Déjà Vu: Multilingual LLM Evaluation through the Lens of Machine Translation Evaluation | Cohere | Research | TechiSeek

AddAdd your Listings

Research

Déjà Vu: Multilingual LLM Evaluation through the Lens of Machine Translation Evaluation

Generation capabilities and language coverage of multilingual large language models (mLLMs) are advancing rapidly.

Research Cohere

ResearchRLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMsCohere ResearchRewardBench 2: Advancing Reward Model EvaluationCohere ResearchThe Multilingual Divide and Its Impact on Global AI SafetyCohere ResearchLLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable ObjectivesCohere ResearchCIRCLE: A Framework for Evaluating AI from a Real-World LensCohere ResearchReality Check: A New Evaluation Ecosystem Is Necessary to Understand AI's Real World EffectsCohere NewsMachine Learning Algorithm Sidesteps the Scientific MethodThenewstack BlogsHow Eisan made POS analytics faster, cheaper, and more reliable with ClickHouse CloudClickhouse BlogsFixing Headlamp OIDC login with Tailscale and tsidpTailscale BlogsWhat a $20 Claude Code or Codex subscription actually buys, per ApertureTailscale BlogsAccelerating Code Completion with Fireworks Fast LLM InferenceFireworks

BlogsA decade of governance: Cloud Custodian at 10 and its role in the agentic AI eraCncf BlogsRegistry Mirror Authentication with Kubernetes SecretsCncf BlogsHow to Translate Video into Any Language with AIHeygen BlogsLocalize Your Ads and Boost ROAS with AI Video TranslationHeygen BlogsImproving Composer through real-time RL · CursorCursor BlogsContinually improving our agent harness · CursorCursor BlogsA technical report on Composer 2 · CursorCursor BlogsIntroducing Commenting on Preview DeploymentsVercel Products & ServicesNew this month: Performance upgrades, better LLM support, new blocks and moreGitbook