On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance 事件

On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance arXiv:2606.00467v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used for zero-shot annotation and LLM-as-a-judge tasks, yet their reliability hinges on how model-internalized priors interact with user-provided instructions. We investigate three dimensions of this interaction: (1) how an LLM's familiarity with data and task definitions affects performance, (2) the e