Plausibility Processing in Transformer Language Models: Focusing on the Role of Attention Heads in GPT
This work addresses the problem of understanding semantic processing in AI models for researchers in NLP and cognitive science, but it is incremental as it builds on existing knowledge of attention mechanisms.
The paper investigates how Transformer language models, specifically GPT2, process semantic knowledge about noun-verb plausibility, finding that GPT2 shows higher similarity to humans than other models and that specific attention heads detect and contribute to this ability, though individual head performance does not correlate with overall contribution.
The goal of this paper is to explore how Transformer language models process semantic knowledge, especially regarding the plausibility of noun-verb relations. First, I demonstrate GPT2 exhibits a higher degree of similarity with humans in plausibility processing compared to other Transformer language models. Next, I delve into how knowledge of plausibility is contained within attention heads of GPT2 and how these heads causally contribute to GPT2's plausibility processing ability. Through several experiments, it was found that: i) GPT2 has a number of attention heads that detect plausible noun-verb relationships; ii) these heads collectively contribute to the Transformer's ability to process plausibility, albeit to varying degrees; and iii) attention heads' individual performance in detecting plausibility does not necessarily correlate with how much they contribute to GPT2's plausibility processing ability.