FIELD NOTES TOPIC
evaluation protocols
2 notes, newest first.
Adversarial Pragmatics for AI Safety Evaluation: A Benchmark for Instruction Conflict, Embedded Commands, and Policy Ambiguity
The text introduces 'adversarial pragmatics', a new benchmark and annotation protocol to evaluate the behavior of language models in various ambiguous situations. The goal is to clarify whether failures occur due to…
Towards Continual Motion-Language Agents: LoRA Variants for Incremental Motion Understanding and Generation
The paper presents a new method to create motion-language agents that can understand and generate human movements in dynamic environments without forgetting previously acquired skills. The method, called LoRA variants…
