Recent years have witnessed major technical breakthroughs in AI- facilitated by tremendous data and high-performance computers, large language models (LLMs) have brought disruptive progress to information technology from accessing data to performing analysis. While demonstrating unprecedented capabilities, LLMs have been found unreliable in tasks requiring factual knowledge and rigorous reasoning. Despite recent works discussing the hallucination problem of LLMs, systematic studies on empowering LLMs with the ability to plan, reason, and ground with explicit knowledge are still lacking. On the other hand, real-world data are enormous and complex, coming from different sources and bearing various modalities. Data professionals have spent tremendous efforts collecting and curating countless datasets with different schemas and standards. Transforming the separate datasets into unified knowledge graphs (KGs) can facilitate their integrative analysis and utilization, but these processes would often require strong domain expertise and significant human labor. In this paper, we discuss recent progress and promise in the co-learning of KGs and LLMs, through LLM-aided KG construction, KG-guided LLM enhancement, and knowledge-aware multi-agent federation, particularly emphasizing a structure-oriented retrieval augmented generation (SRAG) paradigm, towards fully utilizing the value of complex data, unleashing the power of generative models, and expediting next-generation trustworthy AI.
{"title":"Knowledge Graph and Large Language Model Co-learning via Structure-oriented Retrieval Augmented Generation.","authors":"Carl Yang, Ran Xu, Linhao Luo, Shirui Pan","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Recent years have witnessed major technical breakthroughs in AI- facilitated by tremendous data and high-performance computers, large language models (LLMs) have brought disruptive progress to information technology from accessing data to performing analysis. While demonstrating unprecedented capabilities, LLMs have been found unreliable in tasks requiring factual knowledge and rigorous reasoning. Despite recent works discussing the hallucination problem of LLMs, systematic studies on empowering LLMs with the ability to plan, reason, and ground with explicit knowledge are still lacking. On the other hand, real-world data are enormous and complex, coming from different sources and bearing various modalities. Data professionals have spent tremendous efforts collecting and curating countless datasets with different schemas and standards. Transforming the separate datasets into unified knowledge graphs (KGs) can facilitate their integrative analysis and utilization, but these processes would often require strong domain expertise and significant human labor. In this paper, we discuss recent progress and promise in the co-learning of KGs and LLMs, through LLM-aided KG construction, KG-guided LLM enhancement, and knowledge-aware multi-agent federation, particularly emphasizing a structure-oriented retrieval augmented generation (SRAG) paradigm, towards fully utilizing the value of complex data, unleashing the power of generative models, and expediting next-generation trustworthy AI.</p>","PeriodicalId":92006,"journal":{"name":"Bulletin of the Technical Committee on Data Engineering","volume":"48 4","pages":"9-46"},"PeriodicalIF":0.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12998269/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147488817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Aditya Parameswaran, Akash Das Sarma, Vipul Venkataraman
Crowdsourcing is the primary means to generate training data at scale, and when combined with sophisticated machine learning algorithms, crowdsourcing is an enabler for a variety of emergent automated applications impacting all spheres of our lives. This paper surveys the emerging field of formally reasoning about and optimizing open-ended crowdsourcing, a popular and crucially important, but severely understudied class of crowdsourcing-the next frontier in crowdsourced data management. The underlying challenges include distilling the right answer when none of the workers agree with each other, teasing apart the various perspectives adopted by workers when answering tasks, and effectively selecting between the many open-ended operators appropriate for a problem. We describe the approaches that we've found to be effective for open-ended crowdsourcing, drawing from our experiences in this space.
{"title":"Optimizing Open-Ended Crowdsourcing: The Next Frontier in Crowdsourced Data Management.","authors":"Aditya Parameswaran, Akash Das Sarma, Vipul Venkataraman","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Crowdsourcing is the primary means to generate training data at scale, and when combined with sophisticated machine learning algorithms, crowdsourcing is an enabler for a variety of emergent automated applications impacting all spheres of our lives. This paper surveys the emerging field of formally reasoning about and optimizing open-ended crowdsourcing, a popular and crucially important, but severely understudied class of crowdsourcing-the next frontier in crowdsourced data management. The underlying challenges include distilling the right answer when none of the workers agree with each other, teasing apart the various perspectives adopted by workers when answering tasks, and effectively selecting between the many open-ended operators appropriate for a problem. We describe the approaches that we've found to be effective for open-ended crowdsourcing, drawing from our experiences in this space.</p>","PeriodicalId":92006,"journal":{"name":"Bulletin of the Technical Committee on Data Engineering","volume":"39 4","pages":"26-37"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5610657/pdf/nihms843644.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"35450700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号