beam search

G2: Guided Generation for Enhanced Output Diversity in LLMs EMNLP 2025 Gatsby without the ‘E’: Creating Lipograms with LLMs IJCNLP 2025 Guideline Compliance in Task-Oriented Dialogue: The Chained Prior Approach NAACL 2025 HARP: Hesitation-Aware Reframing in Transformer Inference Pass NAACL 2025 Is Incremental Structure Prediction Process Universal across Languages?: Revisiting Parsing Strategy through Speculation CoNLL 2025 Just One is Enough: An Existence-based Alignment Check for Robust Japanese Pronunciation Estimation EMNLP 2025 Learning to Search Effective Example Sequences for In-Context Learning NAACL 2025 Mixture of Small and Large Models for Chinese Spelling Check ACL 2025 NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding Interspeech 2025 Positive Text Reframing under Multi-strategy Optimization COLING 2025 PropRAG: Guiding Retrieval with Beam Search over Proposition Paths EMNLP 2025 Question-guided Insights Generation for Automated Exploratory Data Analysis AAAI 2025 Revealing the Unwritten: Visual Investigation of Beam Search Trees to Address Language Model Prompting Challenges ACL 2025 Scaling Combinatorial Optimization Neural Improvement Heuristics with Online Search and Adaptation AAAI 2025 SKALD: Learning-Based Shot Assembly for Coherent Multi-Shot Video Creation ICCV 2025 Smarter, Not Harder: Training-Free Adaptive Computation for Transformers ACL 2025 Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs’ Reasoning EMNLP 2025 Supervised Optimism Correction: Be Confident When LLMs Are Sure ACL 2025 UvA-MT’s Participation in the WMT25 General Translation Shared Task EMNLP 2025 WIND: Accelerated RNN-T Decoding with Windowed Inference for Non-blank Detection Interspeech 2025 A Call for Clarity in Beam Search: How It Works and When It Stops COLING 2024 A Decoding Algorithm for Length-Control Summarization Based on Directed Acyclic Transformers EMNLP 2024 A Thorough Examination of Decoding Methods in the Era of LLMs EMNLP 2024 Automatic Engineering of Long Prompts ACL 2024 BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering ACL 2024