Retrieval-Augmented Generation (RAG)
Open accessThe DOI matches its Crossref record; 68 of the 75 references it cites were found in a registry or an index, and 7 are not checked yet.
Abstract
The necessity for information is a fundamental aspect of human nature, and as such, there are ongoing efforts to enhance information retrieval with information systems (Alavi and Leidner 2001 ; Alavi et al. 2024 ). Companies are particularly affected by this, as they have extensive data at their disposal, and employees need to access it. Unfortunately, current systems are not able to adequately meet employees’ expectations. In fact, studies have shown that 79% of employees are dissatisfied with the user interfaces of enterprise search systems (Cleverley and Burnett 2019 ). This has led to a need for new approaches that can better address the information needs of organizations.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Embedding generation technologies transform textual information into these vector representations through neural network models trained on massive text corpora, capturing semantic relationships as geometric relationships within vector spaces.”
From Recent Innovations in Cloud-Optimized Retrieval-Augmented Generation Architectures for AI-Driven Decision Systems (2025) · cites this paper as [3]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Unlike traditional relational databases optimized for exact matching, vector databases implement approximate nearest neighbor algorithms, enabling efficient similarity identification across millions or billions of vectors.”
From Recent Innovations in Cloud-Optimized Retrieval-Augmented Generation Architectures for AI-Driven Decision Systems (2025) · cites this paper as [3]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“These systems store document representations as high-dimensional numerical vectors capturing semantic meaning through coordinate positions within embedding spaces [3].”
From Recent Innovations in Cloud-Optimized Retrieval-Augmented Generation Architectures for AI-Driven Decision Systems (2025) · cites this paper as [3]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Operational requirements include comprehensive monitoring, capturing performance metrics across distributed components, logging systems, maintaining audit trails for generated responses, and automated scaling responding to variable request volumes.”
From Recent Innovations in Cloud-Optimized Retrieval-Augmented Generation Architectures for AI-Driven Decision Systems (2025) · cites this paper as [3]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Processing requirements include substantial CPU resources for text processing operations, GPU acceleration for embedding generation and inference processes, and memory capacity supporting large model loading alongside vector operations [3].”
From Recent Innovations in Cloud-Optimized Retrieval-Augmented Generation Architectures for AI-Driven Decision Systems (2025) · cites this paper as [3]
Experimental — accuracy not yet measured
3 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Alavi, M., & Leidner, D. E. (2001) · MIS Quarterly · doi:10.2307/3250961 · Cited by 10,176 · cited 1×
“The necessity for information is a fundamental aspect of human nature, and as such, there are ongoing efforts to enhance information retrieval with information systems (Alavi and Leidner 2001; Alavi et al. 2024).”
A Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2022) · ACM Computing Surveys · doi:10.1145/3457607 · Cited by 5,812 · cited 2×
“For a current overview, see for instance Mehrabi et al. (2022) or Gallegos et al. (2024).”
A Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2019) · arXiv · doi:10.48550/arxiv.1908.09635 · Cited by 5,812
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025 · cited 1×
“This type of answer has been termed hallucination (Maynez et al. 2020; Ji et al. 2023), which is defined as ‘‘ content that is inconsistent with real-world facts or user inputs ’’ (Ji et al. 2023, p. 1).”
Dense passage retrieval for open-domain question answering
Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W.-T. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.550 · Cited by 3,575
Llama 2: Open Foundation and Fine-Tuned Chat Models
Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.09288 · Cited by 2,604
Feuerriegel, S., Hartmann, J., Janiesch, C., & Zschech, P. (2024) · Business & Information Systems Engineering · doi:10.1007/s12599-023-00834-7 · Cited by 2,267
The Self-Regulation of Attitudes, Intentions, and Behavior
Bagozzi, R. P. (1992) · Social Psychology Quarterly · doi:10.2307/2786945 · Cited by 2,176 · cited 1×
“Various determinants of behavior, including cognitive, affective, and conative (CAC) constructs (Bagozzi 1992), may be influenced.”
