Aug 2026· Vestnik of the Plekhanov Russian University of Economics· Vol 23, pp. 48-57· 0 citations· 5 references
TL;DR
Analysis of current approach to using corporate data to upgrade quality of answers generated by LLM and the absence of mechanism necessary for integral analysis of loaded proprietary data is shown.
Abstract
The development of large language models (LLM) has extended opportunities of processing non-structured data in corporate environment. However, LLM fundamental restriction lies in their dependence on data of preliminary learning, which can decrease their ability to work safely with enterprise information non-published in other sources. The article provides analysis of current approach to using corporate data to upgrade quality of answers generated by LLM. Systems of Retrieval-Augmented Generation (RAG) are studied both in classical vector realization and in GraphRAG. Agent systems and integration of RAGand GraphRAG approaches in their architecture were discussed, as it can make it possible to build complicated systems of AI and solutions requiring multi-stage analysis of corporate non-structured data. Architecture of classical vector RAG-approach is described, which consists of three key stages: getting vector presentation of indexed fragments of papers; searching for fragments relevant to user requirement; forming the answer on extracted context combined with the initial request. As a key restriction the author showed the absence of mechanism necessary for integral analysis of loaded proprietary data. In its turn GraphRAG uses mechanism of plotting knowledge graph on context, which can help work not with semantically similar data fragments but with hierarchically clustered information by accumulated analysis of text summaries. Shortcomings and benefits of using approaches were formulated, criteria of expediency of RAG and GraphRAG practical application were identified and examples of systems for their use were provided
This study provides an AI- Based document analyzer with a question-answer system that makes use of Natural Language Processing approaches that is affordable, scalable, and suitable for business, education, and research.
Radhika Sharma, Devraj Gautam· Revolutionary Advances in Co...· 0 citations
This work introduces a trust based adaptive reranking model- ATM (Adaptive Trust Model) that allocates computational resources according to file level uncertainty, instead of assigning a fixed number of reranker calls per query, which focuses computation only where ranking confidence is low.
Jenny Kalaiarasi.S· Journal of Intelligent Decis...· 0 citations
The study resulted in the development of a novel six-component framework comprising Input Processing, LLM Core, Knowledge Enhancement, Context Management, Response Generation, Response Generation, and Human Feedback that successfully addressed resource scarcity through language detection and cross-lingual query understanding.
The research field of Natural Language Processing (NLP) has experienced a major shift since the introduction of Large Language Models (LLMs). All facets and application scenarios within NLP have been impacted by the use of LLMs. Current research as well as practice of text processing tools is focused mainly on the application and development of LLMs. Major investments, not only by LLM providers but also other companies applying LLMs in their workflows, have only solidified the role of LLMs in NLP - and in other research and application areas - as part of the artificial intelligence boom in recent years.
However, limitations and downsides of the application of LLMs have also emerged. Problems regarding the generated texts as well as the environmental impact of the large-scale use of LLMs are just two of many factors that should be critically analyzed, despite the hype and the prevalence of LLMs for NLP tasks. These restrictions provide the main motivation for this thesis. Traditional models as alternatives to LLMs will be discussed from different perspectives. The characterization of traditional models will be progressively developed as features of alternatives to LLMs will emerge during the course of this thesis. This process will be grounded in experiments, observations and evaluations. Several NLP applications will be presented by surveying the state of the art with neural network-based models such as LLMs as well as the current usage of traditional models. The concrete NLP applications comprise information and relation extraction, text classification, text segmentation, text simplification and text summarization.
The first half of this thesis will present the emergence of LLMs contextualized along previous developments within NLP. Characteristics of the selected NLP applications will be collected before a structured literature review will display the prevalence of LLMs regarding each application and will discuss if traditional models are still actively researched. Lessons from domains with long-standing development procedures and processes will also be taken into account to provide a purposeful and structured manner of approaching NLP tasks. A collection of challenges within current NLP will conclude the first half of the thesis, which will serve as motivation for the analysis of experiments and applications of the latter half.
The second half of this thesis will present observations and evaluations from use cases, aligned towards the challenges recognized in the first half. Through the analysis of these use cases, benefits of applying traditional models will be collected and supported, in particular through the analysis of a text segmentation use case that is purposefully applied with the lessons drawn from the first half of the thesis in mind. The interpretation of these results will conclude in a discussion on the applicability of traditional models in contrast to LLMs and also give recommendations of both model types for different use cases.
Concrete use cases for information extraction, entity matching, text classification and text segmentation will be presented, in which traditional models match or surpass the performance of modern methods. Through improved efficiency as well as enhanced explainability and reproducibility in comparison with neural network-based techniques, these showcases demonstrate the continued relevancy of traditional techniques in today's NLP landscape.
Overall, this thesis discusses the role of traditional models in current NLP research and practice, especially in contrast and comparison to modern neural network-based approaches including LLMs. The applicability of modern and less modern techniques is analyzed through a case-based analysis of NLP tasks in a structured and purposeful manner.
Robin Jegan· Schriften aus der Fakultät W...· 0 citations
Experiments on three different domain tasks show that FKGLM can effectively integrate LLMs and large-scale knowledge graphs, leading to a significant enhancement in the reasoning capabilities of LLMs.
Yulin Zhou, Yongbin Qin, Chuan Lin· Journal of King Saud Univers...· 0 citations
The emergence of Large Language Models (LLMs) has redefined how users interact with information in digital environments. However, their widespread and often indiscriminate integration has raised significant concerns regarding reliability and trustworthiness issues that are particularly critical when accessing digital libraries and historical archives. How can one leverage the generalization capacity of an LLM without losing the level of accountability required for an archival institution? In this paper, we present an agentic retrieval system designed to deliver more accurate and verifiable access to historical data while preserving much of the flexibility associated with unconstrained LLMs. As a contribution to historical document analysis, we compare traditional Retrieval-Augmented Generation (RAG) with an agentic GraphRAG architecture in their ability to deliver historical information under realistic conditions, including the presence of OCR and transcription errors. We introduce a semi-symbolic framework that integrates word-spotting techniques for post-OCR correction with a knowledge graph representation that enables the agent to access information through synthesized queries. The interleaved collaboration between word spotting and code generation allows the agent to construct strong retrieval queries that are robust to misinterpretation and hallucination, while still leveraging approximate search when noise and uncertainty, common in historical document analysis, would otherwise hinder precise retrieval.
S. Nicolau, Adrià Molina, O. R. Terrades et al.· 0 citations