Natural Language Understanding

CxGGEC: Construction-Guided Grammatical Error Correction ACL 2025 Decoding Alzheimer’s: Interpretable Visual and Logical Attention in Picture Description Tasks Interspeech 2025 Definition Generation for Word Meaning Modeling: Monolingual, Multilingual, and Cross-Lingual Perspectives EMNLP 2025 Detecting Referring Expressions in Visually Grounded Dialogue with Autoregressive Language Models ACL 2025 DnDScore: Decontextualization and Decomposition for Factuality Verification in Long-Form Text Generation EMNLP 2025 Dynamic Head Selection for Neural Lexicalized Constituency Parsing ACL 2025 Enhancing NLU in Large Language Models Using Adversarial Noisy Instruction Tuning AAAI 2025 Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing AAAI 2025 Evaluating Conversational Agents with Persona-driven User Simulations based on Large Language Models: A Sales Bot Case Study EMNLP 2025 Explainability and Interpretability of Multilingual Large Language Models: A Survey EMNLP 2025 Explaining Differences Between Model Pairs in Natural Language through Sample Learning EMNLP 2025 Fann or Flop: A Multigenre, Multiera Benchmark for Arabic Poetry Understanding in LLMs EMNLP 2025 Findings of the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-powered Tutors ACL 2025 FINKRX: Establishing Best Practices for Korean Financial NLP ACL 2025 FLOW-BENCH: Towards Conversational Generation of Enterprise Workflows EMNLP 2025 Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates EMNLP 2025 Is There No Such Thing as a Bad Question? H4R: HalluciBot for Ratiocination, Rewriting, Ranking, and Routing AAAI 2025 It’s Not Bragging If You Can Back It Up: Can LLMs Understand Braggings? ACL 2025 Knowledge-Augmented Multimodal Clinical Rationale Generation for Disease Diagnosis with Small Language Models ACL 2025 KRISTEVA: Close Reading as a Novel Task for Benchmarking Interpretive Reasoning ACL 2025 Language Models are Crossword Solvers NAACL 2025 LLMs can be easily Confused by Instructional Distractions ACL 2025 LoCt-Instruct: An Automatic Pipeline for Constructing Datasets of Logical Continuous Instructions EMNLP 2025 Mapping semantic networks to Dutch word embeddings as a diagnostic tool for cognitive decline EMNLP 2025 MaXIFE: Multilingual and Cross-lingual Instruction Following Evaluation ACL 2025