Language Modeling

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache ICML 2025 RAP: A Metric for Balancing Repetition and Performance in Open-Source Large Language Models NAACL 2025 RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding ICML 2025 RATIONALYST: Pre-training Process-Supervision for Improving Reasoning ACL 2025 R-BPE: Improving BPE-Tokenizers with Token Reuse EMNLP 2025 Re3Syn: A Dependency-Based Data Synthesis Framework for Long-Context Post-training ACL 2025 Realistic Training Data Generation and Rule Enhanced Decoding in LLM for NameGuess EMNLP 2025 Reasoning Enhanced Missing Knowledge Retrieval Augmented Generation Framework for Domain Specific Question Answering IJCNLP 2025 ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement ICLR 2025 Regress, Don’t Guess: A Regression-like Loss on Number Tokens for Language Models ICML 2025 Representations of Fact, Fiction and Forecast in Large Language Models: Epistemics and Attitudes ACL 2025 Restoring Missing Spaces in Scraped Hebrew Social Media NAACL 2025 Rethinking the Role of Text Complexity in Language Model Pretraining EMNLP 2025 Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning ACL 2025 Retrofitting Large Language Models with Dynamic Tokenization ACL 2025 Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks ICML 2025 Revisiting Chain-of-Thought in Code Generation: Do Language Models Need to Learn Reasoning before Coding? ICML 2025 Revisiting In-Context Learning with Long Context Language Models ACL 2025 Revisiting Word Embeddings in the LLM Era IJCNLP 2025 RISCORE: Enhancing In-Context Riddle Solving in Language Models through Context-Reconstructed Example Augmentation COLING 2025 Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions ICLR 2025 Rubic2: Ensemble Model for Russian Lemmatization ACL 2025 SabiYarn: Advancing Low Resource Languages with Multitask NLP Pretraining ACL 2025 SAKI-RAG: Mitigating Context Fragmentation in Long-Document RAG via Sentence-level Attention Knowledge Integration EMNLP 2025 Sample-Efficient Language Modeling with Linear Attention and Lightweight Enhancements EMNLP 2025