Bias and Fairness in Large Language Models: A Survey
Gallegos, I. O., Rossi, R. A., Barrow, J., Tanjim, M. M., Kim, S., Dernoncourt, F., Yu, T., Zhang, R., & Ahmed, N. K. (2024) · Computational Linguistics · doi:10.1162/coli_a_00524 · Cited by 1,245 · cited 2×
“For a current overview, see for instance Mehrabi et al. (2022) or Gallegos et al. (2024).”
Parameter-efficient fine-tuning of large-scale pre-trained language models
Ding, N., Qin, Y., Yang, G., Wei, F., Yang, Z., Su, Y., Hu, S., Chen, Y., Chan, C.-M., Chen, W., et al. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00626-4 · Cited by 1,191
On Faithfulness and Factuality in Abstractive Summarization
Maynez, J., Narayan, S., Bohnet, B., & McDonald, R. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.173 · Cited by 1,185
On Faithfulness and Factuality in Abstractive Summarization
Maynez, J., Narayan, S., Bohnet, B., & McDonald, R. (2020) · arXiv · doi:10.48550/arxiv.2005.00661 · Cited by 1,185 · cited 1×
“This type of answer has been termed hallucination (Maynez et al. 2020; Ji et al. 2023), which is defined as ‘‘ content that is inconsistent with real-world facts or user inputs ’’ (Ji et al. 2023, p. 1).”
THE PROBABILITY RANKING PRINCIPLE IN IR
ROBERTSON, S. E. (1977) · Journal of Documentation · doi:10.1108/eb026647 · Cited by 1,103 · cited 2×
“Most commonly, the ranking system is built upon the probability ranking principle (Robertson 1977), which is not always ideal.”
Managing artificial intelligence
Berente, N., Gu, B., Recker, J., & Santhanam, R. (2021) · MIS Quarterly · doi:10.25300/misq/2021/16274 · Cited by 898
Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems
(2024) · doi:10.1145/3613904 · Cited by 896
Retrieval-Augmented Generation for Large Language Models: A Survey
Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., & Wang, H. (2023) · arXiv · doi:10.48550/arxiv.2312.10997 · Cited by 876 · cited 1×
“For a more comprehensive overview of recent enhancements, we refer to in-depth reviews of RAG (Zhao et al. 2024; Yu et al. 2024; Gao et al. 2023).”
Augmenting large language models with chemistry tools
M. Bran, A., Cox, S., Schilter, O., Baldassari, C., White, A. D., & Schwaller, P. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00832-8 · Cited by 794 · cited 1×
“For instance, individuals can use CAs to access recipe information for cooking (Jaber et al. 2024) and to obtain assistance with complex chemistry-related tasks (Bran et al. 2024) and geometric problems (Trinh et al. 2024).”
Big Data Research in Information Systems: Toward an Inclusive Research Agenda
University of Virginia, Abbasi, A., Sarker, S., University of Virginia, Aalto University, Chiang, R., & University of Cincinnati (2016) · Journal of the Association for Information Systems · doi:10.17705/1jais.00423 · Cited by 688 · cited 2×
“This is particularly true for IT architecture and data management capabilities, which are a major challenge for organizations (Abbasi et al. 2016; Blohm et al. 2024).”
Longo, L., Brcic, M., Cabitza, F., Choi, J., Confalonieri, R., Ser, J. D., Guidotti, R., Hayashi, Y., Herrera, F., Holzinger, A., et al. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102301 · Cited by 626 · cited 1×
“Providing references to the contextual data is closely related to the concept of Explainable AI (XAI) (Schneider 2024; Longo et al. 2024), because users get additional information about the results of an LLM.”
