The work, carried out by Rohini Kokare and Sunil Mane, focuses on a niche but important use case: soybean cultivation advisory for Indian agriculture. The researchers scraped unstructured documents from the ICAR-National Soybean Research Institute in Indore, Tamil Nadu Agricultural University and the TNAU Agritech portal, covering crop protection, crop production, farm mechanization, good agricultural practices, variety information and region-wise crop recommendations. From these documents they built a curated instruction dataset of 1,200 samples, each containing exactly one relational triplet, split 90:10 between training and testing with no sentence overlap.

At the heart of the system is a fine-tuned Llama-3.2-1B-Instruct model, a one-billion-parameter language model with multilingual support for eight languages. Rather than retraining the entire network, the team used Low-Rank Adaptation, or LoRA, a parameter-efficient fine-tuning technique that freezes the pre-trained weights and trains only small adapter matrices. For a frozen weight matrix of size 512 by 512, LoRA decomposes the update into two matrices of 512 by 8 and 8 by 512, yielding just 8,192 trainable parameters per adapted matrix. This dramatic reduction in trainable parameters makes the approach computationally affordable while still allowing the model to learn domain-specific behavior.

The researchers chose their target modules carefully. In Llama-style architectures, the feed-forward sub-block contains most of the parameters, so adapting only the attention mechanism would leave much of the model’s representational capacity untouched. The team therefore applied LoRA across all linear modules: the attention projections for query, key, value and output, plus the gated MLP SwiGLU blocks known as gate_proj, up_proj and down_proj. They set the LoRA rank to 8, with an alpha of 16 giving a scaling factor of two, and applied a light dropout of 0.05 on the adapter path to avoid overfitting on the specialized vocabulary of agronomy.

Instruction fine-tuning was central to the approach. Instead of simply exposing the model to domain text, the researchers trained it with explicit instructions such as “Extract entities and relationships as triples,” paired with input sentences and structured outputs. An example from the dataset maps the sentence “Macs 330 controls Bradyrhizobium japonicum” to the triplet consisting of the subject MACS 330, the relation “controls” and the object Bradyrhizobium japonicum. This format teaches the model to follow task-specific guidelines and produce consistent, machine-parseable output rather than free-form text.

Once fine-tuned, the model extracts triplets from unstructured text at inference time, and these subject-predicate-object structures are pushed into Neo4j, a graph database where entities become nodes and relations become edges. The resulting knowledge graph captures multi-relational information about soybean varieties, diseases, pests, treatments and practices in a form that supports structured queries written in the Cypher query language. This graph then serves as the retrieval backbone for a GraphRAG system, a hybrid of graph retrieval and large language model generation.

The GraphRAG retrieval layer combines vector and keyword search over the text properties of document nodes, using embeddings from HuggingFace models matched against embedding properties stored on each node. A user’s natural language query flows directly into the hybrid retriever through a LangChain pipeline without rewriting or entity extraction. Both the retrieved graph context and the original question are then passed to a fixed prompt template, and the fine-tuned Llama model generates the final answer. This design grounds responses in retrieved facts, reducing the hallucination risk that plagues out-of-the-box language models when they answer specialized questions.

The experimental results showed clear gains from the approach. When the team compared fine-tuning configurations, the model trained with all projection modules and instruction fine-tuning outperformed variants trained only on attention layers or only on feed-forward layers, measured by macro-averaged precision, recall and F1-score across the test set. On end-to-end response generation, the fine-tuned GraphRAG pipeline beat conventional vector database retrieval, standard RAG and knowledge-graph-only retrieval on both ROUGE and BLEU precision metrics, which measure how closely generated answers overlap with reference responses at the unigram, bigram and longest-common-subsequence levels.

The authors argue that the framework addresses a genuine gap. Previous research has explored agricultural chatbots and question-answering systems, agricultural knowledge graphs and general-purpose GraphRAG frameworks separately, but no existing system, to their knowledge, had combined LoRA-based generative triple extraction, automated knowledge graph construction and GraphRAG-style retrieval for a low-resource domain like Indian soybean advisory. Conventional pipelines that treat named entity recognition and relation extraction as separate steps are labor-intensive to train and prone to cascading errors, while generalized prompting or full-parameter fine-tuning is computationally inefficient and time-consuming.

