Large language models and the treaty interpretation game

Abstract

Large language models (LLMs) are currently disrupting law. Yet their precise impact on international law, especially treaty interpretation, remains underexplored. Treaty interpretation can be analogised to a game in which ‘players’ strategically deploy ‘cards’, usually principles of treaty interpretation, to persuade an ‘audience’ that their interpretation is correct. Leveraging this analogy, this paper offers a limited case study of how OpenAI’s ChatGPT, a prominent LLM-based chatbot, navigates the treaty interpretation game. In line with the existing research on ChatGPT’s legal abilities, the author concludes that ChatGPT competently plays the treaty interpretation game. This conclusion leads to a broader discussion of how LLM usage may impact international law’s development. The argument advanced is that, while LLMs have the potential to enhance efficiency and accessibility, biased training data and interpretative standardisation could reinforce international law’s dominant narratives. As such, this paper concludes with a cautionary note: the potential gains derived from LLMs risk being offset by disciplinary stagnation.