Artificial Intelligence

Mechanism Design for Large Language Models (Extended Abstract) IJCAI 2025 Mechanisms vs. Outcomes: Probing for Syntax Fails to Explain Performance on Targeted Syntactic Evaluations EMNLP 2025 Mechanistic Fine-tuning for In-context Learning EMNLP 2025 Mechanistic Interpretability for Steering Vision-Language-Action Models CoRL 2025 Mechanistic Interpretability of Emotion Inference in Large Language Models ACL 2025 Mechanistic PDE Networks for Discovery of Governing Equations ICML 2025 Mechanistic Permutability: Match Features Across Layers ICLR 2025 Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models EMNLP 2025 Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization ICML 2025 Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning NAACL 2025 MECoT: Markov Emotional Chain-of-Thought for Personality-Consistent Role-Playing ACL 2025 MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference NAACL 2025 MedArabiQ: Benchmarking Large Language Models on Arabic Medical Tasks MLHC 2025 Med-CoDE: Medical Critique based Disagreement Evaluation Framework NAACL 2025 MedCOD: Enhancing English-to-Spanish Medical Translation of Large Language Models Using Enriched Chain-of-Dictionary Framework EMNLP 2025 MedCodER: A Generative AI Assistant for Medical Coding NAACL 2025 MedDiT: A Knowledge-Controlled Diffusion Transformer Framework for Dynamic Medical Image Generation in Virtual Simulated Patient IJCAI 2025 MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis ACL 2025 MEDEQUALQA: Evaluating Biases in LLMs with Counterfactual Reasoning AACL 2025 MedEthicEval: Evaluating Large Language Models Based on Chinese Medical Ethics NAACL 2025 MedEx: Enhancing Medical Question-Answering with First-Order Logic based Reasoning and Knowledge Injection COLING 2025 MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models EMNLP 2025 Media Source Matters More Than Content: Unveiling Political Bias in LLM-Generated Citations EMNLP 2025 Mediation Analysis for Probabilities of Causation AAAI 2025 Medical MLLM Is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models AAAI 2025