Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Convergent Functions, Divergent FormsAllen Institute for AI · neural information processing systemsJan 1, 2025TinyScientist: An Interactive, Extensible, and Controllable Framework for Building Research AgentsAllen Institute for AI · Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP)Jan 1, 2025HypER: Literature-grounded Hypothesis Generation and Distillation with ProvenanceAllen Institute for AI · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025Critical Batch Size Revisited: A Simple Empirical Approach to Large-Batch Language Model TrainingAllen Institute for AI · neural information processing systemsJan 1, 2025Exact Expressive Power of Transformers with PaddingAllen Institute for AI · neural information processing systemsJan 1, 2025Datasets, Documents, and Repetitions: The Practicalities of Unequal Data QualityAllen Institute for AI, Anthropic, OpenAI · neural information processing systemsJan 1, 2025Signal and Noise: A Framework for Reducing Uncertainty in Language Model EvaluationAllen Institute for AI · neural information processing systemsJan 1, 2025First-Step Advantage: Importance of Starting Right in Multi-Step Math ReasoningAllen Institute for AI · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1, 2025Is It JUST Semantics? A Case Study of Discourse Particle Understanding in LLMsAllen Institute for AI · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1, 2025Superlatives in Context: Modeling the Implicit Semantics of SuperlativesAllen Institute for AI · Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)Jan 1, 2025Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task SupervisionAllen Institute for AI · Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)Jan 1, 2025A Systematic Examination of Preference Learning through the Lens of Instruction-FollowingAllen Institute for AI · Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)Jan 1, 2025ComPO: Community Preferences for Language Model PersonalizationAllen Institute for AI · Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)Jan 1, 2025Social Intelligence in the Age of LLMsAllen Institute for AI · Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)Jan 1, 2025A Practical Method for Generating String CounterfactualsAllen Institute for AI · Findings of the Association for Computational Linguistics: NAACLJan 1, 2025When Worse is Better: Navigating the Compression Generation Trade-off In Visual TokenizationAllen Institute for AI, Meta · neural information processing systemsJan 1, 2025