Papers › Think before You Simulate: Symbolic Reasoning to Orchestrate Neural Computation for...
Think before You Simulate: Symbolic Reasoning to Orchestrate Neural Computation for Counterfactual Question Answering
Adam Ishay, Zhun Yang, Joohyung Lee, Ilgu Kang, Dongjae Lim
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.
Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Visual Reasoning | CLEVRER | AI Core | Average-per ques. | 95.24 | #1 of 13 | Archive leaderboard | report |
| Visual Reasoning | CLEVRER | AI Core | Counterfactual-per opt. | 96.61 | #1 of 13 | Archive leaderboard | report |
| Visual Reasoning | CLEVRER | AI Core | Counterfactual-per ques. | 90.72 | #1 of 13 | Archive leaderboard | report |
| Visual Reasoning | CLEVRER | AI Core | Descriptive | 96.46 | #1 of 13 | Archive leaderboard | report |
| Visual Reasoning | CLEVRER | AI Core | Explanatory-per opt. | 99.94 | #1 of 13 | Archive leaderboard | report |
| Visual Reasoning | CLEVRER | AI Core | Explanatory-per ques. | 99.81 | #1 of 13 | Archive leaderboard | report |
| Visual Reasoning | CLEVRER | AI Core | Predictive-per opt. | 93.96 | #1 of 13 | Archive leaderboard | report |
| Visual Reasoning | CLEVRER | AI Core | Predictive-per ques. | 93.96 | #1 of 13 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections