Generation

Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models ACL 2025 Bengali ChartSumm: A Benchmark Dataset and study on feasibility of Large Language Models on Bengali Chart to Text Summarization COLING 2025 BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute ICML 2025 Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases ACL 2025 Between the Drafts: An Evaluation Framework for Identifying Quality Improvement and Stylistic Differences in Scientific Texts AACL 2025 Beyond Autoregression: Fast LLMs via Self-Distillation Through Time ICLR 2025 Beyond Binary Preferences: Semi-Online Label-Free GRACE-KTO with Group-Wise Adaptive Calibration for High-Quality Long-Text Generation EMNLP 2025 Beyond Cairo: Sa’idi Egyptian Arabic Literary Corpus Construction and Analysis NAACL 2025 Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs COLING 2025 Beyond Coarse Labels: Fine-Grained Problem Augmentation and Multi-Dimensional Feedback for Emotional Support Conversation EMNLP 2025 Beyond Dialogue: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Model ACL 2025 Beyond Discrete Personas: Personality Modeling Through Journal Intensive Conversations COLING 2025 Beyond Distribution: Investigating Language Models’ Understanding of Sino-Korean Morphemes EMNLP 2025 Beyond Factual Accuracy: Evaluating Coverage of Diverse Factual Information in Long-form Text Generation ACL 2025 Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines ACL 2025 Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification ICLR 2025 Beyond Next Token Prediction: Patch-Level Training for Large Language Models ICLR 2025 Beyond N-Grams: Rethinking Evaluation Metrics and Strategies for Multilingual Abstractive Summarization ACL 2025 Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models EMNLP 2025 Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMs ACL 2025 Beyond Reconstruction: Generating Privacy-Preserving Clinical Letters NAACL 2025 Beyond Repetition: Text Simplification and Curriculum Learning for Data-Constrained Pretraining EMNLP 2025 Beyond Sequences: Two-dimensional Representation and Dependency Encoding for Code Generation ACL 2025 Beyond Single-User Dialogue: Assessing Multi-User Dialogue State Tracking Capabilities of Large Language Models EMNLP 2025 Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents EMNLP 2025