The work is not finished. The researchers note that systematic verification of triplet semantics and quality, including comparison of gold versus predicted triples and elimination of noisy extractions, is scheduled as upcoming work. They also plan explicit graph-traversal-based retrieval using relation-path expansion from matched entities, and controlled comparisons against size-matched open-weight models such as Qwen2.5-1.5B-Instruct and DeepSeek small variants, as well as larger frontier models like GPT-4o and Mistral, under identical test questions and decoding settings. Even so, the study demonstrates that a small, efficiently fine-tuned language model can transform scattered agricultural documents into a queryable knowledge network, offering a template for bringing structured, trustworthy AI question-answering to domains where data is abundant but structured knowledge is scarce.

Subject of Research: LoRA-based instruction fine-tuning of large language models for agronomic triple extraction and GraphRAG knowledge retrieval

Article Title: LoRA based instruction fine tuning of large language models for agronomic triple extraction and GraphRAG knowledge retrieval

Article References: Kokare, R., & Mane, S. (2026). LoRA based instruction fine tuning of large language models for agronomic triple extraction and GraphRAG knowledge retrieval. Discover Artificial Intelligence, 6(1), Article 1381. https://doi.org/10.1007/s44163-026-02410-w

Image Credits: AI Generated

DOI: 10.1007/s44163-026-02410-w

Keywords: LoRA, instruction fine-tuning, large language models, Llama, triple extraction, GraphRAG, knowledge graph, Neo4j, agronomy, soybean, retrieval-augmented generation, parameter-efficient fine-tuning

The research, led by Zirui Tang and Qingshi Tu of the Sustainable Bioeconomy Research Group at the University of British Columbia, together with Max Dreger and Kourosh Malek of Forschungszentrum Jülich in Germany and Peijin Jiang of UBC, addresses a bottleneck that has long frustrated the sustainability field. Life cycle assessment, or LCA, is the standard tool for comparing the environmental credentials of products and services, but its reliability hinges on high-quality inventory data. Collecting that data by hand from the literature is slow, labor-intensive, and notoriously difficult to scale, which means that meta-analyses and large-scale syntheses often lag years behind the primary studies they should be aggregating.

The team’s framework combines two complementary technologies. On the front end, a retrieval-augmented generation pipeline—commonly known as RAG—sends large language models into the full text of published articles to extract three core categories of information: life cycle inventory data, life cycle impact assessment results, and the modeling assumptions that underpin each study. On the back end, the extracted information is normalized and mapped into an ontology-driven knowledge graph built specifically for LCA data and implemented in the Neo4j graph database. The ontology gives every extracted fact a defined place in a shared semantic structure, turning a pile of heterogeneous paper-specific numbers into an interconnected, machine-queryable web of knowledge.

The technical challenge is considerable. Scientific papers do not present their data uniformly; inventory tables appear in different formats, use inconsistent units and system boundaries, and embed crucial context—such as functional units, allocation choices, and geographic scope—in prose rather than structured fields. The pipeline therefore has to parse documents, identify which tables actually contain inventory data, and interpret the surrounding text to understand what each number means. The authors report that the extraction stage achieved F1-scores ranging from 75.18 to 89.50 percent across the three data types, a level of semantic accuracy that suggests the models are genuinely understanding the content rather than merely pattern-matching on keywords.

Extraction alone, however, would only produce a better-organized archive. The second half of the framework is what makes it genuinely interactive: an LLM-based question-answering system that translates natural language queries into executable graph queries. A user can ask, in ordinary English, about the greenhouse gas intensity of a particular bio-based chemical under a given set of assumptions, and the system converts the question into Cypher—the query language of Neo4j—retrieves the relevant nodes and relationships from the knowledge graph, and returns an answer. Crucially, users need no prior knowledge of the graph’s schema, which has historically been one of the biggest barriers preventing domain scientists from exploiting structured databases directly.

The query system itself was evaluated rigorously, and the results reveal an instructive lesson about how to build such tools. A baseline approach relying on a single strategy achieved an F1-score of only 56.98 percent—hardly reliable enough for scientific work. By combining similarity search, which locates the most relevant portions of the graph for a given question, with text-to-Cypher reasoning, which generates the formal query, the team raised the score to 75.18 percent. The hybrid architecture outperforms either method alone because the two strategies fail in different ways: semantic search is robust to vague phrasing but imprecise about graph structure, while query generation is precise but brittle when a question does not map cleanly onto the schema.

