Assessment of RAG and Fine-Tuning for Industrial Question-Answering-Applications
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913109452521472 |
|---|---|
| author | Sturm, Jakob Pichlmeier, Josef Bernhard, Christian Karalashvili, Maka Klepsch, Johannes Groh, Georg Luckow, Andre |
| author_facet | Sturm, Jakob Pichlmeier, Josef Bernhard, Christian Karalashvili, Maka Klepsch, Johannes Groh, Georg Luckow, Andre |
| contents | Large Language Models (LLMs) are increasingly employed in enterprise question-answering (QA) systems, requiring adaptation to domain-specific knowledge. Among the most prevalent methods for incorporating such knowledge are Retrieval-Augmented Generation (RAG) and fine-tuning (FT). Yet, from a cost-accuracy trade-off perspective, it remains unclear which approach best suits industry scenarios. This study examines the impact of RAG and FT on two closed datasets specific to the automotive industry, assessing answer quality and operational costs. We extend the Cost-of-Pass framework proposed by Erol et al. (arXiv:2504.13359) to jointly assess output quality, generation cost, and user interaction cost. Our findings reveal that while premium models perform best out of the box, open-source models can achieve comparable quality when enhanced with RAG. Overall, RAG emerges as the most effective and cost-efficient adaptation method for both closed- and open-source models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_09533 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Assessment of RAG and Fine-Tuning for Industrial Question-Answering-Applications Sturm, Jakob Pichlmeier, Josef Bernhard, Christian Karalashvili, Maka Klepsch, Johannes Groh, Georg Luckow, Andre Computation and Language Artificial Intelligence Large Language Models (LLMs) are increasingly employed in enterprise question-answering (QA) systems, requiring adaptation to domain-specific knowledge. Among the most prevalent methods for incorporating such knowledge are Retrieval-Augmented Generation (RAG) and fine-tuning (FT). Yet, from a cost-accuracy trade-off perspective, it remains unclear which approach best suits industry scenarios. This study examines the impact of RAG and FT on two closed datasets specific to the automotive industry, assessing answer quality and operational costs. We extend the Cost-of-Pass framework proposed by Erol et al. (arXiv:2504.13359) to jointly assess output quality, generation cost, and user interaction cost. Our findings reveal that while premium models perform best out of the box, open-source models can achieve comparable quality when enhanced with RAG. Overall, RAG emerges as the most effective and cost-efficient adaptation method for both closed- and open-source models. |
| title | Assessment of RAG and Fine-Tuning for Industrial Question-Answering-Applications |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2605.09533 |