Retrieval Augmentation Reduces Hallucination in ConversationPreprint
Shuster, K., Poff, S., Chen, M., Kiela, D., & Weston, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.07567 · Cited by 494 · cited 1×
“…extended context, a RAG-based system can generate outcomes based on the context which reduces hallucinations and increases factual accuracy (Lewis et al. 2020; Shuster et al. 2021) Grounding Generated output is combined with references to the contextual data (i.e., grounding (Magesh et al. 2024)).”
The Pile: An 800GB Dataset of Diverse Text for Language Modeling
Gao, L., Biderman, S., Black, S., Golding, L., Hoppe, T., Foster, C., Phang, J., He, H., Thite, A., Nabeshima, N., et al. (2021) · arXiv · doi:10.48550/arxiv.2101.00027 · Cited by 492 · cited 1×
“Most commonly, models are trained on massive text corpora from the World Wide Web (Touvron et al. 2023), including the CommonCrawl dataset and the Pile (Gao et al. 2020).”
Hicks, M. T., Humphries, J., & Slater, J. (2024) · Ethics and Information Technology · doi:10.1007/s10676-024-09775-5 · Cited by 456
Jiang, A. Q., Sablayrolles, A., Mensch, A., Bamford, C., Chaplot, D. S., Casas, D. D. L., Bressand, F., Lengyel, G., Lample, G., Saulnier, L., et al. (2023) · arXiv · doi:10.48550/arxiv.2310.06825 · Cited by 340
Solving olympiad geometry without human demonstrations
Trinh, T. H., Wu, Y., Le, Q. V., He, H., & Luong, T. (2024) · Nature · doi:10.1038/s41586-023-06747-5 · Cited by 311 · cited 1×
“By guiding the content generation process with additional data, RAG ensures that the quality and relevance of the output is maintained at a high level (Wu et al. 2024; Wang et al. 2024b).”
RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on AgriculturePreprint
Balaguer, A. D. L., Benara, V., Cunha, R. L. F., Filho, R. D. M. E., Hendry, T., Holstein, D., Marsman, J., Mecklenburg, N., Malvar, S., Nunes, L. O., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2401.08406 · Cited by 305
Kazemitabaar, M., Ye, R., Wang, X., Henley, A. Z., Denny, P., Craig, M., & Grossman, T. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642773 · Cited by 290 · cited 1×
“This approach not only increases the accuracy of results, but also ensures that generated answers are directly linked to relevant reference materials (Wei et al. 2024; Kazemitabaar et al. 2024; Rai et al. 2024; Strobel and Banh 2024).”
RAFT: Adapting Language Model to Domain Specific RAG
Zhang, T., Patil, S. G., Jain, N., Shen, S., Zaharia, M., Stoica, I., & Gonzalez, J. E. (2024) · arXiv · doi:10.48550/arxiv.2403.10131 · Cited by 286 · cited 1×
“Moreover, retrieval-augmented fine-tuning (RAFT) combines the advantages of RAG and fine-tuning, creating synthetic datasets for fine-tuning models to specific domains (Zhang et al. 2024).”
Organized Complexity of Digital Business Strategy: A Configurational Perspective
Park, Y., & Mithas, S. (2020) · MIS Quarterly · doi:10.25300/misq/2020/14477 · Cited by 285 · cited 1×
“From a theoretical perspective, appropriate configurations should be identified (Park and Mithas 2020) that guide organizations in how to organize their data for fine-tuning, RAG, or both.”
Retrieval-Augmented Generation for AI-Generated Content: A Survey
Zhao, P., Zhang, H., Yu, Q., Wang, Z., Geng, Y., Fu, F., Yang, L., Zhang, W., Jiang, J., & Cui, B. (2024) · arXiv · doi:10.48550/arxiv.2402.19473 · Cited by 240
Foundation Models: A New Paradigm for Artificial Intelligence
Schneider, J., Meske, C., & Kuss, P. (2024) · Business & Information Systems Engineering · doi:10.1007/s12599-024-00851-0 · Cited by 209 · cited 3×
“Since prior work has already identified important avenues for research with foundation models (Schneider et al. 2024; Feuerriegel et al. 2024), we illustrate some nuanced research questions that occur in combination with RAG from three different perspectives: (1) organizational , (2) individual ,…”
An Analysis of Fusion Functions for Hybrid Retrieval
Bruch, S., Gai, S., & Ingber, A. (2023) · ACM Transactions on Information Systems · doi:10.1145/3596512 · Cited by 200 · cited 1×
“Current approaches include permutation-invariant ranking models (Pang et al. 2020), list-aware re-rankings, and hybrid searches (Bruch et al. 2023) (Table 3).”
SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval
Pang, L., Xu, J., Ai, Q., Lan, Y., Cheng, X., & Wen, J.-R. (2020) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3397271.3401104 · Cited by 188 · cited 1×
“Current approaches include permutation-invariant ranking models (Pang et al. 2020), list-aware re-rankings, and hybrid searches (Bruch et al. 2023) (Table 3).”
Knowledge Management Perspective of Generative Artificial Intelligence
Alavi, M., Georgia Institute of Technology, Leidner, D. E., University of Virginia, Mousavi, R., & University of Virginia (2024) · Journal of the Association for Information Systems · doi:10.17705/1jais.00859 · Cited by 185 · cited 1×
“The necessity for information is a fundamental aspect of human nature, and as such, there are ongoing efforts to enhance information retrieval with information systems (Alavi and Leidner 2001; Alavi et al. 2024).”
Fair AI: Challenges and Opportunities
Feuerriegel, S., Dolata, M., & Schwabe, G. (2020) · Business & Information Systems Engineering · doi:10.1007/s12599-020-00650-3 · Cited by 159 · cited 1×
“Previous catchword articles have already covered important aspects of AI, namely fair AI (Feuerriegel et al. 2020), AI as a Service (Lins et al. 2021), foundation models (Schneider et al. 2024), and generative AI (Feuer-riegel et al. 2024).”
From local to global: a graph rag approach to query-focused summarization
Edge, D., Trinh, H., Cheng, N., Bradley, J., Chao, A., Mody, A., Truitt, S., Metropolitansky, D., Ness, R. O., & Larson, J. (2024) · arXiv · doi:10.48550/arxiv.2404.16130 · Cited by 159 · cited 4×
“Further, graph-based approaches such as GraphRAG offer significant improvements by extracting knowledge graphs and structuring them hierarchically to improve RAG-based tasks (Edge et al. 2024).”
InfluentialExplainable Generative AI (GenXAI): a survey, conceptualization, and research agenda
Schneider, J. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10916-x · Cited by 156 · cited 3×
“We argue that the impact of grounding is still under-researched, and more empirical data is required to investigate if grounding is a valuable addition to XAI.”
Med-HALT: Medical Domain Hallucination Test for Large Language Models
Pal, A., Umapathi, L. K., & Sankarasubbu, M. (2023) · arXiv · doi:10.48550/arxiv.2307.15343 · Cited by 152
Med-HALT: Medical Domain Hallucination Test for Large Language Models
Pal, A., Umapathi, L. K., & Sankarasubbu, M. (2023) · Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL) · doi:10.18653/v1/2023.conll-1.21 · Cited by 152
Is Cosine-Similarity of Embeddings Really About Similarity?
Steck, H., Ekanadham, C., & Kallus, N. (2024) · Companion Proceedings of the ACM Web Conference 2024 · doi:10.1145/3589335.3651526 · Cited by 137 · cited 1×
“Additionally and importantly, the same embedding model that was used for the creation of the vector database must be used to translate the input query into a vector, as the similarity between query and chunks (or documents) in the database is measured using these vectors (Steck et al. 2024).”
RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon GenerationPreprint
Wang, Z., Liu, A., Lin, H., Li, J., Ma, X., & Liang, Y. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2403.05313 · Cited by 136 · cited 1×
“This method provides more contextual and coherent output, supporting tasks such as code generation and mathematical reasoning (Wang et al. 2024c).”
