[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-515466-105":59,"doc-detail-515466-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","protrix-building-models-for-planning-and-reasoning-over-tables-with-sentence-context-515466","PROTRIX - Building Models for Planning and Reasoning over Tables with Sentence Context","","Tables are central for organizing information, yet answering table-based questions is difficult and time-consuming for humans. This work proposes a Plan-then-Reason framework that plans reasoning paths using both table content and sentence context, then maps each step to program-based or textual reasoning. Experiments show GPT-3.5-Turbo improvements with fewer calls and self-consistency-free prompting, plus PROTRIX finetuning on TrixInstruct generalizing across unseen tabular tasks.",{"@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/protrix-building-models-for-planning-and-reasoning-over-tables-with-sentence-context-515466/515466/",{"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/protrix-building-models-for-planning-and-reasoning-over-tables-with-sentence-context-515466/515466.png","ImageObject",300,407,{"name":92,"@type":93},"Blue Pony","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-20","2026-10-06",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",14,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does PROTRIX address in table question answering?","Question",{"text":113,"@type":114},"It targets the difficulty of answering user queries over tables, where human effort is high due to large and structured information content. It also addresses limitations of purely textual or purely program-based reasoning approaches.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the Plan-then-Reason framework work?",{"text":118,"@type":114},"It first plans reasoning paths over both tabular data and sentence context, then assigns each reasoning step to either program-based or textual reasoning to produce the final answer.",{"name":120,"@type":111,"acceptedAnswer":121},"What are the main experimental outcomes for PROTRIX?",{"text":122,"@type":114},"The PROTRIX model family, finetuned on TrixInstruct, generalizes to diverse unseen tabular tasks with only 6k training instances, and it can generate accurate and faithful explanations for complex free-form questions.","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},515466,1791383778,{"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},962090760266,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","PROTRIX: Building Models for Planning and Reasoning  \nover Tables with Sentence Context  \nZirui Wu, Yansong Feng􀀌  \nWangxuan Institute of Computer Technology, Peking University, China {ziruiwu, [fengyansong}@pku.edu.cn](fengyansong}@pku.edu.cn)  \narXiv :2403 .02177v3 [ cs .CL] 28 Mar 2025  \nAbstract  \nTables play a crucial role in conveying information of various domains. We propose a novel Plan-then-Reason framework to answer different types of user queries over tables with sentence context. Our framework first plans the reasoning paths over both tabular and sentence context, then assigns each step to programbased or textual reasoning to reach the final answer. This framework enhances the table reasoning abilities for both in-context learning and finetuning methods. GPT-3.5-Turbo following our Plan-then-Reason framework surpasses other prompting baselines that do not employ self-consistency while using fewer API calls and in-context demonstrations. We also construct an instruction tuning set TrixInstruct to evaluate the effectiveness of finetuning with this framework. We present a PROTRIX model family by finetuning models on TrixInstruct. Our experiments show that the PROTRIX family can generalize to diverse unseen tabular tasks with only 6k training instances. We further demonstrate that PROTRIX can generate accurate and faithful explanations to answer complex free-form questions. Our work underscores the importance of the planning and reasoning abilities towards a model over tabular tasks with generalizability and interpretability. We open-source our dataset and models at [https://github.com/WilliamZR/ProTrix](https://github.com/WilliamZR/ProTrix).  \n1 Introduction  \nTables, serve as a fundamental tool for organizing and presenting information across various domains. Whether in business reports, or scientific publications, tables are commonly employed to represent complex data effectively. Despite their widespread utility, the process of human beings answering questions involving tables appears tobe time-consuming, given the often substantial amount of content involved. Recognizing this challenge, there arises a need to leverage Large Lan-  \nFigure 1: Demonstrations of user queries to a table in Wikipedia. Some of the sentences with hyperlinks to the table are presented as sentence context.  \nguage Models (LLMs) to understand and respond to user queries automatically.  \nFigure 1 demonstrates three kinds of user queries for a table from Wikipedia. In the first example, the user query is how many medals were won by Kenya. This question is annotated as a programunsolvable question by SQL experts (Shi et al., 2020) attributed to the absence of an explicit column for medals in the table. To resolve this, the model must fill the gap between the query and the  \nFigure 2: Demonstration of disadvantages of program-based and textual reasoning on tabular tasks. Program-based reasoning fails to answer the query since it tries to compare general concepts with a math operator. The textual reasoning fails on a program-solvable query that needs to count distinct countries in the table.  \ntable by recalling the commonsense knowledge that only the top three players can win medals.  \nThe second query delves into a multi-hop scenario asking whether the silver medalist at the 2001 Goodwill Games has ever won an Olympic gold medal. Addressing such queries raises two challenges (1) Decompose the query into sub-tasks. Such as the model plans to derive the silver medalists first and then verify their record of Olympic medals. (2) Combining structured and unstructured context. The model must extract the athletic name from the table and derive the information from the sentence context that Kosgei has won an Olympic gold medal since he is the youngest ever winner of an Olympic gold medal.  \nThe last query also requires the model to recall commonsense knowledge to decide which contextual information can be used as evidence to judge if Kenya is successf","cbCaidH5mJKegkKY","https://ap.wps.com/l/cbCaidH5mJKegkKY","pdf",895483,29,"English","# Introduction\n## Table question answering challenges\n## Textual vs program-based reasoning\n## Related work\n## Proposed Plan-then-Reason framework","[{\"question\":\"What problem does PROTRIX address in table question answering?\",\"answer\":\"It targets the difficulty of answering user queries over tables, where human effort is high due to large and structured information content. It also addresses limitations of purely textual or purely program-based reasoning approaches.\"},{\"question\":\"How does the Plan-then-Reason framework work?\",\"answer\":\"It first plans reasoning paths over both tabular data and sentence context, then assigns each reasoning step to either program-based or textual reasoning to produce the final answer.\"},{\"question\":\"What are the main experimental outcomes for PROTRIX?\",\"answer\":\"The PROTRIX model family, finetuned on TrixInstruct, generalizes to diverse unseen tabular tasks with only 6k training instances, and it can generate accurate and faithful explanations for complex free-form questions.\"}]","PROTRIX - Building Models for Planning and Reasoning over Tables with Sentence Context | PDF",1791315369,73,[148,152,156,160],{"page_no":8,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/9eff7c6e0b4047cf9799ff43edbfe0db.webp",983,1390,{"page_no":14,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/0b884deda3145884c1abc7fd0d32296e.webp",982,1388,{"page_no":81,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/76f9667e224cc20f8276f889de86d5fe.webp",981,1387,{"page_no":19,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/60c9c3e2854cdee6ed8f615c6348a5cc.webp",980,1385]