27 citations · 48 across the 44 of their papers we have counts for
13 papers · 1 filter
QuantumCanvas: A Multimodal Benchmark for Visual Learning of Atomic Interactions
Can Polat, Erchin Serpedin, Mustafa Kurban +1
Despite rapid advances in molecular and materials machine learning, most models still lack physical transferability: they fit correlations across whole molecules or crystals rather…
Audit-of-Understanding: Posterior-Constrained Inference for Mathematical Reasoning in Language Models
Samir Abdaljalil, Erchin Serpedin, Khalid Qaraqe +1
Large language models (LLMs) often generate reasoning traces that appear coherent but rest on unsupported assumptions, leading to hallucinated conclusions. Prior work mainly addres…
Evaluating Multilingual and Code-Switched Alignment in LLMs via Synthetic Natural Language Inference
Samir Abdaljalil, Erchin Serpedin, Khalid Qaraqe +1
Large language models (LLMs) are increasingly applied in multilingual contexts, yet their capacity for consistent, logically grounded alignment across languages remains underexplor…
EMPATHIA: Multi-Faceted Human-AI Collaboration for Refugee Integration
Mohamed Rayan Barhdadi, Mehmet Tuncel, Erchin Serpedin +1
Current AI approaches to refugee integration optimize narrow objectives such as employment and fail to capture the cultural, emotional, and ethical dimensions critical for long-ter…
Theorem-of-Thought: A Multi-Agent Framework for Abductive, Deductive, and Inductive Reasoning in Language Models
Samir Abdaljalil, Hasan Kurban, Khalid Qaraqe +1
Large language models (LLMs) have shown strong performance across natural language reasoning tasks, yet their reasoning processes remain brittle and difficult to interpret. Prompti…
Beyond Atomic Geometry Representations in Materials Science: A Human-in-the-Loop Multimodal Framework
Can Polat, Erchin Serpedin, Mustafa Kurban +1
Most materials science datasets are limited to atomic geometries (e.g., XYZ files), restricting their utility for multimodal learning and comprehensive data-centric analysis. These…
xChemAgents: Agentic AI for Explainable Quantum Chemistry
Can Polat, Mehmet Tuncel, Mustafa Kurban +2
Recent progress in multimodal graph neural networks has demonstrated that augmenting atomic XYZ geometries with textual chemical descriptors can enhance predictive accuracy across…
Stress-Testing Multimodal Foundation Models for Crystallographic Reasoning
Can Polat, Hasan Kurban, Erchin Serpedin +1
Evaluating foundation models for crystallographic reasoning requires benchmarks that isolate generalization behavior while enforcing physical constraints. This work introduces a mu…
Understanding the Capabilities of Molecular Graph Neural Networks in Materials Science Through Multimodal Learning and Physical Context Encoding
Can Polat, Hasan Kurban, Erchin Serpedin +1
Molecular graph neural networks (GNNs) often focus exclusively on XYZ-based geometric representations and thus overlook valuable chemical context available in public databases like…
Advanced Deep Learning and Large Language Models: Comprehensive Insights for Cancer Detection
Yassine Habchi, Hamza Kheddar, Yassine Himeur +4
The rapid advancement of deep learning (DL) has transformed healthcare, particularly in cancer detection and diagnosis. DL surpasses traditional machine learning and human accuracy…
HalluVerse25: Fine-grained Multilingual Benchmark Dataset for LLM Hallucinations
Samir Abdaljalil, Hasan Kurban, Erchin Serpedin
Large Language Models (LLMs) are increasingly used in various contexts, yet remain prone to generating non-factual content, commonly referred to as "hallucinations". The literature…
SINdex: Semantic INconsistency Index for Hallucination Detection in LLMs
Samir Abdaljalil, Hasan Kurban, Parichit Sharma +2
Large language models (LLMs) are increasingly deployed across diverse domains, yet they are prone to generating factually incorrect outputs - commonly known as "hallucinations." Am…
SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs
Samir Abdaljalil, Filippo Pallucchini, Andrea Seveso +3
Despite the state-of-the-art performance of Large Language Models (LLMs), these models often suffer from hallucinations, which can undermine their performance in critical applicati…