Integrating Selectional Constraints and Subcategorization Frames in a Dependency Parser
(2016) · HAL · doi:10.1162/coli · Cited by 135
Artificial Intelligence as a Service: Classification and Research Directions
Lins, S., Pandl, K. D., Teigeler, H., Thiebes, S., Bayer, C., & Sunyaev, A. (2021) · Business & Information Systems Engineering · doi:10.1007/s12599-021-00708-w · Cited by 130 · cited 2×
“Previous catchword articles have already covered important aspects of AI, namely fair AI (Feuerriegel et al. 2020), AI as a Service (Lins et al. 2021), foundation models (Schneider et al. 2024), and generative AI (Feuer-riegel et al. 2024).”
Hallucinations in Large Multilingual Translation Models
Guerreiro, N. M., Alves, D. M., Waldendorf, J., Haddow, B., Birch, A., Colombo, P., & Martins, A. F. T. (2023) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00615 · Cited by 124 · cited 13×
“The core idea of RAG is to combine the generative capabilities of LLMs with external knowledge retrieved from a separate database (e.g., an organizational database) (Lewis et al. 2020).”
InfluentialHallucinations in Large Multilingual Translation Models
Guerreiro, N. M., Alves, D., Waldendorf, J., Haddow, B., Birch, A., Colombo, P., & Martins, A. F. T. (2023) · arXiv · doi:10.48550/arxiv.2303.16104 · Cited by 124
ChemCrow: Augmenting large-language models with chemistry tools
Bran, A. M., Cox, S., Schilter, O., Baldassari, C., White, A. D., & Schwaller, P. (2023) · arXiv · doi:10.48550/arxiv.2304.05376 · Cited by 122
RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback
Liu, Y., Peng, X., Zhang, X., Liu, W., Yin, J., Cao, J., & Du, T. (2024) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2024.findings-acl.281 · Cited by 98
The Evolution of Information Systems Architecture: An Agent-Based Simulation Model
Haki, K., Beese, J., Aier, S., & Winter, R. (2020) · MIS Quarterly · doi:10.25300/misq/2020/14494 · Cited by 95 · cited 1×
“More generally, research is needed that investigates what outcomes can be expected from the evolution and advancements of new architectures (Haki et al. 2020).”
Explanation matters: An experimental study on explainable AI
Hamm, P., Klesel, M., Coberger, P., & Wittmann, H. F. (2023) · Electronic Markets · doi:10.1007/s12525-023-00640-9 · Cited by 94 · cited 1×
“This is similar to previous research that has investigated the relationship between XAI and latent constructs such as trust (Hamm et al. 2023) or intention to use (Meske and Bunde 2022).”
Self-citationAn examination of the trade-off between internal and external IT capabilities
Nevo, S., Wade, M. R., & Cook, W. D. (2006) · The Journal of Strategic Information Systems · doi:10.1016/j.jsis.2006.10.002 · Cited by 90 · cited 1×
“For this reason, it also raises questions about the development of internal versus external capabilities (Nevo et al. 2007).”
Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?
Gekhman, Z., Yona, G., Aharoni, R., Eyal, M., Feder, A., Reichart, R., & Herzig, J. (2024) · arXiv · doi:10.48550/arxiv.2405.05904 · Cited by 86
Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?
Gekhman, Z., Yona, G., Aharoni, R., Eyal, M., Feder, A., Reichart, R., & Herzig, J. (2024) · Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2024.emnlp-main.444 · Cited by 86
FeB4RAG: Evaluating Federated Search in the Context of Retrieval Augmented Generation
Wang, S., Khramtsova, E., Zhuang, S., & Zuccon, G. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657853 · Cited by 74 · cited 3×
“This is particularly beneficial in complex information environments where data is distributed across multiple platforms (Wang et al. 2024a).”
