CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models
By: Kairong Han , Wenshuo Zhao , Ziyu Zhao and more
Potential Business Impact:
Teaches computers to understand cause and effect.
Large Language Models (LLMs) have achieved remarkable success across various domains. However, a fundamental question remains: Can LLMs effectively utilize causal knowledge for prediction and generation? Through empirical studies, we find that LLMs trained directly on large-scale data often capture spurious correlations rather than true causal relationships, leading to suboptimal performance, especially in out-of-distribution (OOD) scenarios. To address this challenge, we propose Causal Attention Tuning (CAT), a novel approach that injects fine-grained causal knowledge into the attention mechanism. We propose an automated pipeline that leverages human priors to automatically generate token-level causal signals and introduce the Re-Attention mechanism to guide training, helping the model focus on causal structures while mitigating noise and biases in attention scores. Experimental results on our proposed Spurious Token Game (STG) benchmark and multiple downstream tasks demonstrate that our approach effectively leverages causal knowledge for prediction and remains robust in OOD scenarios. Implementation details can be found at https://github.com/Kairong-Han/CAT.
Similar Papers
CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models
Computation and Language
Teaches computers to understand cause and effect.
Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning
Computation and Language
Helps AI focus on important information, not distractions.
Attention and Compression is all you need for Controllably Efficient Language Models
Machine Learning (CS)
Lets computers remember more with less effort.