For Those Who May Find Themselves on the Red Team
It addresses the need for interdisciplinary involvement in AI interpretability, but is incremental as it builds on existing debates without introducing new empirical results.
The paper argues that literary scholars should engage with large language model interpretability research to challenge the current instrumental approaches, proposing the red team as a potential site for this engagement.
This position paper argues that literary scholars must engage with large language model (LLM) interpretability research. While doing so will involve ideological struggle, if not out-right complicity, the necessity of this engagement is clear: the abiding instrumentality of current approaches to interpretability cannot be the only standard by which we measure interpretation with LLMs. One site at which this struggle could take place, I suggest, is the red team.