beam search

Assessing the Impact of Typological Features on Multilingual Machine Translation in the Age of Large Language Models EACL 2026 Character-Level Transformer for Tajik–Persian Transliteration with a Parallel Lexical Corpus EACL 2026 Deep Hidden Cognition Facilitates Reliable Chain-of-Thought Reasoning AAAI 2026 Diving into the Decoding Space of Non-Autoregressive Models via Lexically Constrained Search ACL 2026 Entropy-Gated Branching for Efficient Test-Time Reasoning EACL 2026 Think Hard Only When Needed: A Hybrid Best-of-N and Beam Search for Efficient Test-Time Compute EACL 2026 ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling ACL 2026 Accelerating LLM Reasoning via Early Rejection with Partial Reward Modeling EMNLP 2025 An Analysis of Scoring Methods for Reranking in Large Language Model Story Generation NAACL 2025 BeamLoRA: Beam-Constraint Low-Rank Adaptation ACL 2025 Beyond the Mode: Sequence-Level Distillation of Multilingual Translation Models for Low-Resource Language Pairs NAACL 2025 Beyond WER: Probing Whisper’s Sub‐token Decoder Across Diverse Language Resource Levels EMNLP 2025 BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving ACL 2025 ClozeMath: Improving Mathematical Reasoning in Language Models by Learning to Fill Equations ACL 2025 Collaborative Beam Search: Enhancing LLM Reasoning via Collective Consensus EMNLP 2025 Cross-Lingual Pitfalls: Automatic Probing Cross-Lingual Weakness of Multilingual Large Language Models ACL 2025 Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport ACL 2025 Dynamic-Width Speculative Beam Decoding for LLM Inference AAAI 2025 EBBS: An Ensemble with Bi-Level Beam Search for Zero-Shot Machine Translation AAAI 2025 Efficient Beam Search for Large Language Models Using Trie-Based Decoding EMNLP 2025 Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents ACL 2025 Enhancing Retrieval-Augmented Generation via Evidence Tree Search ACL 2025 Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators ICML 2025 Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models ICLR 2025 FiDeLiS: Faithful Reasoning in Large Language Models for Knowledge Graph Question Answering ACL 2025