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

• URL: http://arxiv.org/abs/2212.08322v1
• Date: Fri, 16 Dec 2022 07:48:02 GMT
• Title: ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks
• Abstract summary: We propose a novel Reliable Causal chain reasoning framework(ReCo) Experiments show that ReCo outperforms a series of strong baselines on both Chinese and English CCR datasets. BERT can achieve better performances on four downstream causal-related tasks than BERT models enhanced by other kinds of knowledge.
• Score: 32.537505018598736
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Time Series Causal Discovery via Context-Conditioned and Causality-Augmented Pretraining [17.01926647313838]
  Causal discovery from time series is critical for many real-world applications, such as tracing the root causes of anomalies.<n>We propose textbfPTCD, a novel textbfPretraining framework for textbfTime-series textbfCausal textbfDiscovery.
  arXiv  Detail & Related papers  (2026-05-26T09:30:42Z)
• Are Reasoning LLMs Robust to Interventions on Their Chain-of-Thought? [79.86483056611105]
  Reasoning LLMs generate step-by-step chains of thought before giving an answer.<n>How robust are these reasoning traces to disruptions that occur within them?<n>We introduce a controlled evaluation framework that perturbs a model's own CoT at fixed timesteps.
  arXiv  Detail & Related papers  (2026-02-07T10:02:58Z)
• Assessing LLM Reasoning Through Implicit Causal Chain Discovery in Climate Discourse [22.71538103040959]
  This work scrutinizes the mechanistic causal reasoning capabilities of large language models.<n>We generate all possible intermediate causal steps linking given cause-effect pairs in causal chain structures.
  arXiv  Detail & Related papers  (2025-10-15T11:15:00Z)
• AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models [62.70575022567081]
  We propose AdvChain, an alignment paradigm that teaches models dynamic self-correction through adversarial CoT tuning.<n>Our work establishes a new direction for building more robust and reliable reasoning models.
  arXiv  Detail & Related papers  (2025-09-29T04:27:23Z)
• Correlation or Causation: Analyzing the Causal Structures of LLM and LRM Reasoning Process [15.790468401903874]
  This study contributes to the understanding of causality in reasoning models and provides insights for designing future AI systems with stronger causal foundations.<n>Our findings reveal that RLVR-trained LRMs exhibit enhanced causal reasoning capabilities, aligning more closely with ideal causal structures.
  arXiv  Detail & Related papers  (2025-09-22T06:44:44Z)
• ChainReaction! Structured Approach with Causal Chains as Intermediate Representations for Improved and Explainable Causal Video Question Answering [13.950975794272603]
  We propose a novel framework that explicitly decouples causal reasoning from answer generation.<n>Inspired by human cognitive models, structured cause-effect sequences bridge low-level video content with high-level causal reasoning.<n>We also propose CauCo, a new evaluation metric for causality-oriented captioning.
  arXiv  Detail & Related papers  (2025-08-28T17:10:53Z)
• Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers [76.42159902257677]
  We argue that both behaviors stem from a single mechanism known as out-of-context reasoning (OCR)<n>OCR drives both generalization and hallucination, depending on whether the associated concepts are causally related.<n>Our work provides a theoretical foundation for understanding the OCR phenomenon, offering a new lens for analyzing and mitigating undesirable behaviors from knowledge injection.
  arXiv  Detail & Related papers  (2025-06-12T16:50:45Z)
• Graph-of-Causal Evolution: Challenging Chain-of-Model for Reasoning [4.586907225774023]
  This work proposes a graph of causal evolution (GoCE)<n>GoCE maps the implicit token representation into a differentiable and sparse causal adjacency matrix, then permeate causal constraints through each layer of calculation.<n>It is evaluated on publicly available datasets including CLUTRR, CLADDER, EX-FEVER, and CausalQA.
  arXiv  Detail & Related papers  (2025-06-09T07:26:47Z)
• Argument-Centric Causal Intervention Method for Mitigating Bias in Cross-Document Event Coreference Resolution [12.185497507437555]
  Cross-document Event Coreference Resolution (CD-ECR) seeks to determine whether event mentions across multiple documents refer to the same real-world occurrence.<n>We propose a novel method based on Argument-Centric Causal Intervention (ACCI)<n>ACCI integrates a counterfactual reasoning module that quantifies the causal influence of trigger word perturbations, and an argument-aware enhancement module to promote greater sensitivity to semantically grounded information.
  arXiv  Detail & Related papers  (2025-06-02T09:46:59Z)
• A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generation [59.473751744275496]
  Scene Graph Generation (SGG) frameworks typically incorporate a detector to extract relationship features and a classifier to categorize these relationships.<n>Such a causal chain structure can yield spurious correlations between the detector's inputs and the final predictions.<n>We propose reconstructing the causal chain structure into a reverse causal structure, wherein the classifier's inputs are treated as the confounder.
