This study explores a semantic variation methodology to augment training data by generating question-answer pairs with explicit control over semantic similarity, and shows that semantically controlled augmentation improves domain-specific knowledge acquisition while preserving consistency.
Natural Language Understanding (NLU) addresses cross-domain challenges in understanding language due to inconsistent data distributions, uncertain concept semantics, and inconsistent language use specific to individual domains across different geographical locations. The majority of classical deep learning systems perform poorly because it cannot generalize, leading to cross-domain underperformance in practical settings. Therefore, this research develops a new class of meta-learning that provides a systematic means to advance cross-domain adaptability for NLU in the context of distributed knowledge systems. More specifically, this approach combines federated learning methods, model-agnostic meta-learning (MAML), and domain-adaptive transformers for the first time to enable rapid extraction of domain-invariant representations while concurrently maintaining local contextual semantics across reasonably distributed datasets. The author conducted benchmark assessments on the most recent multi-domain evaluations and cross-lingual and domain-shifted data to simulate distributed knowledge systems. The custom model outperformed all baselines, transformers, and fine-tuning models by an average of 12.8% cross-domain accuracy, 15.3% lower generalization error, and 18.6% faster convergence rate. In the scenario, the new model decreased to less than 90% and maintained over 90% of its performance after a 40% reduction in training samples. Meta-learning enables superior transfer efficiency and model adaptation to new, previously unseen domains with minimal training. The new meta-learning frameworks successfully addressed the required performance and adaptability for advanced intelligent information systems for cross-domain NLU in distributed knowledge bases.
Deepti Patnaik, Rakshak Bharti· 2026 6th International Confe...· 0 citations
The integration of Large Language Models into recommender systems has introduced a new paradigm in which models leverage their pre-trained knowledge to generate recommendations. A prevailing assumption is that an LLM’s inherent knowledge is sufficient to support high-quality recommendations across diverse domains. This paper challenges that assumption, positing that in specialized domains, recommendation efficacy is limited by the textual nature of an LLM’s knowledge. To address this limitation, we propose REKALM, a comprehensive integration framework for enhancing LLM-based recommenders through knowledge integration. Central to our approach is the extension of established text-conversion techniques to non-traditional data modalities. We utilize knowledge lexicalization, a process that translates heterogeneous data sources into a unified natural language format. This lexicalized corpus is then used in a knowledge-aware instruction-tuning pipeline to explicitly align the LLM’s internal representations with four distinct types of domain-specific information. We conduct experiments across four distinct domains to validate our framework. Our findings provide consistent empirical evidence that while an LLM’s inherent knowledge may suffice for universally familiar domains like movies, recommendation quality in more specialized areas is significantly improved through knowledge integration. The proposed approach demonstrates that augmenting LLMs with lexicalized, domain-specific knowledge is an effective system-level strategy for advancing the next generation of recommender systems.
Alessandro Petruzzelli, C. Musto, Marco de Gemmis et al.· ACM Transactions on Informat...· 0 citations
Large language models (LLMs) have demonstrated strong reasoning performance, but their tendency to hallucinate limits their reliability in knowledge-intensive tasks requiring up-to-date and grounded information. Combining knowledge graphs (KGs) with LLMs facilitates the use of explicit symbolic knowledge that can be continuously updated without costly fine-tuning, while benefiting from rapidly advancing LLM reasoning. We propose MARS, a scalable knowledge graph question answering (KGQA) approach that requires no model fine-tuning. Rather than relying on open-ended agentic exploration, MARS performs a structured retrieval procedure that links question entities to the KG and iteratively retrieves relevant next-hop information. At each step, MARS decides whether to continue graph traversal or to generate the final SPARQL query, allowing the model to adapt the retrieval depth to the question while keeping the overall pipeline more predictable than fully agentic approaches. We evaluate MARS on three established KGQA benchmarks across several LLMs and settings, including multilingual evaluation, and provide insights through ablation studies and error analysis. Our approach achieves competitive performance relative to state-of-the-art methods while remaining efficient and scalable. The evaluation results, code and resources are publicly available: https://github.com/dice-group/mars-kgqa.
