language model

On Linear Representations and Pretraining Data Frequency in Language Models ICLR 2025 Online Preference Alignment for Language Models via Count-based Exploration ICLR 2025 Only a Little to the Left: A Theory-grounded Measure of Political Bias in Large Language Models ACL 2025 On Pruning State-Space LLMs EMNLP 2025 On Support Samples of Next Word Prediction ACL 2025 On the Correspondence between the Squared Norm and Information Content in Text Embeddings EMNLP 2025 On the Interplay between Positional Encodings, Morphological Complexity, and Word Order Flexibility IJCNLP 2025 On The Origin of Cultural Biases in Language Models: From Pre-training Data to Linguistic Phenomena NAACL 2025 On the Role of Attention Heads in Large Language Model Safety ICLR 2025 On the Transferability of Causal Knowledge for Language Models NAACL 2025 Open-DeBias: Toward Mitigating Open-Set Bias in Language Models EMNLP 2025 OpenPRM: Building Open-domain Process-based Reward Models with Preference Trees ICLR 2025 Optimising Factual Consistency in Summarisation via Preference Learning from Multiple Imperfect Metrics EMNLP 2025 Optimizing Cross-Client Domain Coverage for Federated Instruction Tuning of Large Language Models EMNLP 2025 Optimizing Hidden Markov Language Models: An Empirical Study of Reparameterization and Initialization Techniques NAACL 2025 Optimizing Language Models for Inference Time Objectives using Reinforcement Learning ICML 2025 “Otherwise” in Context: Exploring Discourse Functions with Language Models EMNLP 2025 OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literature EMNLP 2025 PanicToCalm: A Proactive Counseling Agent for Panic Attacks EMNLP 2025 ParamΔ for Direct Mixing: Post-Train Large Language Model At Zero Cost ICLR 2025 Paraphrase Generation Evaluation Powered by an LLM: A Semantic Metric, Not a Lexical One COLING 2025 Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning EMNLP 2025 PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks ICLR 2025 Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs ICLR 2025 Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents ICLR 2025