To demonstrate the framework in practice, the researchers applied it to a case study of LCA studies on bio-based chemical production—a domain where the literature has expanded rapidly as industry and academia race to replace fossil-derived chemicals with renewable alternatives. Bio-based chemicals are an ideal testbed because published assessments vary widely in feedstock, conversion technology, and impact categories, making manual synthesis across studies especially painful. The knowledge graph lets researchers compare results across studies while preserving the assumptions that make each figure meaningful, something a simple spreadsheet of extracted numbers could never do.

The broader significance extends beyond one application domain. The study arrives amid a wave of efforts to apply large language models to scientific data extraction, from polymer properties to carbon capture technologies to toxicology reports. What distinguishes this work is the full pipeline: it does not stop at extraction but carries the data through normalization, ontological mapping, and interactive retrieval, addressing the interoperability problem that has long plagued LCA data systems. Previous semantic efforts in the field, including minimal ontology patterns for LCA data proposed over the past decade, laid conceptual groundwork, but the manual effort required to populate such structures remained prohibitive. Automating that population step changes the economics of knowledge synthesis entirely.

There are, of course, caveats. F1-scores in the 75 to 90 percent range mean that a meaningful fraction of extracted facts will still be wrong or missed, and in a field where numbers feed policy decisions and corporate sustainability claims, errors carry consequences. The authors make their ground-truth datasets, extracted results, and pipeline code publicly available through the article’s supplementary materials and a GitHub repository, which allows the community to audit performance and build improvements. The work was supported by the Natural Sciences and Engineering Research Council of Canada, and the authors declare no competing interests.

Still, the trajectory is clear. As the volume of scientific literature grows faster than any human team can read, the bottleneck in fields like industrial ecology is shifting from generating data to finding and reconciling it. A framework that reads the papers, structures the findings, and answers questions in plain language offers a glimpse of how sustainability science might scale its evidence base to meet the pace of the energy and materials transition—turning decades of scattered assessments into a single, queryable map of environmental knowledge.

Subject of Research: Automated extraction and retrieval of life cycle assessment data from scientific literature using large language models and knowledge graphs

Article Title: From literature to knowledge graphs: automated extraction and retrieval of life cycle assessment data with large language models

Article References: Tang, Z., Dreger, M., Jiang, P., Malek, K., & Tu, Q. (2026). From literature to knowledge graphs: automated extraction and retrieval of life cycle assessment data with large language models. Journal of Industrial Ecology, 30(4), 1985-2000. https://doi.org/10.1007/s44498-026-00135-8

Image Credits: AI Generated

DOI: 10.1007/s44498-026-00135-8

Keywords: life cycle assessment, large language models, knowledge graphs, retrieval-augmented generation, life cycle inventory, data extraction, Neo4j, text-to-Cypher, sustainability, industrial ecology, natural language processing, bio-based chemicals

The core challenge the researchers set out to address is deceptively simple to state and fiendishly hard to solve. Because cryptocurrencies are decentralized and anonymous, they have become a preferred tool for criminals engaging in financial crimes, as the authors note in their paper. Detecting abnormal transactions in this environment is not just a matter of flagging a suspicious account. Transactions form enormous, constantly shifting webs in which every payment links one address to another, and the meaning of any single node depends on its position within that web. Traditional machine learning approaches, which treat each transaction or account as an independent row of features, throw away precisely the relational information that distinguishes a laundering operation from ordinary commerce.

E-GTNet’s answer is to treat the Bitcoin ledger as what it truly is: a graph. The team constructed a heterogeneous transaction graph based on Bitcoin transaction records, incorporating temporal evolution features. In other words, the model does not see a static snapshot of the network but a living structure that changes over time, with nodes representing addresses and edges representing the flows of value between them. Heterogeneity matters here because not all nodes and edges carry the same semantic weight; the graph encodes different types of entities and relationships, allowing the model to reason about the varied roles that addresses play in the ecosystem.

