Cause and Effect: Can Large Language Models Truly Understand Causality?
Proceedings of the AAAI Symposium Series · 08.11.2024 · 4 (1) · 2-9
DOI: 10.1609/aaaiss.v4i1.31764 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 08.11.2024. Verfasst von Swagata Ashwani und 8 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref).
Abstract (Originalsprache)
With the rise of Large Language Models (LLMs), it has become crucial to understand their capabilities and limitations in deciphering and explaining the complex web of causal relationships that language entails. Current methods use either explicit or implicit causal reasoning, yet there is a strong need for a unified approach combining both to tackle a wide array of causal relationships more effectively. This research proposes a novel architecture called Context-Aware Reasoning Enhancement with Counterfactual Analysis (CARE-CA) to enhance causal reasoning and explainability. The proposed framework incorporates an explicit causal detection module with ConceptNet and counterfactual statements, as well as implicit causal detection through LLMs. Our framework goes one step further with a layer of counterfactual explanations to accentuate LLMs' understanding of causality. The knowledge from ConceptNet enhances the performance of multiple causal reasoning tasks such as causal discovery, causal identification, and counterfactual reasoning. The counterfactual sentences add explicit knowledge of `not caused by' scenarios. By combining these powerful modules, our model aims to provide a deeper understanding of causal relationships, enabling enhanced interpretability. Evaluation of benchmark datasets shows improved performance across all metrics, such as accuracy, precision, recall, and F1 scores. We also present CausalNet, a novel dataset specifically curated to benchmark and enhance the causal reasoning capabilities of LLMs. This dataset is accompanied by code designed to facilitate further research in this domain.
Zitieren
APA
Ashwani, S., Hegde, K., Mannuru, N. R., Sengar, D. S., Jindal, M., Kathala, K. C. R., Banga, D., Jain, V., & Chadha, A. (2024). Cause and Effect: Can Large Language Models Truly Understand Causality?. Proceedings of the AAAI Symposium Series, 4(1), 2-9. https://doi.org/10.1609/aaaiss.v4i1.31764
Vancouver
Ashwani S, Hegde K, Mannuru NR, Sengar DS, Jindal M, Kathala KCR, et al. Cause and Effect: Can Large Language Models Truly Understand Causality?. Proceedings of the AAAI Symposium Series. 2024;4(1):2-9. doi:10.1609/aaaiss.v4i1.31764
BibTeX
@article{Ashwani2024,
author = {Ashwani, Swagata and Hegde, Kshiteesh and Mannuru, Nishith Reddy and Sengar, Dushyant Singh and Jindal, Mayank and Kathala, Krishna Chaitanya Rao and Banga, Dishant and Jain, Vinija and Chadha, Aman},
title = {Cause and Effect: Can Large Language Models Truly Understand Causality?},
journal = {Proceedings of the AAAI Symposium Series},
year = {2024},
volume = {4},
number = {1},
pages = {2--9},
doi = {10.1609/aaaiss.v4i1.31764}
}
EUVIMED