Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2510.03748 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916990208180224 |
|---|---|
| author | Kakavand, Ramtin Ansari, Ebrahim |
| author_facet | Kakavand, Ramtin Ansari, Ebrahim |
| contents | Large Language Models (LLMs) have consistently demonstrated strong performance in machine translation, especially when guided by high-quality prompts. Few-shot prompting is an effective technique to improve translation quality; however, most existing example selection methods focus solely on query-to-example similarity and do not account for the quality of the examples. In this work, we propose TreePrompt, a novel example selection approach that learns LLM preferences to identify high-quality, contextually relevant examples within a tree-structured framework. To further explore the balance between similarity and quality, we combine TreePrompt with K-Nearest Neighbors (K-NN) and Adaptive Few-Shot Prompting (AFSP). Evaluations on two language pairs - English-Persian (MIZAN) and English-German (WMT19) - show that integrating TreePrompt with AFSP or Random selection leads to improved translation performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_03748 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TreePrompt: Leveraging Hierarchical Few-Shot Example Selection for Improved English-Persian and English-German Translation Kakavand, Ramtin Ansari, Ebrahim Computation and Language Artificial Intelligence Large Language Models (LLMs) have consistently demonstrated strong performance in machine translation, especially when guided by high-quality prompts. Few-shot prompting is an effective technique to improve translation quality; however, most existing example selection methods focus solely on query-to-example similarity and do not account for the quality of the examples. In this work, we propose TreePrompt, a novel example selection approach that learns LLM preferences to identify high-quality, contextually relevant examples within a tree-structured framework. To further explore the balance between similarity and quality, we combine TreePrompt with K-Nearest Neighbors (K-NN) and Adaptive Few-Shot Prompting (AFSP). Evaluations on two language pairs - English-Persian (MIZAN) and English-German (WMT19) - show that integrating TreePrompt with AFSP or Random selection leads to improved translation performance. |
| title | TreePrompt: Leveraging Hierarchical Few-Shot Example Selection for Improved English-Persian and English-German Translation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2510.03748 |