Meske, C., & Bunde, E. (2022) · Information Systems Frontiers · doi:10.1007/s10796-021-10234-5 · Cited by 66 · cited 1×
“This is similar to previous research that has investigated the relationship between XAI and latent constructs such as trust (Hamm et al. 2023) or intention to use (Meske and Bunde 2022).”
MasakhaNER: Named entity recognition for African languages
(2021) · HAL · doi:10.1162/tacl · Cited by 61
Cooking With Agents: Designing Context-aware Voice Interaction
Jaber, R., Zhong, S., Kuoppamäki, S., Hosseini, A., Gessinger, I., Brumby, D. P., Cowan, B. R., & Mcmillan, D. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642183 · Cited by 55 · cited 1×
“For instance, individuals can use CAs to access recipe information for cooking (Jaber et al. 2024) and to obtain assistance with complex chemistry-related tasks (Bran et al. 2024) and geometric problems (Trinh et al. 2024).”
Advancing the search frontier with AI agents
White, R. W. (2024) · Communications of the ACM · doi:10.1145/3655615 · Cited by 55 · cited 1×
“Secondly, they are increasingly capable of tackling complex search tasks, facilitating problem-solving and decision-making in various domains (White 2024).”
RAG based Question-Answering for Contextual Response Prediction SystemPreprint
Veturi, S., Vaichal, S., Jagadheesh, R. L., Tripto, N. I., & Yan, N. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.03708 · Cited by 52 · cited 3×
“For example, Veturi et al. (2024) use organizational data (e.g., policy documents) to enhance the performance of a frequently asked questions (FAQ) system.”
Data products, data mesh, and data fabric
Blohm, I., Wortmann, F., Legner, C., & Köbler, F. (2024) · Business & Information Systems Engineering · doi:10.1007/s12599-024-00876-5 · Cited by 41 · cited 3×
“This is particularly true for IT architecture and data management capabilities, which are a major challenge for organizations (Abbasi et al. 2016; Blohm et al. 2024).”
Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools
Magesh, V., Surani, F., Dahl, M., Suzgun, M., Manning, C. D., & Ho, D. E. (2024) · arXiv · doi:10.48550/arxiv.2405.20362 · Cited by 37 · cited 3×
“…extended context, a RAG-based system can generate outcomes based on the context which reduces hallucinations and increases factual accuracy (Lewis et al. 2020; Shuster et al. 2021) Grounding Generated output is combined with references to the contextual data (i.e., grounding (Magesh et al. 2024)).”
RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Sarthi, P., Abdullah, S., Tuli, A., Khanna, S., Goldie, A., & Manning, C. D. (2024) · arXiv · doi:10.48550/arxiv.2401.18059 · Cited by 36 · cited 3×
“In such cases, recent developments, including RAPTOR (Sarthi et al. 2024) and GraphRAG (Edge et al. 2024), should be considered.”
Finding Generalizable Evidence by Learning to Convince Q&A Models
Perez, E., Karamcheti, S., Fergus, R., Weston, J., Kiela, D., & Cho, K. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1244 · Cited by 27 · cited 1×
“While Lewis et al. (2020) acknowledge previous work on the integration of external data (Guu et al. 2020; Karpukhin et al. 2020; Perez et al. 2019), they coined the term ‘‘ Retrieval-Augmented Generation (RAG)’’ and proposed a general framework that leverages the strength of pre-trained parametric…”
Cleverley, P. H., & Burnett, S. (2018) · Journal of Information Science · doi:10.1177/0165551518770969 · Cited by 25 · cited 1×
“In fact, studies have shown that 79% of employees are dissatisfied with the user interfaces of enterprise search systems (Cleverley and Burnett 2019).”
Centralizing Data Management with Considerations of Uncertainty and Information-Based Flexibility
Velu, C. K., Madnick, S., & Alstyne, M. V. (2013) · Journal of Management Information Systems · doi:10.2753/mis0742-1222300307 · Cited by 19 · cited 1×
“In addition to well-known shortcomings such as the centralization of data management (Velu et al. 2013), a RAG-based architecture brings new challenges that organizations need to address.”
