concept

information extraction

Also known as: IE, information extraction pipeline, entity extraction

Facts (40)

Sources

LLM-Powered Knowledge Graphs for Enterprise Intelligence and ... arxiv.org arXiv Mar 11, 2025 9 facts

measurementThe knowledge-graph-enhanced LLM system achieved 92% accuracy in entity extraction and 89% accuracy in relationship extraction, with contextual enrichment improving task alignment by 15%.

claimIntegrating contextual data from a knowledge graph improves entity extraction accuracy and downstream task performance in LLM-based enterprise applications.

claimThe entity extraction component improves precision and consistency by using Large Language Models (LLMs) with prompt engineering and contextual data retrieved from the Contextual Retrieval Module (CRM).

claimExperiments comparing entity extraction methods demonstrated that using enriched contextual information significantly outperforms methods relying on basic prompts or few-shot examples.

claimLarge Language Models expand the potential of knowledge graphs through their capabilities in entity extraction, relation inference, and contextual understanding.

claimLarge Language Models (LLMs) are ideal for creating dynamic and adaptive graph structures because they excel in semantic enrichment, entity extraction, and contextual reasoning.

procedureThe framework automates entity extraction, relationship inference, and semantic enrichment to enable querying, reasoning, and analytics across diverse data types including emails, calendars, chats, documents, and logs.

claimThe framework uses large language models to automate entity extraction, relationship inference, and contextual enrichment, creating a unified graph representation where nodes represent entities like people, topics, or events, and edges represent relationships.

procedureThe Entity-Relationship Extraction workflow begins with contextual retrieval, followed by entity extraction, and concludes with relationship extraction to ensure an accurate mapping of interactions.

The construction and refined extraction techniques of knowledge ... nature.com Nature Feb 10, 2026 3 facts

procedureThe knowledge extraction process described in the study consists of three main steps: text refinement, entity extraction, and relationship extraction, which are designed to extract structured, high-quality knowledge from unstructured text.

claimEntity extraction is a core task in the knowledge extraction process aimed at identifying key entities with decision-making value from unstructured text.

referenceMartinez-Rodriguez, J. L., Hogan, A. & Lopez-Arevalo, I. published 'Information extraction Meets the semantic web: a survey' in Semantic Web. 11 (2), 255–335 (2020).

LLM-empowered knowledge graph construction: A survey - arXiv arxiv.org arXiv Oct 23, 2025 3 facts

referenceThe ChatIE framework, proposed by Wei et al. (2024), reformulates information extraction as a multi-turn dialogue process where the model iteratively refines entity and relation candidates through chained question answering.

referenceThe KGGEN framework, proposed by Mo et al. (2025), decomposes information extraction into two sequential LLM invocations—detecting entities first, then generating relations—to reduce cognitive load and mitigate error propagation.

referenceYang Yang, Zhilei Wu, Yuexiang Yang, Shuangshuang Lian, Fengjie Guo, and Zhiwei Wang authored a survey of information extraction based on deep learning.

Combining large language models with enterprise knowledge graphs frontiersin.org Frontiers Aug 26, 2024 3 facts

referenceThe paper 'How to invest my time: lessons from human-in-the-loop entity extraction' by Zhang et al. (2019) discusses strategies for human-in-the-loop entity extraction.

claimPrompting in information extraction tasks faces hallucination issues, where models overconfidently label negative inputs as entities or relations.

claimLarge Language Models, such as GPT-3, struggle with specific information extraction tasks, including managing sentences that do not contain named entities or relations (Gutierrez et al., 2022).

Combining Knowledge Graphs and Large Language Models - arXiv arxiv.org arXiv Jul 9, 2024 3 facts

claimLarge language models are utilized for tasks including language translation, content creation, virtual assistants, automated essay writing, report generation, creative storytelling, chatbots, customer service, text summarization, information extraction, and sentiment analysis.

referenceKhorashadizadeh et al. identified methods using Large Language Models for knowledge graph construction tasks including text-to-ontology mapping, entity extraction, ontology alignment, and knowledge graph validation through fact-checking and inconsistency detection.

claimThe construction of knowledge graphs is difficult, costly, and time-consuming, requiring steps such as entity extraction, knowledge fusion, and coreference resolution.

Knowledge Graphs vs RAG: When to Use Each for AI in 2026 - Atlan atlan.com Atlan Feb 12, 2026 2 facts

claimRAG systems do not require entity extraction, schema design, or relationship mapping.

claimKnowledge graphs have high setup complexity requiring entity extraction and schema design, while RAG systems have low setup complexity as they work with existing documents.

Efficient Knowledge Graph Construction and Retrieval from ... - arXiv arxiv.org arXiv Aug 7, 2025 2 facts

claimThe TripleExtractor system utilizes the SpaCy dependency parser for information extraction because SpaCy is designed for industrial use, offers high-speed performance, and includes a state-of-the-art dependency parser suitable for open-ended information extraction.

claimBuilding a knowledge graph at enterprise scale incurs significant GPU or CPU costs and high latency when relying on Large Language Models or heavyweight NLP pipelines for entity and relation extraction.