Architecturally, the framework fuses three complementary strands of modern deep learning. The first is an edge-aware attention mechanism. In graph neural networks, attention lets a node weigh the influence of its neighbors differently rather than treating them all equally, and by making the mechanism edge-aware, E-GTNet exploits edge-level features directly. This is a meaningful distinction in financial networks, where the characteristics of a transaction itself, such as its timing and its position in the flow of funds, can be as informative as the properties of the addresses on either end. The second strand is the graph convolutional structure, the workhorse of graph representation learning, which aggregates information across neighborhoods so that each node’s embedding reflects its local context. The third strand is temporal sequence modeling, which captures the temporal dynamics of transactions, ensuring that the model learns not only who is connected to whom but how those connections unfold across time.

The choice of a Transformer-style backbone for the graph reasoning is significant. Graph Transformers have emerged as a powerful class of models because attention can, in principle, relate any two nodes in a graph rather than being limited to immediate neighbors, which helps capture long-range dependencies that simple message-passing networks can miss. For anomaly detection, this matters because illicit behavior often reveals itself through subtle, multi-hop patterns: a chain of intermediate addresses that exists solely to obscure the origin of funds. A model that can attend across the whole graph, while still honoring local structure through convolutional components, is better positioned to recognize such patterns than one that only sees a node’s immediate surroundings.

To validate the framework, the researchers turned to the publicly available Elliptic Bitcoin transaction dataset, a widely used benchmark in the anti-money-laundering research community that maps real Bitcoin transactions with labels identifying which nodes are associated with illicit activity. The data are publicly accessible, which means other teams can reproduce and extend the results. On this foundation, the authors trained and evaluated E-GTNet as an anomaly detection system, asking it to distinguish anomalous nodes from legitimate ones within the transaction graph.

But detection alone was not the end goal. To further validate the accuracy and interpretability of the proposed anomaly detection framework, the team used the Neo4j graph database to visualize and trace the anomalous transaction graphs identified by the model. This is where the work acquires a distinctly practical flavor for regulators and forensic investigators. Neo4j is a native graph database, meaning it stores and queries data as nodes and relationships rather than tables, making it a natural home for exploring network structures interactively. By loading the model’s predicted anomalous subgraphs into Neo4j, the researchers could render the suspected criminal networks as navigable visual maps, tracing how value moves through them and comparing those maps against the ground-truth anomalous nodes labeled in the dataset.

The visualizations yielded one of the study’s most striking findings: anomaly structures evolve from linear chains to more complex and covert patterns over time. In the early stages, illicit activity in the data tends to resemble simple pipelines, with funds passing through a straightforward sequence of addresses. As time progresses, the anomalous structures branch out and interweave, becoming harder to spot and harder to untangle. This observation carries real weight for anti-money-laundering strategy, because it suggests that detection systems and the investigators who rely on them must contend with adversaries whose network topologies adapt deliberately to evade scrutiny. A static model tuned to yesterday’s laundering patterns may be blind to tomorrow’s.

Encouragingly, the model appears to keep pace with that evolution. The authors report that the predicted anomalous transaction graphs closely mirror the structural patterns and temporal dynamics of the ground-truth anomalous nodes, validating the model’s effectiveness in both structural and temporal pattern learning. In plain terms, when E-GTNet flags a set of addresses as suspicious, the surrounding network it paints, with its shapes and its timing, looks like the network that surrounds the addresses known to be illicit. That dual agreement, in both structure and time, is exactly the kind of evidence needed to trust an automated system in a domain where a false accusation can freeze legitimate funds and a false negative can let a laundering ring operate unchecked.

The study arrives amid a rapidly growing body of research applying graph neural networks to financial crime. Recent work in the same journal and elsewhere has explored self-supervised node embeddings for detecting money laundering in Bitcoin, graph diffusion transformers with temporal information for anti-money-laundering, wavelet-temporal graph transformers for illicit transaction detection, and explainable graph neural network frameworks for illicit financial transactions, alongside systematic reviews cataloguing dynamic temporal approaches to graph-based anomaly detection. Graph databases, too, have been increasingly paired with machine learning for fraud detection in banking and e-commerce. What distinguishes the new study is the combination of a fusion architecture that explicitly integrates edge features, neighborhood attention, and temporal modeling with a visualization pipeline that turns model output into something a human investigator can explore and interrogate.

