Language Modeling

Respond in my Language: Mitigating Language Inconsistency in Response Generation based on Large Language Models ACL 2024 Rethinking the Reversal Curse of LLMs: a Prescription from Human Knowledge Reversal EMNLP 2024 [RETRACTED] Vikhr: Constructing a State-of-the-art Bilingual Open-Source Instruction-Following Large Language Model for Russian EMNLP 2024 Revisiting Character-level Adversarial Attacks for Language Models ICML 2024 Robust Evaluation Measures for Evaluating Social Biases in Masked Language Models AAAI 2024 Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts NeurIPS 2024 SAAS: Solving Ability Amplification Strategy for Enhanced Mathematical Reasoning in Large Language Models EMNLP 2024 Scaling Laws for Linear Complexity Language Models EMNLP 2024 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies NeurIPS 2024 Scaling Retrieval-Based Language Models with a Trillion-Token Datastore NeurIPS 2024 SciPrompt: Knowledge-augmented Prompting for Fine-grained Categorization of Scientific Topics EMNLP 2024 SEGMENT+: Long Text Processing with Short-Context Language Models EMNLP 2024 Selective Attention: Enhancing Transformer through Principled Context Control NeurIPS 2024 Self-Alignment with Instruction Backtranslation ICLR 2024 Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations EMNLP 2024 Self-Evolving GPT: A Lifelong Autonomous Experiential Learner ACL 2024 Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards EMNLP 2024 Self-Infilling Code Generation ICML 2024 Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models ICML 2024 Self-playing Adversarial Language Game Enhances LLM Reasoning NeurIPS 2024 Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels NeurIPS 2024 Semformer: Transformer Language Models with Semantic Planning EMNLP 2024 Semiparametric Token-Sequence Co-Supervision ACL 2024 Sequence Reducible Holdout Loss for Language Model Pretraining COLING 2024 Sequence-to-Sequence Spanish Pre-trained Language Models COLING 2024