AI RESEARCH
How Hypocritical Is Your LLM judge? Listener-Speaker Asymmetries in the Pragmatic Competence of Large Language Models
arXiv CS.CL
•
ArXi:2604.15873v1 Announce Type: new Large language models (LLMs) are increasingly studied as repositories of linguistic knowledge. In this line of work, models are commonly evaluated both as generators of language and as judges of linguistic output, yet these two roles are rarely examined in direct relation to one another. As a result, it remains unclear whether success in one role aligns with success in the other.