Recent progress in language models has been defined by scale, yet many practical applications benefit more from robust reasoning than extensive parametric knowledge. We introduce OCC-RAG, a family of models for faithful context-based QA, which prioritizes task-specific reasoning capabilities over knowledge capacity. To train OCC-RAG, we implement a novel pipeline synthesizing over three million multi-context, multi-hop QA examples that target multi-hop reasoning, strict context faithfulness, and calibrated abstention. Mid-trained on this corpus, the models produce structured reasoning traces with source citations grounded in literal quotes from the context. Despite their compact size, OCC-RAG models outperform their same-size general-purpose counterparts on every benchmark and exceed models 2–6× larger on financial reasoning (TAT-QA) and faithfulness (ConFiQA), attaining the best results among all evaluated open-weight models up to 32B parameters. On ConFiQA they rank behind only a frontier proprietary models; on multi-hop reasoning (HotpotQA, MuSiQue) and refusal (MuSiQue-Un) they are on par with 8B-class models and close much of the remaining gap to the largest evaluated systems. We release both our code and family of models.[<https://hf.co/collections/occ-ai/occ-rag>]

Knowledge graphs (KGs) provide structured, verifiable grounding for large language models (LLMs), but current LLM-based systems commonly use KGs as auxiliary structures for text retrieval, leaving their intrinsic quality underexplored.In this work, we propose Wikontic, a multi-stage pipeline that constructs KGs from open-domain texts by extracting candidate triplets with qualifiers, enforcing Wikidata-based type and relation constraints, and normalizing entities to reduce duplication.The resulting KGs are compact, ontology-consistent, and well-connected; on MuSiQue, the correct answer entity appears in 96% of generated triplets.On HotpotQA, our triplets-only setup achieves 76.0 F1, and on MuSiQue 59.8 F1, matching or surpassing several retrieval-augmented generation baselines that still require textual context. In addition, Wikontic attains state-of-the-art information-retention performance on the MINE-1 benchmark (86%), outperforming prior KG construction methods.Wikontic is also efficient at build time: KG construction uses less than 1,000 output tokens, about 3× fewer than AriGraph and <1/20 of GraphRAG.The proposed pipeline improves the quality of the generated KG and offers a scalable solution for leveraging structured knowledge in LLMs. Wikontic is available at https://github.com/screemix/Wikontic.

This study explores a method for extending real-world knowledge graphs (specifically, Wikidata) by extracting triplets from texts with the aid of Large Language Models (LLMs). We propose a two-step pipeline that includes the initial extraction of entity candidates, followed by their refinement and linkage to the canonical entities and relations of the knowledge graph. Finally, we utilize Wikidata relation constraints to select only verified triplets. We compare our approach to a model that was fine-tuned on a machine-generated dataset and demonstrate that it performs better on natural data. Our results suggest that LLM-based triplet extraction from texts, with subsequent verification, is a viable method for real-world applications.

Real-world Knowledge Graphs (KGs) often suffer from incompleteness, which limits their potential performance. Knowledge Graph Completion (KGC) techniques aim to address this issue. However, traditional KGC methods are computationally intensive and impractical for large-scale KGs, necessitating the learning of dense node embeddings and computing pairwise distances. Generative transformer-based language models (e.g., T5 and recent KGT5) offer a promising solution as they can predict the tail nodes directly. In this study, we propose to include node neighborhoods as additional information to improve KGC methods based on language models. We examine the effects of this imputation and show that, on both inductive and transductive Wikidata subsets, our method outperforms KGT5 and conventional KGC approaches. We also provide an extensive analysis of the impact of neighborhood on model prediction and show its importance. Furthermore, we point the way to significantly improve KGC through more effective neighborhood selection.