How to Improve Multi-Hop Reasoning With Knowledge Graphs and ... neo4j.com Neo4j Jun 18, 2025 2 facts

claimThe information extraction pipeline is a process of extracting structured information, such as entities and relationships, from unstructured text.

claimLLMs or custom text domain models can be used to perform the information extraction pipeline.

Practices, opportunities and challenges in the fusion of knowledge ... frontiersin.org Frontiers 2 facts

referenceGraphusion (Yang et al., 2024d) addresses the challenge of using free text inputs for entity extraction by combining entity merging, conflict resolution, and novel triple discovery to provide a global perspective.

claimLarge Language Models (LLMs) assist in Knowledge Graph construction by acting as prompts and generators for entity, relation, and event extraction, as well as performing entity linking and coreference resolution.

EdinburghNLP/awesome-hallucination-detection - GitHub github.com GitHub 1 fact

referenceModel-based metrics for hallucination detection are structured into Information-Extraction (IE)-based classes, which retrieve an answer from a knowledge source and compare it with the generated answer, though this method may suffer from error propagation from the IE model.

How NebulaGraph Fusion GraphRAG Bridges the Gap Between ... nebula-graph.io NebulaGraph Jan 27, 2026 1 fact

claimNebulaGraph's Fusion GraphRAG framework automates the pipeline of entity extraction, relationship mapping, and graph construction, reducing the time required for knowledge graph creation from weeks to hours.

KG-IRAG with Iterative Knowledge Retrieval - arXiv arxiv.org arXiv Mar 18, 2025 1 fact

claimMost Retrieval-Augmented Generation (RAG) methods struggle with multi-step reasoning tasks that require both information extraction and inference.

Combining Knowledge Graphs With LLMs | Complete Guide - Atlan atlan.com Atlan Jan 28, 2026 1 fact

claimLarge Language Models are effective at initial entity extraction and relationship identification but require human validation to ensure domain-specific accuracy.

Construction of Knowledge Graphs: State and Challenges - arXiv arxiv.org arXiv 1 fact

claimKnowledge graphs in the geoscience domain are utilized for data analysis, including enhancing information extraction for public health hazards.

Enterprise AI Requires the Fusion of LLM and Knowledge Graph stardog.com Stardog Dec 4, 2024 1 fact

claimGNNs (Graph Neural Networks) are typically used for information extraction from unstructured text to build knowledge graphs, but they often struggle to generalize to out-of-distribution inputs. LLMs (Large Language Models) generalize better than GNNs and do not require specific training efforts, although they do not always achieve state-of-the-art results compared to GNNs.

The State Of The Art On Knowledge Graph Construction From Text nlpsummit.org NLP Summit 1 fact

claimNandana Mihindukulasooriya's research interests include relation extraction and linking, information extraction, knowledge representation and reasoning, and Neuro-Symbolic AI.

Knowledge Graphs: Opportunities and Challenges - Springer Nature link.springer.com Springer Apr 3, 2023 1 fact

referenceThe three primary methods of knowledge acquisition are relation extraction, entity extraction, and attribute extraction, with attribute extraction functioning as a subset of entity extraction (Fu et al. 2019).

Unlocking the Potential of Generative AI through Neuro-Symbolic ... arxiv.org arXiv Feb 16, 2025 1 fact

referenceLejla Begic Fazlic et al. developed an NLP-fuzzy system prototype for information extraction from medical guidelines, presented at the 2019 42nd International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO).

KG-IRAG: A Knowledge Graph-Based Iterative Retrieval-Augmented ... arxiv.org arXiv Mar 18, 2025 1 fact

claimThe KG-IRAG (Knowledge Graph-Based Iterative Retrieval-Augmented Generation) framework operates by transforming a larger temporal question into multiple fixed-time subproblems, which are solved via entity and temporal information extraction.

RAG Using Knowledge Graph: Mastering Advanced Techniques procogia.com Procogia Jan 15, 2025 1 fact

codeclass Entities(BaseModel): """Identifying information about entities.""" names: list[str] = Field( ..., description=( "All the person, organization, or business entities that " "appear in the text" ) ) prompt = ChatPromptTemplate.from_messages( [ ( "system", "You are extracting organization and person entities from the text.", ), ( "human", "Use the given format to extract information from the following " "input: {question}", ), ] ) def generate_full_text_query(input: str) -> str: words = [el for el in remove_lucene_chars(input).split() if el] if not words: return "" full_text_query = " AND ".join([f"{word}~2" for word in words]) print(f"Generated Query: {full_text_query}") return full_text_query.strip() # Full-text index query def graph_retriever(question: str) -> str: """ Collects the neighborhood of entities mentioned in the question """ result = "" # Detect entities through the entity chain and pass them to the graph query entities = entity_chain.invoke(question) for entity in entities.names: response = graph.query( """ CALL db.index.fulltext.queryNodes('fulltext_entity_id', $query, {limit:2}) YIELD node, score CALL { WITH node MATCH (node)-[r:!MENTIONS]->(neighbor) RETURN node.id + ' - ' + type(r) + ' -> ' + neighbor.id AS output UNION ALL WITH node MATCH (node)<-[r:!MENTIONS]-(neighbor) RETURN neighbor.id + ' - ' + type(r) + ' -> ' + node.id AS output } RETURN output LIMIT 50 """, {"query": entity}, ) result += "\n".join([el['output'] for el in response]) return result