The broader stakes are considerable. Estimates of the scale of cryptocurrency-financed crime run into the billions of dollars annually, and regulatory authorities worldwide have been searching for methods to monitor suspicious transaction behavior without dismantling the legitimate uses of the technology. Tools like E-GTNet point toward a future in which compliance teams and law enforcement can move beyond rule-based flags, such as fixed thresholds on transaction size, toward models that understand the shape of criminal networks and how those shapes mutate. The interpretability layer is particularly important in this context: an alert that comes with a visual map of the surrounding transaction graph gives an analyst something to verify, contextualize, and act upon, rather than an opaque score.

There are, of course, limits to what any single study can establish. The evaluation rests on one public dataset, and the arms race between illicit actors and detection systems guarantees that the covert patterns observed here will not be the last word in evasion tactics. The authors acknowledge the field’s ongoing challenges implicitly by situating their contribution within a broader research program on temporal graph learning. Still, the work offers a concrete demonstration that fusing edge-aware attention, graph convolution, and temporal modeling can track criminal structures as they evolve, and that rendering those structures in a graph database transforms abstract model predictions into actionable intelligence. For a financial system built on anonymity, the paradox deepens: the very connectivity that makes Bitcoin attractive to criminals also leaves an indelible trail, and with models like E-GTNet, that trail is becoming steadily easier to read.

Subject of Research: Graph neural network-based anomaly detection for illicit Bitcoin transactions

Article Title: Visualized anomaly detection on Bitcoin transaction based on the E-GTNet fusion model and graph database

Article References: Wu, F., Yin, W., Hu, X., & Luo, X. (2026). Visualized anomaly detection on Bitcoin transaction based on the E-GTNet fusion model and graph database. Applied Intelligence, 56(15), Article 453. https://doi.org/10.1007/s10489-026-07433-5

Image Credits: AI Generated

DOI: 10.1007/s10489-026-07433-5

Keywords: Bitcoin, anomaly detection, graph neural networks, E-GTNet, graph transformer, Neo4j, graph database, money laundering, blockchain, financial crime, temporal modeling, Applied Intelligence

The core problem the researchers set out to solve is one that plagues nearly every large infrastructure domain: heterogeneity. Levee records are maintained by different organizations using different vocabularies, formats, and levels of detail. A levee system may be described one way in a federal database, another way in a state GIS layer, and yet another way in an engineering inspection report. This fragmentation limits interoperability, undermines semantic consistency, and ultimately hampers risk-informed decision-making. When flood managers cannot reliably connect a culvert record to the levee segment it penetrates, or trace a monitoring asset back to the system it serves, the consequences can be measured in degraded situational awareness during emergencies.

The team’s solution centers on transforming normalized levee datasets into what they call a Levee System Knowledge Graph, or LSKG. A knowledge graph represents information as entities, such as levee systems, segments, structural components, and monitoring assets, connected by meaningful relationships. Rather than treating records as isolated rows in a table, the graph encodes the actual structure of the world: this segment is part of that system, this component is located on that segment, this sensor monitors that structure. The researchers aligned their normalized datasets with the National Levee Database Ontology, abbreviated NLD-O, a formal schema that defines the classes and relationships relevant to levee infrastructure in the United States. Ontology alignment is what gives the graph its semantic spine, ensuring that the same concept is represented the same way regardless of which source dataset it came from.

The choice of ontology was not arbitrary. The National Levee Database, maintained by the U.S. Army Corps of Engineers, is the country’s authoritative repository of levee information, and the datasets analyzed in the study are publicly available from it. By anchoring the knowledge graph to an ontology derived from this national resource, the framework inherits a vocabulary that flood-risk professionals already use, which matters enormously for adoption. The authors drew on established ontology engineering practices, including the Common Core Ontologies suite and the Basic Formal Ontology, both of which provide rigorously specified mid-level frameworks for representing entities, processes, and their relationships. Tools such as Protégé, the long-standing ontology editor developed at Stanford, support this kind of formal knowledge modeling.

Building the graph, however, is only half the challenge. The real innovation lies in how the framework answers questions. The researchers constructed a graph-addressable semantic corpus and deployed a hybrid retrieval strategy that combines three complementary techniques. The first is TF-IDF vectorization, a classical information retrieval method that dates back to Karen Spärck Jones’s foundational 1972 work on term specificity. TF-IDF weighs terms by how frequently they appear in a document relative to how common they are across the whole corpus, allowing the system to find text passages that are statistically relevant to a query. The second technique is graph reasoning, which exploits the explicit structure of the knowledge graph itself, traversing relationships between entities to answer questions that no single document could answer alone. The third is large language model assistance, in which an LLM interprets the retrieved evidence and composes a natural-language response.

