Mona T. Diab

24 papers · 2009–2026 · 6 conferences · across top CS/AI conferences

Achievements

+6 more ↓

🏃 Academic Marathon (16) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (5) 🐝 Cross-Pollinator (7)

🌍 Conference Polyglot (5) 🏃 Academic Marathon (16) 🗃️ Keyword Collector (80) ⚡ Prolific Year (10) 💎 Century Club (14) ❓ The Questioner (3)

Conferences

EACL (8) ACL (7) EMNLP (4) NAACL (3) ICLR (1) IJCNLP (1)

Top co-authors

Jiarui Liu (7) Aashiq Muhamed (6) Virginia Smith (5) Yunze Xiao (4) Zhijing Jin (4) Kshitish Ghate (3) Maarten Sap (3) Bernhard Schölkopf (2) Adam Meyers (2) Wei Yun Ma (2)

Research topics

Applications (1)

Keywords

large language model (7) social bia (2) sparse autoencoder (2) pretraining datum (2) benchmark evaluation (2) text generation (2) multi-agent system (2) retrieval-augmented generation (2) vision-language model (2) machine translation (1) text analysis (1) direct preference optimization (1) content moderation (1) bias detection (1) model selection (1) dialogue generation (1) knowledge base (1) question answering (1) natural language processing (1) feature disentanglement (1)

Papers

StressRoBERTa: Cross-Condition Transfer Learning from Depression, Anxiety, and PTSD to Stress Detection EACL 2026 PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers in Overleaf ACL 2026 Hire Your Anthropologist! Rethinking Culture Benchmarks Through an Anthropological Lens EACL 2026 Mechanistic Interpretability Should Prioritize Feature Consistency in Sparse Autoencoders ACL 2026 JiraiBench: A Bilingual Benchmark for Evaluating Large Language Models’ Detection of Human risky health behavior Content in Jirai Community EACL 2026 Taming Object Hallucinations with Verified Atomic Confidence Estimation EACL 2026 RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models EACL 2026 Beyond Understanding: Evaluating the Pragmatic Gap in LLMs’ Cultural Processing of Figurative Language EACL 2026 Common Sense or Ableism? Rethinking Commonsense Reasoning Through the Lens of Disability EACL 2026 Personal Information Parroting in Language Models EACL 2026 CoRAG: Collaborative Retrieval-Augmented Generation NAACL 2025 BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data ACL 2025 Biases Propagate in Encoder-based Vision-Language Models: A Systematic Analysis From Intrinsic Measures to Zero-shot Retrieval Outcomes ACL 2025 Toward Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST) ACL 2025 From Complexity to Clarity: AI/NLP’s Role in Regulatory Compliance ACL 2025 Humanizing Machines: Rethinking LLM Anthropomorphism Through a Multi-Level Framework of Design EMNLP 2025 Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics EMNLP 2025 SimBA: Simplifying Benchmark Analysis Using Performance Matrices Alone EMNLP 2025 Intrinsic Bias is Predicted by Pretraining Data and Correlates with Downstream Performance in Vision-Language Encoders NAACL 2025 Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models NAACL 2025 Can Large Language Models Infer Causation from Correlation? ICLR 2024 GRASS: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients EMNLP 2024 Who, What, When, Where, Why? Comparing Multiple Approaches to the Cross-Lingual 5W Task ACL 2009 Who, What, When, Where, Why? Comparing Multiple Approaches to the Cross-Lingual 5W Task IJCNLP 2009