[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-273861-105":59,"doc-detail-273861-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","enhancing-llms-in-predictive-political-qa-with-semi-structured-data","Enhancing LLMs in Predictive Political QA with Semi-Structured Data","","Predictive political question answering (QA) aims to forecast how political actors will vote or respond, relying on evidence beyond factual retrieval. Existing LLM augmentation methods use external political resources as knowledge-based evidence, which under-models prediction-relevant signals. The work identifies two complementary signals: actor stance capturing issue-specific preferences, and high-order structure capturing indirect dependencies in actor interaction networks. It proposes PSL, a dual-view framework converting semi-structured political records into inference-oriented evidence via semantic stance extraction and structure-aware vector representations, improving performance across multiple datasets and LLMs with ablation support.",{"@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/enhancing-llms-in-predictive-political-qa-with-semi-structured-data/273861/",{"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/enhancing-llms-in-predictive-political-qa-with-semi-structured-data/273861.png","ImageObject",300,407,{"name":92,"@type":93},"Valentina","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-31","2026-09-15",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",13,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why can’t predictive political QA be solved by direct factual retrieval?","Question",{"text":113,"@type":114},"For predictive questions, the target behavior has not yet occurred, so external resources provide only indirect records rather than the answer itself. Direct retrieval therefore fails to capture prediction-relevant signals.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What two signals does the proposed method use for predictive political QA?",{"text":118,"@type":114},"It uses actor stance signals that reflect issue-specific preferences and high-order structure signals that characterize indirect dependencies among political actors in interaction networks.",{"name":120,"@type":111,"acceptedAnswer":121},"How does PSL convert semi-structured political data into evidence for LLMs?",{"text":122,"@type":114},"PSL builds actor profiles in a semantic view to retrieve question-relevant records and infer stance signals, and uses a vector view to propagate information on an actor interaction graph to encode high-order neighborhood structure.","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},273861,1789473045,{"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":130,"read_time":145,"preview_page_count":4},13056703020460,"https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923","Enhancing LLMs in Predictive Political QA with Semi-Structured Data  \nYinan Liu*,† Zihan Zhou†  \nZichun Jin Xinyu Wang Bin Wang Xiaochun Yang  \nSchool of Computer Science and Engineering, Northeastern University, Shenyang 110819, China  \n†Equal contribution. * Corresponding author.  \narXiv : 2608 .2 12 18v 1 [cs .AI] 2 1 Aug 2026  \nAbstract  \nPredictive political question answering (QA), such as predicting how a political actor will vote, goes beyond factual lookup. External political resources offer rich historical evidence, but rarely contain the answer itself. Existing LLM augmentation methods, including actor-profile-based simulation and knowledge graph evidence injection, improve political reasoning but largely treat external resources as knowledge-based evidence, leaving predictionrelevant signals under-modeled. We identify two complementary signals for predictive political QA: actor stances that capture issue-specific preferences, and high-order structure signals that capture indirect dependencies among political actors. We propose PSL, a dual-view framework that converts semi-structured political records into inference-oriented evidence for LLMs. PSL extracts stance signals from question-relevant actor records in a semantic view, and learns structure-aware actor representations from an actor interaction graph in a vector view. Across three real-world datasets and multiple LLMs, PSL consistently outperforms baselines, with ablations confirming the complementary gains of stance and structure signals.  \n1 Introduction  \nPolitical question answering (QA) serves diverse information needs about political actors, policies, and events. Large language models (LLMs) provide a powerful foundation for political QA, but their knowledge is often incomplete and unreliable in specialized, long-tail settings (Sahoo et al., 2024) . Augmenting LLMs with external political resources is therefore a natural direction (Cuconasu et al., 2024) . The political domain contains abundant external data, including social background information 1 , electoral records2 , and legislative vot-  \n1[https://www.wikipedia.org/](https://www.wikipedia.org/)  \n2[https://ballotpedia.org/](https://ballotpedia.org/)  \ning records3 , much of which is semi-structured or structured. However, many political QA tasks are not simple factual queries but predictive questions, such as predicting how a political actor will vote or respond to a future event (Yang et al., 2020 ; Galla and Burke, 2018) . For these questions, external resources provide valuable records but rarely contain the answer directly, because the relevant behavior has not yet occurred and existing records serve only as indirect facts. Therefore, predictive political QA cannot be solved by direct factual retrieval alone.  \nTo the best of our knowledge, the closest recent studies are PAA (Li et al., 2025) and PEG (Mou et al., 2024), which enhance LLMs’ political reasoning with external resources. PAA uses actorprofile-based simulation, organizing actors’ backgrounds and past behavior into textual profilesand prompting LLMs to simulate their decisions through role-playing. PEG uses knowledge-graphbased evidence injection, converting external resources into a knowledge graph (KG) and retrieving relevant structured evidence to augment LLMs. Both show the value of external resources for political reasoning, but still largely treat them as knowledge-based evidence (e.g. Political Behavior Profiles in Fig. 1) . Moreover, profile-based methods struggle to capture implicit group-level influence among political actors (Sowden et al., 2018), whereas KG-based methods often lose finegrained context when extracting raw resources into triples (Wang and Han, 2025) . What remains missing is an evidence representation suited to predictive political reasoning, beyond treating external  \nresources merely as knowledge-based evidence.  \nIn this work, we identify two complementary signals encoded in political data. i) Actor st","cbCaitkKaE61vDHn","https://ap.wps.com/l/cbCaitkKaE61vDHn","pdf",949695,14,"English","# Introduction\n## Predictive political QA and limitations of factual retrieval\n## Related work: PAA and PEG\n## Two complementary signals and motivation\n## PSL dual-view framework and evidence construction","[{\"question\":\"Why can’t predictive political QA be solved by direct factual retrieval?\",\"answer\":\"For predictive questions, the target behavior has not yet occurred, so external resources provide only indirect records rather than the answer itself. Direct retrieval therefore fails to capture prediction-relevant signals.\"},{\"question\":\"What two signals does the proposed method use for predictive political QA?\",\"answer\":\"It uses actor stance signals that reflect issue-specific preferences and high-order structure signals that characterize indirect dependencies among political actors in interaction networks.\"},{\"question\":\"How does PSL convert semi-structured political data into evidence for LLMs?\",\"answer\":\"PSL builds actor profiles in a semantic view to retrieve question-relevant records and infer stance signals, and uses a vector view to propagate information on an actor interaction graph to encode high-order neighborhood structure.\"}]","Enhancing LLMs in Predictive Political QA with Semi-Structured Data | PDF",35]