[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-339994-105":59,"doc-detail-339994-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","rock-reason-oabout-commonsense-kcausality","ROCK - Reason O(A)bout Commonsense K(C)ausality","","Commonsense causality reasoning (CCR) targets identifying plausible causes and effects in natural-language descriptions that an average person would consider reasonable. Despite strong academic and practical relevance, CCR lacks a solid theoretical foundation and existing methods often depend on deep language models, making them vulnerable to confounding co-occurrences. Motivated by classical causal inference, ROCK introduces a potential-outcomes view for commonsense tasks, uses temporal signals as supervision, and balances confounding through temporal propensities analogous to propensity scores, enabling modular zero-shot causal reasoning.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/rock-reason-oabout-commonsense-kcausality/339994/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/rock-reason-oabout-commonsense-kcausality/339994.png","ImageObject",300,407,{"name":92,"@type":93},"Riley","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-10","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does ROCK address in commonsense causality reasoning?","Question",{"text":113,"@type":114},"ROCK addresses estimating plausible causal relationships between events described in natural language, focusing on identifying how one event intervention changes the likelihood of another event occurring.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does ROCK incorporate temporality and supervision?",{"text":118,"@type":114},"ROCK uses temporal signals as incidental supervision, leveraging temporal order while explicitly accounting for confounding co-occurrences that may create misleading associations.",{"name":120,"@type":111,"acceptedAnswer":121},"How does ROCK reduce the impact of confounding co-occurrences?",{"text":122,"@type":114},"ROCK balances confounding effects using temporal propensities that act as a surrogate for propensity scores, enabling more reliable estimation of causal effects.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},339994,1791051741,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":146,"preview_page_count":19,"preview_urls":147},1374391975076,"https://ap-avatar.wpscdn.com/avatar/14000253ca4ec9f6853?x-image-process=image/resize,m_fixed,w_180,h_180&k=1783305029341752051","ROCK: Causal Inference Principles for Reasoning about Commonsense Causality  \nJiayao Zhang 1 2 Hongming Zhang 1 3 Weijie J. Su 2 Dan Roth 1 4  \nAbstract  \nCommonsense causality reasoning (CCR) aims at identifying plausible causes and effects in natural language descriptions that are deemed reasonable by an average person. Although being of great academic and practical interest, this problem is still shadowed by the lack of a wellposed theoretical framework; existing work usually relies on deep language models wholeheartedly, and is potentially susceptible to confounding co-occurrences. Motivated by classical causal principles, we articulate the central question of CCR and draw parallels between human subjects in observational studies and natural languages to adopt CCR to the potential-outcomes framework which, to the best of our knowledge, is the first such attempt for commonsense tasks. We propose a novel framework, ROCK, to Reason O(A)bout Commonsense K(C)ausality, which utilizes temporal signals as incidental supervision, and balances confounding effects using temporal propensities that are analogous to propensity scores. ROCK is modular and zero-shot, and demonstrates good CCR capabilities.  \n1. Introduction  \nCommonsense causality reasoning (CCR) is an important yet non-trivial task in natural language processing (NLP) that exerts broad industrial and societal impacts (Kuipers, 1984 ; Gordon et al., 2012 ; Mostafazadeh et al., 2020 ; Sapet al., 2020) . We articulate this task as  \nreasoning about cause-and-effect relationships between events in natural language descriptions  \n1 Cognitive Computation Group, University of Pennsylvania, USA. 2Department of Statistics and Data Science, University of Pennsylvania, USA. 3Tencent AI Lab Seattle, USA. 4Amazon AWS AI Labs, USA. Correspondence to:\u003C{zjiayao,hzhangal,danroth,[suw}@upenn.edu](suw}@upenn.edu)> .  \nProceedings of the 39 th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022 . Copyright 2022 by the author(s) .  \n\n| E1 : Alice entered a restaurant. | causes? | E2 : Alice ordered a pizza. |\n| --- | --- | --- |\n|  |  |  |\n\nFigure 1: An Example of CCR: does E 1 cause E2 ? The temporal order E 1 ≺ E2 does not necessitate causation due to confounding co-occurrences (e.g., X 1 ) . Since when conditioning on X 1 , a comparable intervention A 1 of E 1 also precedes E2 , the effect from E 1 to E2 shrinks.  \nthat are deemed reasonable by an average person.  \nThis definition naturally excludes questions that are beyond commonsense knowledge, such as those scientific in nature (e.g., does a surgery procedure reduce mortality?) . Instead, it accommodates causal queries within the reach of an ordinary reasonable person. As a concrete instantiation, we consider the problem of defining and estimating the strength of causation from one given event, E 1 , to another, E2 . For example, in Figure 1, is Alice’s “entering a restaurant”(E1 ) a plausible cause for her “ordering a pizza”( E2 )? Although the precedence from E 1 to E2 is logical, it might be less a“cause” compared with Alice’s “feeling hungry”(X1 ) .  \nTemporality informs causation, but it is still unclear how to account for confounding co-occurrences (such as X 1 in Figure 1) . Motivated by causal inference principles (Section 2), we formulate CCR as estimating the change in the likelihood of E2 ’s occurrence due to intervening E 1 (denoted by ¬ E 1 ):  \n∆ = P (E1 ≺ E2 ) − P (¬ E 1 ≺ E2 ) (1)  \nwhere P (·) can be estimated by pretrained language models (LMs) e.g., via masked language modeling (see Section 4 for implementation details) . The estimand ∆ measures the average treatment effect (ATE): its magnitude signifies the strength of the effect and its sign informs the direction. For example, when ∆ is close to −1, E 1 has a strong effect on E2 towards making E2 less prone to occurring. If the occurrences of E 1 and ¬ E 1 on any unit are purely random, a direct estimation of the temporal probabi","cbCaibfXVddUXvoq","https://ap.wps.com/l/cbCaibfXVddUXvoq","pdf",791261,22,"English","# Introduction\n# Background","[{\"question\":\"What problem does ROCK address in commonsense causality reasoning?\",\"answer\":\"ROCK addresses estimating plausible causal relationships between events described in natural language, focusing on identifying how one event intervention changes the likelihood of another event occurring.\"},{\"question\":\"How does ROCK incorporate temporality and supervision?\",\"answer\":\"ROCK uses temporal signals as incidental supervision, leveraging temporal order while explicitly accounting for confounding co-occurrences that may create misleading associations.\"},{\"question\":\"How does ROCK reduce the impact of confounding co-occurrences?\",\"answer\":\"ROCK balances confounding effects using temporal propensities that act as a surrogate for propensity scores, enabling more reliable estimation of causal effects.\"}]","ROCK - Reason O(A)bout Commonsense K(C)ausality | PDF",1790033582,55,[148,152,156,160],{"page_no":8,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/d480b2dfd16ebcf230c02886b1d2bcb0.webp",983,1272,{"page_no":14,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/dd6f7d3a21f8efb11b447bc1d675e6b3.webp",982,1270,{"page_no":81,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/b3985be1a27d4625da7aa2e8b6fe13ca.webp",981,1269,{"page_no":19,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/1ea5a54c23ea659180af1b1e6a06b7b7.webp",980,1268]