Towards Interactive Language Modeling (2112.11911v2)
Abstract: Interaction between caregivers and children plays a critical role in human language acquisition and development. Given this observation, it is remarkable that explicit interaction plays little to no role in artificial LLMing -- which also targets the acquisition of human language, yet by artificial models. Moreover, an interactive approach to LLMing has the potential to make LLMs substantially more versatile and to considerably impact downstream applications. Motivated by these considerations, we pioneer the space of interactive LLMing. As a first contribution we present a road map in which we detail the steps that need to be taken towards interactive LLMing. We then lead by example and take the first steps on this road map, showing the initial feasibility of our approach. As such, this work aims to be the start of a larger research agenda on interactive LLMing.
- Maartje ter Hoeve (21 papers)
- Evgeny Kharitonov (5 papers)
- Dieuwke Hupkes (49 papers)
- Emmanuel Dupoux (81 papers)