Topology-aware Retrieval Augmentation for Text Generation
Wang, Y., Lipka, N., Zhang, R., Siu, A. F., Zhao, Y., Ni, B., Wang, X., Rossi, R. A., & Derr, T. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679746 · Cited by 9 · cited 1×
“By guiding the content generation process with additional data, RAG ensures that the quality and relevance of the output is maintained at a high level (Wu et al. 2024; Wang et al. 2024b).”
Developing Retrieval Augmented Generation (RAG) based LLM Systems from PDFs: An Experience ReportPreprint
Khan, A. A., Hasan, M. T., Kemell, K. K., Rasku, J., & Abrahamsson, P. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.15944 · Cited by 8 · cited 1×
“This capability is particularly beneficial in scenarios where the most current information is crucial (Amri et al. 2024; Khan et al. 2024).”
Xinyu: An Efficient LLM-based System for Commentary Generation
Wu, Y., Tang, B., Xi, C., Yu, Y., Wang, P., Liu, Y., Kuang, K., Deng, H., Li, Z., Xiong, F., et al. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3671537 · Cited by 6 · cited 1×
“By guiding the content generation process with additional data, RAG ensures that the quality and relevance of the output is maintained at a high level (Wu et al. 2024; Wang et al. 2024b).”
An Approach to the Analysis of Financial Documents Using Generative AI
Amri, S., Bani, R., & Bani, S. (2024) · International Conference on Networking, Information Systems & Security (NISS) · doi:10.1145/3659677.3659736 · Cited by 4 · cited 1×
“This capability is particularly beneficial in scenarios where the most current information is crucial (Amri et al. 2024; Khan et al. 2024).”
GARAG: A General adaptive question-answering system based on RAG
Wei, Z., Huang, D., Zhang, J., Song, C., Zhang, S., Zhang, J., Li, Z., Jiang, K., Li, R., & Duan, Q. (2024) · ICCBD · doi:10.1145/3695080.3695156 · Cited by 4 · cited 1×
“This approach not only increases the accuracy of results, but also ensures that generated answers are directly linked to relevant reference materials (Wei et al. 2024; Kazemitabaar et al. 2024; Rai et al. 2024; Strobel and Banh 2024).”
Barbero (2014) · doi:10.1016/j · Cited by 1
Grounded or Silent: Citation-Faithful Legal Question Answering for Pakistani LawPreprint
Irshad, M. K. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7475238
Untitled work
Vaswani (2017) · doi:10.5555/3295222.3295349
Research works printed but not linked: 10
- Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan T, Child R, Ramesh A, Ziegler DM, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D (2020) Language models are few-shot learners. In: Proceedings of the 34th international conference on neural information processing systems. Curran Associates Inc., Red Hook, NY, USA, NIPS ’20, pp 1877–1901. https://doi.org/10.5555/3495724.3495883 · doi:10.5555/3495724.3495883
- Dehghani Z (2022) Data mesh delivering data-driven value at scale. O’Reilly, Sebastopol
- Guu K, Lee K, Tung Z, Pasupat P, Chang MW (2020) REALM: Retrieval-augmented language model pre-training. In: Proceedings of the 37th international conference on machine learning, JMLR.org, ICML’20. https://doi.org/10.5555/3524938.3525306 · doi:10.5555/3524938.3525306
- Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W (2022) LoRA: Low-rank adaptation of large language models. In: International conference on learning representations, virtual conference
- Lewis P, Perez E, Piktus A, Petroni F, Karpukhin V, Goyal N, Küttler H, Lewis M, Yih Wt, Rocktäschel T, Riedel S, Kiela D (2020) Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Proceedings of the 34th international conference on neural information processing systems, Curran, Red Hook, NIPS ’20, pp 9459–9474. https://doi.org/10.5555/3495724.3496517 · doi:10.5555/3495724.3496517
