Entity · model

encoder-only language models

modelactiveencoder-only-language-models-1932ae17·1 events·first seen May 29, 2026

Aliases: encoder-only language models

Co-occurring entities

neopronouns (xier, en)GRUFF German grammatical gender pronoun fidelity occupational stereotypes

More like this (12)

instruction embedding models multi-turn language models Random Language Model Reasoning Language Models Exposure is Optional: Learning Unlike Coordination in Language Models Tapered Language Models Transformer Language Models Knowledge-Less Language Models Language Models are Few-Shot Learners Knowledgeless Language Models: Suppressing Parametric Recall for Evidence-Grounded Language Modeling Language Model Finetuning Recursive Language Models (RLMs)

Recent events (1)

4arXiv · cs.CL·May 29, 2026·source ↗

GRUFF: Benchmark for LLM Pronoun Fidelity, Reasoning, and Bias in German

The paper introduces GRUFF, a large-scale German dataset designed to evaluate LLM pronoun fidelity—the ability to correctly reuse a previously specified pronoun for a discourse entity despite intervening distractors. The study covers four grammatical gender systems and four pronoun sets including neopronouns (xier, en), finding that LLMs handle masculine and feminine agreement well but struggle with neopronouns and distractor robustness. Encoder-only models show greater robustness in German than English, attributed to grammatical gender cues. Occupational stereotype correlations across grammatical cases are weak and model-dependent.

Evaluation and Benchmarking AI Safety Research neopronouns (xier, en)GRUFF German grammatical gender +3 more