Revisiting Instruction Fine-tuned Model Evaluation to Guide Industrial Applications
Manuel Faysse, Gautier Viaud, Céline Hudelot, Pierre Colombo
Abstract
Instruction Fine-Tuning (IFT) is a powerful paradigm that strengthens the zero-shot capabilities of Large Language Models (LLMs), but in doing so induces new evaluation metric requirements. We show LLM-based metrics to be well adapted to these requirements, and leverage them to conduct an investigation of task-specialization strategies, quantifying the trade-offs that emerge in practical industrial settings. Our findings offer practitioners actionable insights for real-world IFT model deployment.- Anthology ID:
- 2023.emnlp-main.559
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 9033–9048
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.559
- DOI:
- 10.18653/v1/2023.emnlp-main.559
- Cite (ACL):
- Manuel Faysse, Gautier Viaud, Céline Hudelot, and Pierre Colombo. 2023. Revisiting Instruction Fine-tuned Model Evaluation to Guide Industrial Applications. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9033–9048, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Revisiting Instruction Fine-tuned Model Evaluation to Guide Industrial Applications (Faysse et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2023.emnlp-main.559.pdf