Discover the publications that power newmind AI—from protocol papers and scientific research to ontology engineering, semantic governance, and agentic system design.
How structured ontology turns scattered legal records into contestable, governed reasoning — the theory behind newmind's semantic layer.
Make the environment — not the prompt — the design object. Read the corpus once, anchor every fact to its page, and reason in terms that do not drift.
ModernBERT encoders pre-trained from scratch on 112.7B Turkish-dominant tokens and continually adapted — reaching top-3 on the Turkish retrieval leaderboard at a fraction of the parameters.
A Turkish embedding model trained on native — not machine-translated — data with matryoshka representation learning, setting new marks on natural-language inference and semantic textual similarity.
A retrieval-tuned TurkEmbed variant fine-tuned on MS-MARCO-TR that outperforms TurkColBERT on Scifact-TR by 19–26%, raising the bar for Turkish information retrieval.
The first comprehensive benchmark of dense bi-encoders against late-interaction ColBERT-style retrievers for morphologically rich Turkish, across five BEIR-TR domains.
The first suite of hallucination-detection models for Turkish RAG, framing the problem as token-level classification across question answering, data-to-text, and summarization.
A systematic study of guided decoding — Outlines, XGrammar, and LM Format Enforcer — and how multi-turn prompting shapes structured, hallucination-resistant RAG output.
A robustness benchmark that measures how far language models bend the truth under authority and social pressure, with an eight-state behavioral taxonomy evaluated across 22 models.
A training-free method that uses the Ramer–Douglas–Peucker algorithm to pick which layers to adapt — beating full LoRA fine-tuning while touching far fewer layers.
A 15-million-node Turkish synonym graph with a three-way relation discriminator that finally separates synonyms from antonyms and tames semantic drift in large-scale clustering.
A hybrid pipeline — FastText clustering, Gemini classification, and curated dictionaries — that builds an 843K-pair Turkish semantic-relations corpus, a 10× scale-up for about $65.