{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/think-before-you-simulate-symbolic-reasoning-1","title":"Think before You Simulate: Symbolic Reasoning to Orchestrate Neural Computation for Counterfactual Question Answering","arxiv_id":"2506.10753","date":"2025-06-12","proceeding":"IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024 1","authors":["Adam Ishay","Zhun Yang","Joohyung Lee","Ilgu Kang","Dongjae Lim"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2506.10753v1","url_pdf":"https://arxiv.org/pdf/2506.10753v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"think-before-you-simulate-symbolic-reasoning-1","repo_url":"https://github.com/azreasoners/CRCG","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"counterfactual-reasoning","task_name":"Counterfactual Reasoning"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"set","method_name":"SET"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-reasoning-on-clevrer","task":"Visual Reasoning","dataset":"CLEVRER","model":"AI Core","rank_in_archive_order":1,"of":13,"metrics":{"Average-per ques.":"95.24","Counterfactual-per opt.":"96.61","Counterfactual-per ques.":"90.72","Descriptive":"96.46","Explanatory-per opt.":"99.94","Explanatory-per ques.":"99.81","Predictive-per opt.":"93.96","Predictive-per ques.":"93.96"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}