Salvato in:
Dettagli Bibliografici
Autori principali: Ishay, Adam, Yang, Zhun, Lee, Joohyung, Kang, Ilgu, Lim, Dongjae
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.10753
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911002191200256
author Ishay, Adam
Yang, Zhun
Lee, Joohyung
Kang, Ilgu
Lim, Dongjae
author_facet Ishay, Adam
Yang, Zhun
Lee, Joohyung
Kang, Ilgu
Lim, Dongjae
contents Causal and temporal reasoning about video dynamics is a challenging problem. While neuro-symbolic models that combine symbolic reasoning with neural-based perception and prediction have shown promise, they exhibit limitations, especially in answering counterfactual questions. This paper introduces a method to enhance a neuro-symbolic model for counterfactual reasoning, leveraging symbolic reasoning about causal relations among events. We define the notion of a causal graph to represent such relations and use Answer Set Programming (ASP), a declarative logic programming method, to find how to coordinate perception and simulation modules. We validate the effectiveness of our approach on two benchmarks, CLEVRER and CRAFT. Our enhancement achieves state-of-the-art performance on the CLEVRER challenge, significantly outperforming existing models. In the case of the CRAFT benchmark, we leverage a large pre-trained language model, such as GPT-3.5 and GPT-4, as a proxy for a dynamics simulator. Our findings show that this method can further improve its performance on counterfactual questions by providing alternative prompts instructed by symbolic causal reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10753
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Think before You Simulate: Symbolic Reasoning to Orchestrate Neural Computation for Counterfactual Question Answering
Ishay, Adam
Yang, Zhun
Lee, Joohyung
Kang, Ilgu
Lim, Dongjae
Artificial Intelligence
Causal and temporal reasoning about video dynamics is a challenging problem. While neuro-symbolic models that combine symbolic reasoning with neural-based perception and prediction have shown promise, they exhibit limitations, especially in answering counterfactual questions. This paper introduces a method to enhance a neuro-symbolic model for counterfactual reasoning, leveraging symbolic reasoning about causal relations among events. We define the notion of a causal graph to represent such relations and use Answer Set Programming (ASP), a declarative logic programming method, to find how to coordinate perception and simulation modules. We validate the effectiveness of our approach on two benchmarks, CLEVRER and CRAFT. Our enhancement achieves state-of-the-art performance on the CLEVRER challenge, significantly outperforming existing models. In the case of the CRAFT benchmark, we leverage a large pre-trained language model, such as GPT-3.5 and GPT-4, as a proxy for a dynamics simulator. Our findings show that this method can further improve its performance on counterfactual questions by providing alternative prompts instructed by symbolic causal reasoning.
title Think before You Simulate: Symbolic Reasoning to Orchestrate Neural Computation for Counterfactual Question Answering
topic Artificial Intelligence
url https://arxiv.org/abs/2506.10753