Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2311.09758 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912048721428480 |
|---|---|
| author | Lee, Chia-Hsuan Cheng, Hao Ostendorf, Mari |
| author_facet | Lee, Chia-Hsuan Cheng, Hao Ostendorf, Mari |
| contents | Large language models (LLMs) have revolutionized the landscape of Natural Language Processing systems, but are computationally expensive. To reduce the cost without sacrificing performance, previous studies have explored various approaches to harness the potential of Small Language Models (SLMs) as cost-effective alternatives to their larger counterparts. Driven by findings that SLMs and LLMs exhibit complementary strengths in a structured knowledge extraction task, this work presents a novel SLM/LLM routing framework designed to improve computational efficiency and enhance task performance. First, exemplar pools are created to represent the types of contexts where each LM provides a more reliable answer, leveraging a sentence embedding fine-tuned so that context similarity is close to dialogue state similarity. Then, during inference, the k-nearest exemplars to the testing instance are retrieved, and the instance is routed according to majority vote. In dialogue state tracking tasks, the proposed routing framework enhances performance substantially compared to relying solely on LLMs, while reducing the computational costs by over 50%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_09758 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Tracking Lee, Chia-Hsuan Cheng, Hao Ostendorf, Mari Computation and Language Large language models (LLMs) have revolutionized the landscape of Natural Language Processing systems, but are computationally expensive. To reduce the cost without sacrificing performance, previous studies have explored various approaches to harness the potential of Small Language Models (SLMs) as cost-effective alternatives to their larger counterparts. Driven by findings that SLMs and LLMs exhibit complementary strengths in a structured knowledge extraction task, this work presents a novel SLM/LLM routing framework designed to improve computational efficiency and enhance task performance. First, exemplar pools are created to represent the types of contexts where each LM provides a more reliable answer, leveraging a sentence embedding fine-tuned so that context similarity is close to dialogue state similarity. Then, during inference, the k-nearest exemplars to the testing instance are retrieved, and the instance is routed according to majority vote. In dialogue state tracking tasks, the proposed routing framework enhances performance substantially compared to relying solely on LLMs, while reducing the computational costs by over 50%. |
| title | OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Tracking |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2311.09758 |