Can Large Language Models Learn Independent Causal Mechanisms? · The Large Language Model Bible Contribute to LLM-Bible

Can Large Language Models Learn Independent Causal Mechanisms?

Gendron Gaƫl, Nguyen Bao Trung, Peng Alex Yuxuan, Witbrock Michael, Dobbie Gillian. Arxiv 2024

[Paper]    
Fine Tuning Model Architecture Pretraining Methods Security Training Techniques

Despite impressive performance on language modelling and complex reasoning tasks, Large Language Models (LLMs) fall short on the same tasks in uncommon settings or with distribution shifts, exhibiting a lack of generalisation ability. By contrast, systems such as causal models, that learn abstract variables and causal relationships, can demonstrate increased robustness against changes in the distribution. One reason for this success is the existence and use of Independent Causal Mechanisms (ICMs) representing high-level concepts that only sparsely interact. In this work, we apply two concepts from causality to learn ICMs within LLMs. We develop a new LLM architecture composed of multiple sparsely interacting language modelling modules. We show that such causal constraints can improve out-of-distribution performance on abstract and causal reasoning tasks. We also investigate the level of independence and domain specialisation and show that LLMs rely on pre-trained partially domain-invariant mechanisms resilient to fine-tuning.

Similar Work