Saved in:
Bibliographic Details
Main Authors: Hudspeth, Marisa, Burns, Patrick J., O'Connor, Brendan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.20738
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914499375661056
author Hudspeth, Marisa
Burns, Patrick J.
O'Connor, Brendan
author_facet Hudspeth, Marisa
Burns, Patrick J.
O'Connor, Brendan
contents We introduce a benchmark dataset for question answering and translation in bilingual Latin and English settings, containing about 7,800 question-answer pairs. The questions are drawn from Latin pedagogical sources, including exams, quizbowl-style trivia, and textbooks ranging from the 1800s to the present. After automated extraction, cleaning, and manual review, the dataset covers a diverse range of question types: knowledge- and skill-based, multihop reasoning, constrained translation, and mixed language pairs. To our knowledge, this is the first QA benchmark centered on Latin. As a case study, we evaluate three large language models -- LLaMa 3, Qwen QwQ, and OpenAI's o3-mini -- finding that all perform worse on skill-oriented questions. Although the reasoning models perform better on scansion and literary-device tasks, they offer limited improvement overall. QwQ performs slightly better on questions asked in Latin, but LLaMa3 and o3-mini are more task dependent. This dataset provides a new resource for assessing model capabilities in a specialized linguistic and cultural domain, and the creation process can be easily adapted for other languages. The dataset is available at: https://github.com/slanglab/RespondeoQA
format Preprint
id arxiv_https___arxiv_org_abs_2604_20738
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RespondeoQA: a Benchmark for Bilingual Latin-English Question Answering
Hudspeth, Marisa
Burns, Patrick J.
O'Connor, Brendan
Computation and Language
We introduce a benchmark dataset for question answering and translation in bilingual Latin and English settings, containing about 7,800 question-answer pairs. The questions are drawn from Latin pedagogical sources, including exams, quizbowl-style trivia, and textbooks ranging from the 1800s to the present. After automated extraction, cleaning, and manual review, the dataset covers a diverse range of question types: knowledge- and skill-based, multihop reasoning, constrained translation, and mixed language pairs. To our knowledge, this is the first QA benchmark centered on Latin. As a case study, we evaluate three large language models -- LLaMa 3, Qwen QwQ, and OpenAI's o3-mini -- finding that all perform worse on skill-oriented questions. Although the reasoning models perform better on scansion and literary-device tasks, they offer limited improvement overall. QwQ performs slightly better on questions asked in Latin, but LLaMa3 and o3-mini are more task dependent. This dataset provides a new resource for assessing model capabilities in a specialized linguistic and cultural domain, and the creation process can be easily adapted for other languages. The dataset is available at: https://github.com/slanglab/RespondeoQA
title RespondeoQA: a Benchmark for Bilingual Latin-English Question Answering
topic Computation and Language
url https://arxiv.org/abs/2604.20738