Research resources

lexEN

Expert-reviewed labels for English word sense disambiguation.

• 4,861 test items, built from Maru2022.
• Three lexicographers reviewed 363 disputed cases: 211 labels corrected, 56 items removed.
• GPT-5.5 scores 91.8% with Maru labels → 95.6% with lexEN labels, using the same predictions.

LLM-relabeled SemCor

LLM-generated replacement labels for the SemCor training corpus.

• 226,036 training items, independently relabelled by GPT-5.5 and Gemma 4 31B.
• GPT-5.5 labels lift ConSeC accuracy by 2.4 percentage points on Raganato ALL.
• Same architecture and training recipe; BEM and ESCHER also improve.

SenseBench

A benchmark of accuracy and cost in English word sense disambiguation.

• 69 LLMs and 225 verified runs on 4,861 lexEN items.
• Top fine-grained score: 95.66% (GPT 6 Astra, xhigh; 25 September 2026).
• lexEN, Maru2022 and original Raganato answer keys; fine and broader senses.
• Accuracy, cost, confidence intervals and raw responses for each run.

Glite LENS

A bi-encoder for matching English words in context to their meanings.

• 298M parameters; 89.69% fine-grained accuracy on lexEN.
• ConSeC scores 84.88% and the top LLM 95.66% in the same evaluation.
• About $0.13 per million decisions in measured self-hosted inference.

Glite ARF

Verifier-driven research with parallel LLM coding agents.

Glite English Dictionary

Individual English meanings, with examples, images, video, difficulty and frequency—and the research connecting them to personalised learning.

Sense & idiom frequencies

Understanding how often particular meanings and expressions occur, to inform what a learner studies next.

English vocabulary difficulty

Predicting how hard an English word will be for learners with different first languages.