Prompting and fine-tuning have emerged as two competing paradigms for augmenting language models with new capabilities, such as the use of tools. Prompting approaches are quick to set up but rely on providing explicit demonstrations of each tool's usage in the model's prompt, thus coupling tool use to the task at hand and limiting generalisation. Fine-tuning removes the need for task-specific demonstrations of tool usage at runtime; however, this ties new capabilities to a single model, thus making already-heavier setup costs a recurring expense. In this paper, we introduce language hooks, a novel framework for augmenting language models with new capabilities that is decoupled both from the model's task-specific prompt and from the model itself. The language hook algorithm interleaves text generation by the base model with the execution of modular programs that trigger conditionally based on the existing text and the available capabilities. Upon triggering, programs may call external tools, auxiliary language models (e.g. using tool specific prompts), and modify the existing context. We benchmark our method against state-of-the-art baselines, find that it outperforms task-aware approaches, and demonstrate its ability to generalise to novel tasks.

Prof. Jan Scholtes of the University of Maastricht and CSO at ZyLAB today presented a lecture at the Raad van State (the Dutch Council of State), entitled "Artificial Intelligence and Law". The lecture focuses on "Machine Learning" as the new search. The theme, also used in a series of four blogs, elaborates on the "Big Data and Data Science training" that Prof. Scholtes, together with Prof. van den Herik of the Leiden Center of Data Science (LDCS), provides to a group of 20 Dutch judges. In his lecture, Prof. Scholtes emphasizes the recent advances in Artificial Intelligence (AI). Especially compared to the first developments of AI almost 70 years ago, things are accelerating rapidly.