Codebooks--documents that operationalize constructs and outline annotation procedures--
are used almost universally by social scientists when coding unstructured political texts …

Generating rationales that justify scoring decisions has been a promising way to facilitate
explainability in automated scoring systems. However, existing methods do not match the …

The rise of the term" mechanistic interpretability" has accompanied increasing interest in
understanding neural models--particularly language models. However, this jargon has also …

Explanation constitutes an archetypal feature of human rationality, underpinning learning
and generalisation, and representing one of the media supporting scientific discovery and …

Explanation constitutes an archetypal feature of human rationality, underpinning learning,
and generalisation, and representing one of the media supporting scientific discovery and …

Multiple-choice question answering (MCQA) is a key competence of performant transformer
language models that is tested by mainstream benchmarks. However, recent evidence …

The advent of large-scale pretrained Language Models (LMs) has ushered in a new era in
Natural Language Processing (NLP). These models, trained on massive text corpora, have …

Extended endocrine therapy beyond 5 years is of major concern to ER+ breast cancer
survivors. However, it might be unsuitable to apply routinely used genomic tests designed …