Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Shuffles of Context-Free Languages Along Regular TrajectoriesAlphabet · arXiv (Cornell University)Jan 1IF-RewardBench: Benchmarking Judge Models for Instruction-Following EvaluationZhipu AI · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability CalibrationAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1CSPO: Alleviating Reward Ambiguity for Structured Table-to-LaTeX GenerationMicrosoft · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1How Controllable Are Large Language Models? A Unified Evaluation across Behavioral GranularitiesAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1ACR: Adaptive Context Refactoring via Context Refactoring Operators for Multi-Turn DialogueAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1Exploring Two-Phase Continual Instruction Fine-tuning for Multilingual Adaptation in Large Language ModelsMicrosoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1To Diff or Not to Diff? Structure-Aware and Adaptive Output Formats for Efficient LLM-based Code EditingAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1Why Steering Works: Toward a Unified View of Language Model Parameter DynamicsAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1Geoparsing: Diagram Parsing for Plane and Solid Geometry with a Unified Formal LanguageAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1PROBE: PROcess-Based BEnchmark for Hallucination DetectionNVIDIA · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African LanguagesMicrosoft · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1Understanding Emergent Misalignment via Feature Superposition GeometryGoogle DeepMind · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1Graph-Assisted Large Language Models: A Perspective on Mitigating Intrinsic LimitationsMicrosoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language ModelsMicrosoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1MemPO: Self-Memory Policy Optimization for Long-Horizon AgentsAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1On the Step Length Confounding in LLM Reasoning Data SelectionAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1Hierarchical Policy Optimization for Simultaneous Translation of Unbounded SpeechNVIDIA · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1Evaluating Language Model Pluralism through In-the-wild Crowd DiscussionsAllen Institute for AI · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language ModelsAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1Findings of the MAGMaR 2026 Shared TaskOpenAI · Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR)Jan 1IRIS: Interleaved Reinforcement with Incremental Staged Curriculum for Cross-Lingual Mathematical ReasoningNVIDIA · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1From Word to World: Can Large Language Models be Implicit Text-based World Models?Microsoft · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1Retrieval Heads are DynamicAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1I²B-LPO: Latent Policy Optimization via Iterative Information BottleneckAlibaba · Proceedings of the conference - Association for Computational Linguistics. MeetingJan 1