一作ACL 2026Findings· Findings of ACL
How Hypocritical Is Your LLM judge? Listener-Speaker Asymmetries in the Pragmatic Competence of Large Language Models
Judith Sieker · Sina Zarrieß
摘要
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 res...