Nikit Srivastava, Daniel Vollmers, René Speck et al.· 0 citations
In recent years, the integration of Large Language Models (LLMs) with knowledge graphs has gained increasing attention as an approach to improve information retrieval and data accessibility. However, few studies have compared finetuned and prompt-based LLM approaches for generating Cypher queries from natural language inputs. This paper presents a comparative study conducted within BMW AG, focusing on the application of LLM-based Text2Cypher generation for querying a domain-specific knowledge graph designed to support virtual product development. Three approaches are evaluated: a baseline model fine-tuned for generic Cypher generation, a newly developed domain-specific fine-tuned model (KG-Finetune-LLM), and an embedding-based prompt engineering approach (KG-Embed-LLM) leveraging GPT-4. Results show that the KG-Embed-LLM achieves the highest retrieval accuracy (96.88%), outperforming both fine-tuned models. Error analysis further reveals that the primary challenge in industrial Text2Cypher generation lies in correctly interpreting domain-specific graph semantics, particularly relationship selection and graph traversal, rather than in generating syntactically valid Cypher queries. The findings highlight the importance of schema-aware grounding for domain-specific knowledge graph applications and identify key trade-offs between retrieval accuracy, deployment complexity, and reliance on external LLM services. Finally, the study outlines future research directions related to ontology complexity and robustness in enterprise knowledge graph environments.
Language models are often used for tasks involving structured data like tables and graphs, but there is no principled approach for choosing the best format to represent such data for fine-tuning. We address this in three steps. First, we show that format choice remains important even after fine-tuning; models learn more efficiently with specific formats rather than adapting to any format. Second, we show that a pre-trained model can suggest its own candidate formats by auto-completing partial prompts, reducing reliance on developer intuition. Third, and most importantly, we demonstrate that base model performance across formats reliably predicts post-fine-tuning performance: the format that performs best before fine-tuning remains among the top candidates after fine-tuning in 16 out of 18 settings across three data structure types, three models, and six tasks. This finding allows format selection to be done via inference alone, avoiding costly trial-and-error fine-tuning runs.
Usneek Singh, Ananya Singha, Abhijeet Awasthi et al.· Proceedings of the First Wor...· 0 citations
Large Language Models (LLMs) show considerable potential for materials-science question answering. However, LLM responses may still be affected by unsupported parametric associations, while dense Retrieval-Augmented Generation (RAG) can fragment relational evidence across text chunks. Moreover, general graph-based retrieval does not necessarily preserve the hierarchical relations and factual attributes required to resolve implicit material constraints. To address these limitations, we propose MCTD-KG, a multi-source heterogeneous knowledge graph integrated with a Knowledge-Enhanced RAG framework for complex material question answering. MCTD-KG adopts a Classification–Term–Data ontology to connect disciplinary taxonomies, domain concepts, semantic relations, and empirical records from toolbooks and the scientific literature. Through LLM-assisted knowledge extraction, entity normalization, and multi-source integration, the resulting graph contains more than 530,000 entities across three layers, including 61,768 text-extracted Term-layer entities. During inference, Dual-Channel Retrieval jointly retrieves query-relevant relational paths and associated material attributes, while an explicit semantic filtering stage screens candidate evidence against the query constraints. Evaluation on an expert-validated benchmark of 1577 questions shows that the proposed framework achieves an overall accuracy of 68.48%, compared with 17.40% for the zero-shot Pure LLM, 24.79% for the best Vanilla RAG setting, and 44.96% for GraphRAG. It also achieves 45.22% accuracy on four-hop questions, compared with 39.49% for GraphRAG. These results indicate that integrating multi-source domain knowledge with relation-preserved retrieval and attribute-supported filtering provides more focused and inspectable evidence, thereby supporting more accurate complex material question answering.
Peize Li, Xi Guo, Nan Yin et al.· Electronics· 0 citations