29 September 2026 to 3 October 2026
OeAW Main Seat
Europe/Vienna timezone

LLM-Assisted Lexicography in Low-Resource Contexts: From Prompt to Dictionary Article

2 Oct 2026, 15:00
30m
01 | Sitzungssaal (01 | Sitzungssaal, OeAW Main Seat, 1st floor)

01 | Sitzungssaal

01 | Sitzungssaal, OeAW Main Seat, 1st floor

Austrian Academy of Sciences Dr. Ignaz Seipel-Platz 2 1010 Vienna

Speakers

Katharina Korecky-Kröll (Austrian Academy of Sciences, ACDH) Philipp Stöckle (Austrian Academy of Sciences, ACDH) Daniel Elsner (Austrian Academy of Sciences, ACDH) Wolfgang Koppensteiner (Austrian Academy of Sciences, ACDH) Elisabeth Eder (Austrian Academy of Sciences, ACDH)

Description

This paper investigates the potential of Large Language Models (LLMs) to support lexicographic work in low-resource contexts, focusing on Austrian Bavarian dialects documented in the Wörterbuch der bairischen Mundarten in Österreich (WBÖ). Using a structured prompt-engineering workflow and a three-stage data pipeline, 100 dictionary articles were generated with LLaMA 4 (Scout) and systematically compared to human-authored “gold” articles. Evaluation combined automated metrics, LLM-based judgement, and assessment by three human lexicographers. Results show that LLMs reliably reproduce formal lexicographic conventions, producing well-structured and coherent dictionary entries. Nevertheless, limitations emerge in semantic completeness and data fidelity: generated articles sometimes omit senses or misrepresent semantic structure and often inadequately integrate empirical evidence, especially regional information and attestations. While automated metrics indicate a relatively high similarity of original and generated senses based on their embeddings, both human evaluators and LLM-as-a-judge approaches reveal persistent weaknesses. However, the strong alignment between human judgements and the sense similarity metric suggests that embedding-based evaluation is a promising proxy for human assessment, whereas holistic LLM-as-a-judge scores appear comparatively strict and less transparent. The study argues for a hybrid evaluation framework and positions LLMs as assistive tools within human-in-the-loop lexicography.

Presentation materials

There are no materials yet.