Shaping Shared Languages: Human and Large Language Models' Inductive Biases in Emergent Communication
This addresses the problem of aligning human and machine communication by showing how inductive biases affect emergent languages, though it is incremental as it builds on classical referential game paradigms.
The study investigated how artificial languages evolve when optimized for human versus LLM inductive biases using referential games, finding that referentially grounded vocabularies emerged reliably across all conditions, with human-LLM interactions producing more human-like languages than LLM-LLM ones.
Languages are shaped by the inductive biases of their users. Using a classical referential game, we investigate how artificial languages evolve when optimised for inductive biases in humans and large language models (LLMs) via Human-Human, LLM-LLM and Human-LLM experiments. We show that referentially grounded vocabularies emerge that enable reliable communication in all conditions, even when humans \textit{and} LLMs collaborate. Comparisons between conditions reveal that languages optimised for LLMs subtly differ from those optimised for humans. Interestingly, interactions between humans and LLMs alleviate these differences and result in vocabularies more human-like than LLM-like. These findings advance our understanding of the role inductive biases in LLMs play in the dynamic nature of human language and contribute to maintaining alignment in human and machine communication. In particular, our work underscores the need to think of new LLM training methods that include human interaction and shows that using communicative success as a reward signal can be a fruitful, novel direction.