ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks
This work addresses reliability issues in causal chain reasoning for decision-making AI systems, representing an incremental improvement with specific gains in accuracy.
The paper tackles the problem of causal chain reasoning (CCR) in AI systems, which suffers from threshold effect and scene drift issues, by proposing the ReCo framework that uses exogenous variables and structural causal recurrent neural networks to address these contradictions, resulting in outperforming strong baselines on Chinese and English datasets and improving BERT's performance on downstream causal-related tasks.
Causal chain reasoning (CCR) is an essential ability for many decision-making AI systems, which requires the model to build reliable causal chains by connecting causal pairs. However, CCR suffers from two main transitive problems: threshold effect and scene drift. In other words, the causal pairs to be spliced may have a conflicting threshold boundary or scenario. To address these issues, we propose a novel Reliable Causal chain reasoning framework~(ReCo), which introduces exogenous variables to represent the threshold and scene factors of each causal pair within the causal chain, and estimates the threshold and scene contradictions across exogenous variables via structural causal recurrent neural networks~(SRNN). Experiments show that ReCo outperforms a series of strong baselines on both Chinese and English CCR datasets. Moreover, by injecting reliable causal chain knowledge distilled by ReCo, BERT can achieve better performances on four downstream causal-related tasks than BERT models enhanced by other kinds of knowledge.