 2026 Activation Decomposition and Steering for LLM Backdoor Remediation ACL 2026 From Generation to Detection: A Multimodal Multi-Task Dataset for Benchmarking Health Misinformation EMNLP 2025 Wills Aligner: Multi-Subject Collaborative Brain Visual Decoding AAAI 2025 COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism AAAI 2025 Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-up ACL 2025 VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare ACL 2025 ReflectDiffu: Reflect between Emotion-intent Contagion and Mimicry for Empathetic Response Generation via a RL-Diffusion Framework ACL 2025 Leveraging Taxonomy and LLMs for Improved Multimodal Hierarchical Classification COLING 2025 BeefBot: Harnessing Advanced LLM and RAG Techniques for Providing Scientific and Technology Solutions to Beef Producers COLING 2025 Evaluating Large Language Models on Health-Related Claims Across Arabic Dialects COLING 2025 Natural Language Understanding of Devanagari Script Languages: Language Identification, Hate Speech and its Target Detection COLING 2025 Can LLM Agents Maintain a Persona in Discourse? EMNLP 2025 Too Helpful, Too Harmless, Too Honest or Just Right? EMNLP 2025 Pluralistic Alignment for Healthcare: A Role-Driven Framework EMNLP 2025 Truth, Trust, and Trouble: Medical AI on the Edge EMNLP 2025 LLMs on a Budget? Say HOLA EMNLP 2025 Benchmarking Large Language Models for Cryptanalysis and Side-Channel Vulnerabilities EMNLP 2025 TurnBench-MS: A Benchmark for Evaluating Multi-Turn, Multi-Step Reasoning in Large Language Models EMNLP 2025 ExtremeAIGC: Benchmarking LMM Vulnerability to AI-Generated Extremist Content EMNLP 2025 Probing the Limits of Multilingual Language Understanding: Low-Resource Language Proverbs as LLM Benchmark for AI Wisdom EMNLP 2025 Alleviating Textual Reliance in Medical Language-guided Segmentation via Prototype-driven Semantic Approximation ICCV 2025 Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy IJCAI 2025 RF-DTR: A Multi-Stage DCT Token Regression Network for Progressive Rib Fracture Mask Refinement IJCAI 2025 COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement IJCAI 2025 Towards a Bipartisan Understanding of Peace and Vicarious Interactions IJCAI 2025 Overview of BLP-2025 Task 1: Bangla Hate Speech Identification IJCNLP 2025 GameTox: A Comprehensive Dataset and Analysis for Enhanced Toxicity Detection in Online Gaming Communities NAACL 2025 Overview of BLP-2025 Task 1: Bangla Hate Speech Identification AACL 2025 Tiny But Mighty: A Crowdsourced Benchmark Dataset for Triple Extraction from Unstructured Text COLING 2024 Analyzing the Dynamics of Climate Change Discourse on Twitter: A New Annotated Corpus and Multi-Aspect Classification COLING 2024 Stance and Hate Event Detection in Tweets Related to Climate Activism - Shared Task at CASE 2024 EACL 2024 Can Large Language Models Enhance Predictions of Disease Progression? Investigating Through Disease Network Link Prediction EMNLP 2024 Why the Unexpected? Dissecting the Political and Economic Bias in Persian Small and Large Language Models COLING 2024 Extended Multimodal Hate Speech Event Detection During Russia-Ukraine Crisis - Shared Task at CASE 2024 EACL 2024 MLInitiative@WILDRE7: Hybrid Approaches with Large Language Models for Enhanced Sentiment Analysis in Code-Switched and Code-Mixed Texts COLING 2024 Temporal Tides of Emotional Resonance: A Novel Approach to Identify Mental Health on Social Media IJCNLP 2023 Automated Citation Function Classification and Context Extraction in Astrophysics: Leveraging Paraphrasing and Question Answering IJCNLP 2023 Temporal Tides of Emotional Resonance: A Novel Approach to Identify Mental Health on Social Media AACL 2023 Causal Intervention for Abstractive Related Work Generation EMNLP 2023 Multiview Clickbait Detection via Jointly Modeling Subjective and Objective Preference EMNLP 2023 KnowTellConvince at ArAIEval Shared Task: Disinformation and Persuasion Detection in Arabic using Similar and Contrastive Representation Alignment EMNLP 2023 DialectNLU at NADI 2023 Shared Task: Transformer Based Multitask Approach Jointly Integrating Dialect and Machine Translation Tasks in Arabic EMNLP 2023 LowResContextQA at Qur’an QA 2023 Shared Task: Temporal and Sequential Representation Augmented Question Answering Span Detection in Arabic EMNLP 2023 Assessing Political Inclination of Bangla Language Models EMNLP 2023 LowResourceNLU at BLP-2023 Task 1 & 2: Enhancing Sentiment Classification and Violence Incitement Detection in Bangla Through Aggregated Language Models EMNLP 2023 Enhancing ESG Impact Type Identification through Early Fusion and Multilingual Models AACL 2023 Debunking Biases in Attention ACL 2023 Self-Supervised Learning for Multilevel Skeleton-Based Forgery Detection via Temporal-Causal Consistency of Actions AAAI 2023 Reducing Knowledge Noise for Improved Semantic Analysis in Biomedical Natural Language Processing Applications ACL 2023 Breaking Barriers: Exploring the Diagnostic Potential of Speech Narratives in Hindi for Alzheimer’s Disease ACL 2023 A Dynamics and Task Decoupled Reinforcement Learning Architecture for High-Efficiency Dynamic Target Intercept AAAI 2023 Automated Citation Function Classification and Context Extraction in Astrophysics: Leveraging Paraphrasing and Question Answering AACL 2023 Enhancing ESG Impact Type Identification through Early Fusion and Multilingual Models IJCNLP 2023 A Multi-Modal Dataset for Hate Speech Detection on Social Media: Case-study of Russia-Ukraine Conflict EMNLP 2022 Incorporating Medical Knowledge to Transformer-based Language Models for Medical Dialogue Generation ACL 2022 Benchmarking for Public Health Surveillance tasks on Social Media with a Domain-Specific Pretrained Language Model ACL 2022 Accuracy meets Diversity in a News Recommender System COLING 2022