evaluation

RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models

The ability of language models in RAG systems to selectively refuse to answer based on flawed context is critical for safety, yet remains a significant failure point. Our large-scale study reveals that even frontier models struggle in this setting, …

HyTER: Meaning-Equivalent Semantics for Translation Evaluation

It is common knowledge that translation is an ambiguous, 1-to-n mapping process, but to date, our community has produced no empirical estimates of this ambiguity. We have developed an annotation tool that enables us to create representations that …