Large Language Models as Analogical Reasoners
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914708624244736 |
|---|---|
| author | Yasunaga, Michihiro Chen, Xinyun Li, Yujia Pasupat, Panupong Leskovec, Jure Liang, Percy Chi, Ed H. Zhou, Denny |
| author_facet | Yasunaga, Michihiro Chen, Xinyun Li, Yujia Pasupat, Panupong Leskovec, Jure Liang, Percy Chi, Ed H. Zhou, Denny |
| contents | Chain-of-thought (CoT) prompting for language models demonstrates impressive performance across reasoning tasks, but typically needs labeled exemplars of the reasoning process. In this work, we introduce a new prompting approach, analogical prompting, designed to automatically guide the reasoning process of large language models. Inspired by analogical reasoning, a cognitive process in which humans draw from relevant past experiences to tackle new problems, our approach prompts language models to self-generate relevant exemplars or knowledge in the context, before proceeding to solve the given problem. This method presents several advantages: it obviates the need for labeling or retrieving exemplars, offering generality and convenience; it can also tailor the generated exemplars and knowledge to each problem, offering adaptability. Experimental results show that our approach outperforms 0-shot CoT and manual few-shot CoT in a variety of reasoning tasks, including math problem solving in GSM8K and MATH, code generation in Codeforces, and other reasoning tasks in BIG-Bench. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_01714 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Large Language Models as Analogical Reasoners Yasunaga, Michihiro Chen, Xinyun Li, Yujia Pasupat, Panupong Leskovec, Jure Liang, Percy Chi, Ed H. Zhou, Denny Machine Learning Chain-of-thought (CoT) prompting for language models demonstrates impressive performance across reasoning tasks, but typically needs labeled exemplars of the reasoning process. In this work, we introduce a new prompting approach, analogical prompting, designed to automatically guide the reasoning process of large language models. Inspired by analogical reasoning, a cognitive process in which humans draw from relevant past experiences to tackle new problems, our approach prompts language models to self-generate relevant exemplars or knowledge in the context, before proceeding to solve the given problem. This method presents several advantages: it obviates the need for labeling or retrieving exemplars, offering generality and convenience; it can also tailor the generated exemplars and knowledge to each problem, offering adaptability. Experimental results show that our approach outperforms 0-shot CoT and manual few-shot CoT in a variety of reasoning tasks, including math problem solving in GSM8K and MATH, code generation in Codeforces, and other reasoning tasks in BIG-Bench. |
| title | Large Language Models as Analogical Reasoners |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2310.01714 |