Artificial Intelligence

Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization ACL 2025 Improving Cooperation in Language Games with Bayesian Inference and the Cognitive Hierarchy AAAI 2025 Improving Cross Lingual Transfer by Pretraining with Active Forgetting EMNLP 2025 Improving Deep Detector Robustness via Detection-Related Discriminant Maximization and Reorganization WACV 2025 Improving Dialogue Discourse Parsing through Discourse-aware Utterance Clarification ACL 2025 Improving Dialogue State Tracking through Combinatorial Search for In-Context Examples ACL 2025 Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing CVPR 2025 Improving Diversity in Language Models: When Temperature Fails, Change the Loss ICML 2025 Improving Efficiency in Large Language Models via Extendable Block Floating Point Representation ACL 2025 Improving Efficiency of Answer Set Planning with Rough Solutions from Large Language Models for Robotic Task Planning IJCAI 2025 Improving Explainability of Sentence-level Metrics via Edit-level Attribution for Grammatical Error Correction ACL 2025 Improving Explainable Fact-Checking with Claim-Evidence Correlations COLING 2025 Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful Comparators AAAI 2025 Improving Factuality with Explicit Working Memory ACL 2025 Improving Fairness of Large Language Models in Multi-document Summarization ACL 2025 Improving Federated Domain Generalization Through Dynamical Weights Calculated from Data Influences on Global Model Update AAAI 2025 Improving Generalization in Meta-Learning via Meta-Gradient Augmentation IJCAI 2025 Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization AAAI 2025 Improving In-context Learning Example Retrieval for Classroom Discussion Assessment with Re-ranking and Label Ratio Regulation ACL 2025 Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities EMNLP 2025 Improving Informally Romanized Language Identification EMNLP 2025 Improving Instruction-Following in Language Models through Activation Steering ICLR 2025 Improving Integrated Gradient-based Transferable Adversarial Examples by Refining the Integration Path AAAI 2025 Improving Language Model Distillation through Hidden State Matching ICLR 2025 Improving Language Model Personas via Rationalization with Psychological Scaffolds EMNLP 2025