Evaluating Prompt-Based and Fine-Tuned Approaches to Czech Anaphora Resolution
| Authors | |
|---|---|
| Year of publication | 2025 |
| Type | Article in Proceedings |
| Conference | Text, Speech, and Dialogue, TSD 2025 |
| MU Faculty or unit | |
| Citation | |
| Keywords | anaphora resolution, sequence-to-sequence models, fine-tuning, prompt engineering |
| Description | Anaphora resolution plays a critical role in natural language understanding, especially in morphologically rich languages like Czech. This paper presents a comparative evaluation of two modern approaches to anaphora resolution on Czech text: prompt engineering with large language models (LLMs) and fine-tuning compact generative models. Using a dataset derived from the Prague Dependency Treebank, we evaluate several instruction-tuned LLMs, including Mistral Large 2 and Llama 3, using a series of prompt templates. We compare them against fine-tuned variants of the mT5 and Mistral models that we trained specifically for Czech anaphora resolution. Our experiments demonstrate that while prompting yields promising few-shot results (up to 74.5\% accuracy), the fine-tuned models, particularly mT5-large, outperform them significantly, achieving up to 88\% accuracy while requiring fewer computational resources. We analyze performance across different anaphora types, antecedent distances, and source corpora, highlighting key strengths and trade-offs of each approach. |
| Related projects: |