Retrieve, Generate, Evaluate: A Case Study for Medical Paraphrases Generation with Small Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916333734592512 |
|---|---|
| author | Buhnila, Ioana Sinha, Aman Constant, Mathieu |
| author_facet | Buhnila, Ioana Sinha, Aman Constant, Mathieu |
| contents | Recent surge in the accessibility of large language models (LLMs) to the general population can lead to untrackable use of such models for medical-related recommendations. Language generation via LLMs models has two key problems: firstly, they are prone to hallucination and therefore, for any medical purpose they require scientific and factual grounding; secondly, LLMs pose tremendous challenge to computational resources due to their gigantic model size. In this work, we introduce pRAGe, a pipeline for Retrieval Augmented Generation and evaluation of medical paraphrases generation using Small Language Models (SLM). We study the effectiveness of SLMs and the impact of external knowledge base for medical paraphrase generation in French. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_16565 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Retrieve, Generate, Evaluate: A Case Study for Medical Paraphrases Generation with Small Language Models Buhnila, Ioana Sinha, Aman Constant, Mathieu Computation and Language Recent surge in the accessibility of large language models (LLMs) to the general population can lead to untrackable use of such models for medical-related recommendations. Language generation via LLMs models has two key problems: firstly, they are prone to hallucination and therefore, for any medical purpose they require scientific and factual grounding; secondly, LLMs pose tremendous challenge to computational resources due to their gigantic model size. In this work, we introduce pRAGe, a pipeline for Retrieval Augmented Generation and evaluation of medical paraphrases generation using Small Language Models (SLM). We study the effectiveness of SLMs and the impact of external knowledge base for medical paraphrase generation in French. |
| title | Retrieve, Generate, Evaluate: A Case Study for Medical Paraphrases Generation with Small Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2407.16565 |