paper-with-me

홈 › Papers

Counterfactual Reasoning with Knowledge Graph Embeddings

2024-03-11 · Lena Zellinger, Andreas Stephan, Benjamin Roth

Knowledge graph embeddings (KGEs) were originally developed to infer true but missing facts in incomplete knowledge repositories. In this paper, we link knowledge graph completion and counterfactual reasoning via our new task CFKGR. We model the original world state as a knowledge graph, hypothetical scenarios as edges added to the graph, and plausible changes to the graph as inferences from logical rules. We create corresponding benchmark datasets, which contain diverse hypothetical scenarios with plausible changes to the original knowledge graph and facts that should be retained. We develop COULDD, a general method for adapting existing knowledge graph embeddings given a hypothetical premise, and evaluate it on our benchmark. Our results indicate that KGEs learn patterns in the graph without explicit training. We further observe that KGEs adapted with COULDD solidly detect plausible counterfactual changes to the graph that follow these patterns. An evaluation on human-annotated data reveals that KGEs adapted with COULDD are mostly unable to recognize changes to the graph that do not follow learned inference rules. In contrast, ChatGPT mostly outperforms KGEs in detecting plausible changes to the graph but has poor knowledge retention. In summary, CFKGR connects two previously distinct areas, namely KG completion and counterfactual reasoning.

📄 PDF Abstract BibTeX arXiv:2403.06936

Code (1)

lenazellinger/counterfactual_kgr 공식 구현 pytorch

Tasks

counterfactualCounterfactual ReasoningKnowledge Graph CompletionKnowledge Graph Embeddings

Similar Papers 제목 키워드 기반

CausalKG: Causal Knowledge Graph Explainability using interventional and counterfactual reasoning

2022-01-06 · Utkarshani Jaimini, Amit Sheth

Humans use causality and hypothetical retrospection in their daily decision-making, planning, and understanding of life events. The human mind, while retrospecting a given situation, think about questions such as "What w…

counterfactualCounterfactual ReasoningDecision MakingKnowledge Graphs

Causal Cartographer: From Mapping to Reasoning Over Counterfactual Worlds

2025-05-20 · Gaël Gendron, Jože M. Rožanec, Michael Witbrock, Gillian Dobbie

Causal world models are systems that can answer counterfactual questions about an environment of interest, i.e. predict how it would have evolved if an arbitrary subset of events had been realized differently. It require…

Causal InferencecounterfactualCounterfactual ReasoningMemorization+1

Towards Loosely-Coupling Knowledge Graph Embeddings and Ontology-based Reasoning

2022-02-07 · Zoi Kaoudi, Abelardo Carlos Martinez Lorenzo, Volker Markl

Knowledge graph completion (a.k.a.~link prediction), i.e.,~the task of inferring missing information from knowledge graphs, is a widely used task in many applications, such as product recommendation and question answerin…

Graph EmbeddingKnowledge Graph CompletionKnowledge Graph EmbeddingKnowledge Graph Embeddings+5

Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG

2025-09-17 · Harshad Khadilkar, Abhay Gupta arxiv

Large language models (LLMs) have transformed natural language processing (NLP), enabling diverse applications by integrating large-scale pre-trained knowledge. However, their static knowledge limits dynamic reasoning ov…

Semantic Similarity

CounterBench: A Benchmark for Counterfactuals Reasoning in Large Language Models

2025-02-16 · Yuefei Chen, Vivek K. Singh, Jing Ma, Ruxiang Tang

Counterfactual reasoning is widely recognized as one of the most challenging and intricate aspects of causality in artificial intelligence. In this paper, we evaluate the performance of large language models (LLMs) in co…

Commonsense Causal ReasoningcounterfactualCounterfactual InferenceCounterfactual Reasoning