This hybrid architecture is significant because each component compensates for the weaknesses of the others. Pure vector retrieval can find text that looks relevant but miss answers that require multi-hop reasoning across the graph. Pure graph queries are precise but demand structured input that casual users cannot provide. Large language models are fluent but notoriously prone to hallucination when asked to reason about facts they have never seen. By grounding the LLM in retrieved evidence from both the semantic corpus and the graph, the framework follows the retrieval-augmented generation paradigm introduced by researchers at Facebook AI in 2020, while extending it with graph-native reasoning. Crucially, the design preserves traceability: every answer can be linked back to the specific infrastructure records that support it, a property that is essential in engineering contexts where accountability matters.

To evaluate the system rigorously, the authors went beyond simply demonstrating that a knowledge graph could be built. They introduced a quantitative benchmark of ontology-aware levee infrastructure questions spanning four task categories: entity retrieval, which tests whether the system can identify specific objects; attribute retrieval, which tests whether it can report properties of those objects; relationship reasoning, which tests whether it can navigate connections between entities; and aggregation tasks, which require counting, summing, or otherwise computing over sets of records. Performance was measured using Exact Match, which requires the response to match a reference answer precisely, and Contains Match, which accepts answers that contain the correct value, along with response latency.

The results were remarkable in their consistency. The framework achieved 95.16 percent on both Exact Match and Contains Match, indicating that when the system answered correctly, it did so with precision rather than vague approximation. For a domain where a misidentified levee segment or an incorrect culvert count could have safety implications, that level of exactness is the difference between a research demo and a decision-support tool. The benchmark itself is a contribution, since the authors note that evaluating GraphRAG systems on domain-specific, ontology-aware questions remains rare, and they explicitly call for broader validation using additional datasets and independent benchmarks.

The implications extend well beyond levees. Flood risk is escalating as climate change drives non-stationary hydrology, a shift famously summarized in a 2008 Science paper declaring that stationarity is dead in water management. Agencies including FEMA and the U.S. Army Corps of Engineers have emphasized that levee safety depends on integrating inspection records, geospatial data, and monitoring information, and recent research has explored UAV-based thermal imaging for seepage detection, InSAR satellite deformation monitoring, and machine learning for culvert inspection. All of these technologies generate yet more heterogeneous data, which makes a semantic integration layer arguably a prerequisite for any intelligent flood-risk governance. A knowledge graph that can absorb sensor observations, geospatial reasoning, and temporal information, as the authors envision in future extensions, could become the connective tissue for next-generation infrastructure intelligence.

The study also offers a template for how scientific domains broadly might tame their own data chaos. Geoscience knowledge graph efforts, from earthquake emergency support frameworks to large collaborative programs, have been converging on the same insight: large language models become dramatically more reliable when anchored to formally structured, domain-specific knowledge. The levee work demonstrates the full pipeline, from ontology development and data normalization through graph construction in a platform like Neo4j, to hybrid retrieval and benchmark evaluation. Supported by the National Geospatial-Intelligence Agency through the Oak Ridge Institute for Science and Education, and grounded in publicly available National Levee Database records, the framework shows that trustworthy, traceable, natural-language access to critical infrastructure knowledge is no longer a distant aspiration but an engineering achievement with a measured score of 95.16 percent to prove it.

Subject of Research: An ontology-driven GraphRAG framework integrating levee infrastructure data into a knowledge graph for semantic querying and flood-risk decision support

Article Title: Hybrid GraphRAG framework for semantic integration and querying of levee infrastructure data

Article References: Davarpanah, A., Scully, E. J., Lipscomb, M. R., & Morris, A. L. (2026). Hybrid GraphRAG framework for semantic integration and querying of levee infrastructure data. Earth Science Informatics, 19(11), Article 185. https://doi.org/10.1007/s12145-026-02234-3

Image Credits: AI Generated

DOI: 10.1007/s12145-026-02234-3

Keywords: levee infrastructure, knowledge graph, GraphRAG, ontology, large language models, flood risk, National Levee Database, semantic integration, information retrieval, TF-IDF, Neo4j, civil engineering