[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-201214-105":59,"doc-detail-201214-en":130},{"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":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","reasoning-with-graphs-structuring-implicit-knowledge-to-enhance-llms-reasoning","Reasoning with Graphs - Structuring Implicit Knowledge to Enhance LLMs Reasoning","","Large language models achieve strong results on many tasks, yet they struggle with reasoning scenarios that require inferring relationships among information in text sequences. This difficulty becomes critical in logical reasoning and multi-hop question answering, where latent entity connections and multi-hop context links drive correct solutions. Graphs can explicitly encode pairwise relationships, and external graphs have supported LLMs, but many tasks lack a ready-made graph. The paper introduces Reasoning with Graphs (RwG), which builds explicit graphs from context and uses them to improve reasoning performance.",{"@graph":69,"@context":122},[70,84,105],{"@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/reasoning-with-graphs-structuring-implicit-knowledge-to-enhance-llms-reasoning/201214/",{"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/reasoning-with-graphs-structuring-implicit-knowledge-to-enhance-llms-reasoning/201214.png","ImageObject",300,407,{"name":92,"@type":93},"Caleb Sterling","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-09-04",true,{"@type":102,"interactionType":103,"userInteractionCount":46},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What reasoning challenges do the paper focus on?","Question",{"text":112,"@type":113},"The paper targets logical reasoning and multi-hop question answering, where models must infer missing relationships between entities and follow multi-hop connections across the context.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Why are graphs helpful for LLM reasoning?",{"text":117,"@type":113},"Graphs explicitly represent pairwise relationships between entities, making structural information available for reasoning instead of relying only on sequential text.",{"name":119,"@type":110,"acceptedAnswer":120},"How does Reasoning with Graphs (RwG) work?",{"text":121,"@type":113},"RwG first constructs explicit graphs from the given context, then leverages those graphs to enhance LLM performance on reasoning tasks.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},201214,1788527357,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":46,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":36,"preview_page_count":4},962084925290,"https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45","Reasoning with Graphs: Structuring Implicit Knowledge to Enhance  \nLLMs Reasoning  \nHaoyu Han1 , Yaochen Xie2 , Hui Liu2,1 , Xianfeng Tang2 , Sreyashi Nag2 , William Headden2 , Yang Li2 , Chen Luo2 , Shuiwang Ji3 , Qi He2 , Jiliang Tang1  \n1Michigan State University, 2Amazon, 3Texas A&M University  \n{hanhaoy1, liuhui7, [tangjili}@msu.edu](tangjili}@msu.edu) , [sji@tamu.edu](sji@tamu.edu)[ ](sji@tamu.edu){yaochx, liunhu, xianft, sreyanag, headdenw, limyng, cheluo, [qih}@amazon.com](qih}@amazon.com)  \narXiv :2501 .07845v1 [ cs .CL] 14 Jan 2025  \nAbstract  \nLarge language models (LLMs) have demonstrated remarkable success across a wide range of tasks; however, they still encounter challenges in reasoning tasks that require understanding and inferring relationships between distinct pieces of information within text sequences. This challenge is particularly pronounced in tasks involving multi-step processes, such as logical reasoning and multi-hop question answering, where understanding implicit relationships between entities and leveraging multi-hop connections in the given context are crucial. Graphs, as fundamental data structures, explicitly represent pairwise relationships between entities, thereby offering the potential to enhance LLMs’ reasoning capabilities. External graphs have proven effective in supporting LLMs across multiple tasks. However, in many reasoning tasks, no pre-existing graph structure is provided. Can we structure implicit knowledge derived from context into graphs to assist LLMs in reasoning? In this paper, we propose Reasoning with Graphs (RwG) by first constructing explicit graphs from the context and then leveraging these graphs to enhance LLM reasoning performance on reasoning tasks. Extensive experiments demonstrate the effectiveness of the proposed method in improving both logical reasoning and multi-hop question answering tasks.  \n1 Introduction  \nIn recent years, Large Language Models (LLMs) have showcased remarkable capabilities across a variety of tasks, such as question answering (Zhuang et al., 2024 ; Lan et al., 2022), summarization (Pu et al., 2023), and language understanding (Zhao et al., 2023) . Despite these successes, LLMs still encounter significant challenges in certain areas (Zhao et al., 2023 ; Minaee et al., 2024) . A key limitation lies in their struggle with reasoning tasks (Yang et al., 2024 ; Huang et al., 2023), particularly with logical reasoning (Nezhurina et al.,  \nFigure 1: Comparison of Reasoning with Graph (RwG) to other prompting methods. Gray nodes represent thoughts generated by LLMs, while green nodes represent entities extracted from the input.  \n2024), which requires models to infer missing relationships between distinct pieces of information, and multi-hop reasoning (Yang et al., 2024), where they must trace a path or follow some structures through the context to arrive at the correct answer. To enhance the reasoning capabilities of LLMs, several prompting methods have been proposed. Chain-of-Thought (CoT) prompting (Wei et al., 2022 ; Kojima et al., 2022) aids LLMs in reasoning by generating intermediate steps that lead to the final answer. CoT has shown significant improvement in certain reasoning tasks without requiring model tuning. Building on CoT, the Self-Consistency method (Wang et al., 2022b) further enhances reasoning by generating multiple CoT pathways and selecting the most consistent one. Additionally, Tree of Thought (ToT) (Yao et al., 2024) and Graph of Thoughts (GoT) (Besta et al., 2024) extend this approach by structuring the LLMs’ thought process using trees and graphs, respectively. These methods prompt LLMs to generate initial thoughts and organize them into various structures. Despite the successes of these approaches, they still face challenges in handling complex reasoning tasks, such as logical reason-  \ning (Nezhurina et al., 2024) and multi-hop question answering (Yang et al., 2024) .  \nFor these complex reasoning tasks, LLMs need to figur","cbCaivkJ7B20PPcz","https://ap.wps.com/l/cbCaivkJ7B20PPcz","pdf",627234,16,"English","# Abstract\n# Introduction\n## Background on LLM reasoning challenges\n## Related work: prompt-based reasoning with graphs\n## Problem motivation and research question\n## Proposed approach: Reasoning with Graphs (RwG)","[{\"question\":\"What reasoning challenges do the paper focus on?\",\"answer\":\"The paper targets logical reasoning and multi-hop question answering, where models must infer missing relationships between entities and follow multi-hop connections across the context.\"},{\"question\":\"Why are graphs helpful for LLM reasoning?\",\"answer\":\"Graphs explicitly represent pairwise relationships between entities, making structural information available for reasoning instead of relying only on sequential text.\"},{\"question\":\"How does Reasoning with Graphs (RwG) work?\",\"answer\":\"RwG first constructs explicit graphs from the given context, then leverages those graphs to enhance LLM performance on reasoning tasks.\"}]","Reasoning with Graphs - Structuring Implicit Knowledge to Enhance LLMs Reasoning | PDF"]