Language hooks: a modular framework for augmenting LLM reasoning that decouples tool usage from the model and its prompt

TL;DR

The paper introduces language hooks, a modular framework that enhances language models with new capabilities by decoupling tool usage from prompts and the model, enabling better generalization and flexibility.

Contribution

It proposes a novel framework called language hooks that allows modular, decoupled augmentation of language models with new capabilities, improving flexibility and generalization.

Findings

Outperforms state-of-the-art task-aware baselines

Demonstrates strong generalization to unseen tasks

Enables modular integration of external tools

Abstract

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.