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

arXiv: https://arxiv.org/abs/2212.08322 · HTML: https://mlsanity.com/paper/2212.08322/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 35 references that are in the map.
- First posted on arXiv 16 Dec 2022.

## Builds on (most cited first, 12 of 12)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [Revisiting Pre-Trained Models for Chinese Natural Language Processing](https://mlsanity.com/paper/2004.13922/) (2020)
- [Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering](https://mlsanity.com/paper/1911.10470/) (2019)
- [Event2Mind: Commonsense Inference on Events, Intents, and Reactions](https://mlsanity.com/paper/1805.06939/) (2018)
- [e-CARE: a New Dataset for Exploring Explainable Causal Reasoning](https://mlsanity.com/paper/2205.05849/) (2022)
- [Guided Generation of Cause and Effect](https://mlsanity.com/paper/2107.09846/) (2021)
- [CausalBERT: Injecting Causal Knowledge Into Pre-trained Models with Minimal Supervision](https://mlsanity.com/paper/2107.09852/) (2021)
- [Learning to Rank for Plausible Plausibility](https://mlsanity.com/paper/1906.02079/) (2019)
- [ELG: An Event Logic Graph](https://mlsanity.com/paper/1907.08015/) (2019)

## Built on by (most cited first, 1 of 1)

- [Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance](https://mlsanity.com/paper/2403.09085/) (2024)

## Abstract (arXiv)

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.