一作ACL 2026Poster· Natural Language Processing
Model Internal Sleuthing: Finding Lexical Identity and Inflectional Features in Modern Language Models
Michael Li · Nishant Subramani
摘要
Large transformer-based language models dominate modern NLP, yet our understanding of how they encode linguistic information relies primarily on studies of early models like BERT and GPT-2. We systematically probe 25 models from BERT Base to Qwen2.5-7B focusing on two linguistic properties: lexic...