DeepAI AI Chat
Log In Sign Up

ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks

by   Kai Xiong, et al.

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.


page 1

page 2

page 3

page 4


Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation

Causal reasoning ability is crucial for numerous NLP applications. Despi...

Neural Network Attributions: A Causal Perspective

We propose a new attribution method for neural networks developed using ...

On Open-Universe Causal Reasoning

We extend two kinds of causal models, structural equation models and sim...

Reasoning About Causal Models With Infinitely Many Variables

Generalized structural equations models (GSEMs) [Peters and Halpern 2021...

Predicting Directionality in Causal Relations in Text

In this work, we test the performance of two bidirectional transformer-b...

Structural Causal Models Are (Solvable by) Credal Networks

A structural causal model is made of endogenous (manifest) and exogenous...

Decomposing Counterfactual Explanations for Consequential Decision Making

The goal of algorithmic recourse is to reverse unfavorable decisions (e....