Elamur Research⌕
☰
home / authors / Hannah Rose Kirk

Hannah Rose Kirk

3 papers on this site · 2023–2024

current affiliationUniversity of Oxford, Oxford, United Kingdom

Hannah Rose Kirk has 3 papers on this site, in 2023–2024, most of them on Language models & pretraining, Evaluation & benchmarks, Bias, fairness & safety; often with Paul Rottger, Bertie Vidgen, Dirk Hovy.

OpenAlex · ORCID · h-index 16 · 53 works · 1 171 citations OpenAlex, 2026-10-14

3 works on this site · 502 citations in our library · 3 more works in our library · ⭐ Paper Star rank #2837

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

Affiliations

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 more institutions on single bylines are not listed.

Topics

Language models & pretraining2Evaluation & benchmarks2Bias, fairness & safety1

Works by year

2020s

Papers

The most cited first (OpenAlex and our library).

  1. XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models (2023 · 227 citations)
    Safety tuning teaches LLMs to decline harmful requests. Pushed too far, it makes them refuse harmless questions that merely look dangerous because of a word or topic. The authors call this exaggerated safety and present XSTest, a small hand-built diagnostic suite for measuring it.
  2. SemEval-2023 Task 10: Explainable Detection of Online Sexism (2023 · 185 citations)
    Most automated sexism detectors only say whether a post is sexist, without explaining why. This SemEval-2023 shared task, EDOS (Explainable Detection of Online Sexism), addresses that gap by organising detection into three hierarchical levels. Task A is a binary sexist/not-sexist decision. Task B assigns sexist posts…
  3. Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models (2024 · 134 citations)
    Many studies measure the values and opinions of large language models (LLMs) by giving them multiple-choice questionnaires.

Also in our library

3 more works of theirs are in our library without a page here yet; they will appear as we publish them.

Co-authors here

8 co-authors with a page, the most papers together first.

Cited by

Papers of our library cite their works 502 times (of the 140 884 papers whose bibliographies we read); 23 citing papers with a page here →.

This page in Markdown → https://md.research.elamur.ai/free/en/authors/hannah-rose-kirk/