Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
CulturalRiddles: A Multicultural Benchmark of RiddlesCohere · arXiv (Cornell University)Oct 21StepBench: Diagnosing Real-World Procedural Understanding in AI AgentsCohere, Microsoft · arXiv (Cornell University)Oct 19AfriGuard: Safety and Robust Refusal For African LanguagesCohere · arXiv (Cornell University)Oct 19StepBench: Diagnosing Real-World Procedural Understanding in AI AgentsCohere, Microsoft · arXiv (Cornell University)Oct 19Epi: Towards a Persistent, Self-Improving Agent for Autonomous ResearchCohere, Microsoft · arXiv (Cornell University)Oct 18Zero-Shot Spoken Language Understanding with SLAM-ASR: What Do Monolingual ASR-Trained Linear Projectors Enable?Cohere · arXiv (Cornell University)Oct 14Turning Speech Language Models into Multilingual ListenersCohere · arXiv (Cornell University)Sep 27Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language ReasoningCohere · arXiv (Cornell University)Sep 9Multimedia Asset Personalization via Multimodal Embeddings at NetflixCohere · arXiv (Cornell University)Aug 18The IOL-AI Challenge: An Open Challenge towards Advancing Linguistic ReasoningCohere · arXiv (Cornell University)Aug 18Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical DiversityCohere · arXiv (Cornell University)Aug 13Memory-Efficient Activation Checkpointing with Sliding Window and Hirschberg's Algorithm for 0/1 Knapsack Solving in PyTorchCohere · arXiv (Cornell University)Aug 9An Actionable Diagnosis of Multilingual, Multi-Agent Planning FailuresCohere · arXiv (Cornell University)Aug 4MIMIC-Py: An Extensible Tool for Personality-Driven Automated Game Testing with Large Language ModelsCohere · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE)Jul 5Do Medical Vision Language Models Actually See? A Counterfactual Grounding Framework and Hard-Negative Contrastive Training for Visually-Reliant Medical VLMsCohere · arXiv (Cornell University)Jul 4JudgeArena: A Unified Framework for Reproducible LLM-Judge EvaluationCohere · arXiv (Cornell University)Jul 1SEATauBench: Progressively Adapting Tool-Agent-User Evaluation Into Low-Resource Southeast Asian LanguagesCohere · arXiv (Cornell University)Jun 27CALIBER: Calibrating Confidence Before and After Reasoning in Language ModelsCohere · arXiv (Cornell University)Jun 23Counsel: A Meta-Evaluation Dataset for Agentic TasksCohere, Google DeepMind, Mistral AI · arXiv (Cornell University)Jun 19The Culture Funnel: You Can't Align What isn't in the DataCohere · arXiv (Cornell University)Jun 11Soft-SVeRL: Self-Verified Reinforcement Learning with Soft RewardsCohere · arXiv (Cornell University)May 27Pinpointing Flakiness in Web Tests via DOM Event Analysis and LLM-based ReasoningCohere · IEEE International Conference on Software Testing, Verification and Validation (ICST)May 18Cohere Labs Community at FoodBench-QA 2026: The Cake Makes the IngredientsCohere · Language Resources and Evaluation Conference (LREC)May 1Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm TypesCohere · arXiv (Cornell University)Apr 10BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM EvaluationCohere · arXiv (Cornell University)Apr 10