ItD: Large Language Models Can Teach Themselves Induction through Deduction
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_ | 1866911792465182720 |
|---|---|
| author | Sun, Wangtao Xu, Haotian Yu, Xuanqing Chen, Pei He, Shizhu Zhao, Jun Liu, Kang |
| author_facet | Sun, Wangtao Xu, Haotian Yu, Xuanqing Chen, Pei He, Shizhu Zhao, Jun Liu, Kang |
| contents | Although Large Language Models (LLMs) are showing impressive performance on a wide range of Natural Language Processing tasks, researchers have found that they still have limited ability to conduct induction. Recent works mainly adopt ``post processes'' paradigms to improve the performance of LLMs on induction (e.g., the hypothesis search & refinement methods), but their performance is still constrained by the inherent inductive capability of the LLMs. In this paper, we propose a novel framework, Induction through Deduction (ItD), to enable the LLMs to teach themselves induction through deduction. The ItD framework is composed of two main components: a Deductive Data Generation module to generate induction data and a Naive Bayesian Induction module to optimize the fine-tuning and decoding of LLMs. Our empirical results showcase the effectiveness of ItD on two induction benchmarks, achieving relative performance improvement of 36% and 10% compared with previous state-of-the-art, respectively. Our ablation study verifies the effectiveness of two key modules of ItD. We also verify the effectiveness of ItD across different LLMs and deductors. The data and code of this paper can be found at https://anonymous.4open.science/r/ItD-E844. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_05789 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ItD: Large Language Models Can Teach Themselves Induction through Deduction Sun, Wangtao Xu, Haotian Yu, Xuanqing Chen, Pei He, Shizhu Zhao, Jun Liu, Kang Computation and Language Artificial Intelligence Although Large Language Models (LLMs) are showing impressive performance on a wide range of Natural Language Processing tasks, researchers have found that they still have limited ability to conduct induction. Recent works mainly adopt ``post processes'' paradigms to improve the performance of LLMs on induction (e.g., the hypothesis search & refinement methods), but their performance is still constrained by the inherent inductive capability of the LLMs. In this paper, we propose a novel framework, Induction through Deduction (ItD), to enable the LLMs to teach themselves induction through deduction. The ItD framework is composed of two main components: a Deductive Data Generation module to generate induction data and a Naive Bayesian Induction module to optimize the fine-tuning and decoding of LLMs. Our empirical results showcase the effectiveness of ItD on two induction benchmarks, achieving relative performance improvement of 36% and 10% compared with previous state-of-the-art, respectively. Our ablation study verifies the effectiveness of two key modules of ItD. We also verify the effectiveness of ItD across different LLMs and deductors. The data and code of this paper can be found at https://anonymous.4open.science/r/ItD-E844. |
| title | ItD: Large Language Models Can Teach Themselves Induction through Deduction |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2403.05789 |