- Lundberg SM, Lee SI (2017) A unified approach to interpreting model predictions. In: Proceedings of the 31st international conference on neural information processing systems, Curran, Red Hook, NIPS’17, pp 4768–4777. https://doi.org/10.5555/3295222.3295230 · doi:10.5555/3295222.3295230
- Rai A, Chen L, Breazeal C, Ramesh B, Long Y, Aria A (2024) Design and evaluation attributes for scalable, cost-effective personalization of LLM tutors in programming education. In: ICIS 2024 proceedings
- Strobel G, Banh L (2024) What did the doctor say? Empowering patient comprehension with generative artificial intelligence. In: ECIS 2024 proceedings, Paphos
- Wei J, Wang X, Schuurmans D, Bosma M, Ichter B, Xia F, Chi EH, Le QV, Zhou D (2022) Chain-of-thought prompting elicits reasoning in large language models. In: Proceedings of the 36th international conference on neural information processing systems, Curran, Red Hook, NY, USA, NIPS ’22, pp 24824–24837. https://doi.org/10.5555/3600270.3602070 · doi:10.5555/3600270.3602070
- Yu H, Gan A, Zhang K, Tong S, Liu Q, Liu Z (2024) Evaluation of retrieval-augmented generation: A survey. In: Zhu W (ed) Proceedings of the 2024 international conference on cloud computing and big data, New York, ICCBD ’24, pp 442–447. https://doi.org/10.1145/3695080.3695156 · DOI
Cited by
(2025) · doi:10.1007/s12525-025-00862-z · Cited by 23
“Through techniques like retrieval-augmented generation (RAG) (Klesel & Wittmann, 2025; Lewis et al., 2020; Li et al., 2025), active feature acquisition (Hübot-ter et al., 2024), structured templates (Wei et al., 2022; Yang et al., 2025), and APIs (Liang et al., 2024), the perception component curates and enhances the…”
Gao, F., Xu, S., Hao, W., & Lü, T. (2025) · Applied Sciences · doi:10.3390/app152312547 · Cited by 27
Knott, M., Krebs, M., & Kerscher, A. (2026) · Frontiers in Digital Health · doi:10.3389/fdgth.2026.1761641 · Cited by 11
“This architecture enables organizations to maintain control over source information while leveraging generative capabilities for natural language interaction, with embedding models translating queries and documents into vectors for similarity-based retrieval (32).”
Explainable AI for Mental Disorder Detection on Social Media: A Survey and Outlook
Ibrahimov, Y., Anwar, T., & Yuan, T. (2026) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2026.3688443 · Cited by 37
“Retrieved documents act as explicit evidence supporting generated explanations, improving trans-parency, and reducing hallucinations [171], [172], [173].”
Putri, M. R., Husodo, A. Y., & Irmawati, B. (2024) · IEEE International Conference on Communication, Networks and Satellite (COMNETSAT) · doi:10.1109/comnetsat63286.2024.10862926 · Cited by 9
Metadata
- Authors
- Klesel, M., & Wittmann, H. F.
- Affiliations
- Hessian Center for Artificial Intelligence (DE)
- Frankfurt University of Applied Sciences (DE)
- Corresponding author
- Klesel, Michael
- ORCID
- Klesel, Michael
- Venue
- Business & Information Systems Engineering
- Published
- 2025-06-01
- Volume
- 67
- Issue
- 4
- Pages
- 551-561
- ISSN
- 1867-0202 (ISSN-L)
- 2363-7005
- OpenAlex
- W4410929991
- Cited by
- 92
- References
- 62
- Citations by year
- 2026: 76 · 2025: 13
- FWCI
- 92.54
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Business & Information Systems Engineering (publishedVersion, cc-by)
- Econstor (Econstor) (submittedVersion, cc-by)
- Journal of the Association for Information Systems (submittedVersion)
- Funders
- Frankfurt University of Applied Sciences
- Topics
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
- Keywords
- retrieval-augmented generation, information retrieval, employee information needs, large language models, organizational information systems
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.