  arXiv  Detail & Related papers  (2025-05-29T13:57:01Z)
• CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation [3.8808821719659763]
  We introduce Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation (CDF-RAG) CDF-RAG iteratively refines queries, retrieves structured causal graphs, and enables multi-hop causal reasoning across interconnected knowledge sources. We evaluate CDF-RAG on four diverse datasets, demonstrating its ability to improve response accuracy and causal correctness over existing RAG-based methods.
  arXiv  Detail & Related papers  (2025-04-17T01:15:13Z)
• Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs [63.36637269634553]
  We introduce a novel approach where LLMs are fine-tuned to generate a sequence of Diverse Chains of Thought (DCoT) within a single inference step.<n>We show that fine-tuning on DCoT improves performance over the CoT baseline across model families and scales.<n>Our work is also significant because both quantitative analyses and manual evaluations reveal the observed gains stem from the models' ability to refine an initial reasoning chain.
  arXiv  Detail & Related papers  (2024-07-03T15:01:18Z)
• Deep Causal Generative Models with Property Control [11.604321459670315]
  We propose a novel deep generative framework called the Correlation-aware Causal Variational Auto-encoder (C2VAE) C2VAE simultaneously recovers the correlation and causal relationships between properties using disentangled latent vectors.
  arXiv  Detail & Related papers  (2024-05-25T13:07:27Z)
• Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning [21.951313919964484]
  Large language models exhibit high-level commonsense reasoning abilities. CoT-like methods lead to a considerable number of originally correct answers turning wrong. We use attribution tracing and causal tracing methods to probe the internal working mechanism of the model.
  arXiv  Detail & Related papers  (2024-02-28T14:09:02Z)
• Identifiable Latent Polynomial Causal Models Through the Lens of Change [82.14087963690561]
  Causal representation learning aims to unveil latent high-level causal representations from observed low-level data. One of its primary tasks is to provide reliable assurance of identifying these latent causal models, known as identifiability.
  arXiv  Detail & Related papers  (2023-10-24T07:46:10Z)
• Inducing Causal Structure for Abstractive Text Summarization [76.1000380429553]
  We introduce a Structural Causal Model (SCM) to induce the underlying causal structure of the summarization data. We propose a Causality Inspired Sequence-to-Sequence model (CI-Seq2Seq) to learn the causal representations that can mimic the causal factors. Experimental results on two widely used text summarization datasets demonstrate the advantages of our approach.
  arXiv  Detail & Related papers  (2023-08-24T16:06:36Z)
• Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanisms [17.074858228123706]
  We propose a framework for learning causally disentangled representations supervised by causally related observed labels. We show that our framework induces highly disentangled causal factors, improves interventional robustness, and is compatible with counterfactual generation.
  arXiv  Detail & Related papers  (2023-06-02T00:28:48Z)
• Hierarchical Graph Neural Networks for Causal Discovery and Root Cause Localization [52.72490784720227]
  REASON consists of Topological Causal Discovery and Individual Causal Discovery. The Topological Causal Discovery component aims to model the fault propagation in order to trace back to the root causes. The Individual Causal Discovery component focuses on capturing abrupt change patterns of a single system entity.
  arXiv  Detail & Related papers  (2023-02-03T20:17:45Z)
• Causal Lifting and Link Prediction [10.336445584242933]
  We develop the first causal model capable of dealing with path dependencies in link prediction. We show how structural pairwise embeddings exhibit lower bias and correctly represent the task's causal structure. We validate our theoretical findings on three scenarios for causal link prediction tasks.
  arXiv  Detail & Related papers  (2023-02-02T16:25:16Z)
• Variational Causal Networks: Approximate Bayesian Inference over Causal Structures [132.74509389517203]
  We introduce a parametric variational family modelled by an autoregressive distribution over the space of discrete DAGs. In experiments, we demonstrate that the proposed variational posterior is able to provide a good approximation of the true posterior.
  arXiv  Detail & Related papers  (2021-06-14T17:52:49Z)
• Causal Inference Q-Network: Toward Resilient Reinforcement Learning [57.96312207429202]
  We consider a resilient DRL framework with observational interferences. Under this framework, we propose a causal inference based DRL algorithm called causal inference Q-network (CIQ) Our experimental results show that the proposed CIQ method could achieve higher performance and more resilience against observational interferences.
  arXiv  Detail & Related papers  (2021-02-18T23:50:20Z)
• Causal discovery of linear non-Gaussian acyclic models in the presence of latent confounders [6.1221613913018675]
  This paper proposes a causal functional model-based method called repetitive causal discovery (RCD) to discover the causal structure of observed variables affected by latent confounders. RCD repeats inferring the causal directions between a small number of observed variables and determines whether the relationships are affected by latent confounders.
  arXiv  Detail & Related papers  (2020-01-13T12:55:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.