Unsupervised Distractor Generation via Large Language Model Distilling and Counterfactual Contrastive Decoding
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_ | 1866914820938268672 |
|---|---|
| author | Qu, Fanyi Sun, Hao Wu, Yunfang |
| author_facet | Qu, Fanyi Sun, Hao Wu, Yunfang |
| contents | Within the context of reading comprehension, the task of Distractor Generation (DG) aims to generate several incorrect options to confuse readers. Traditional supervised methods for DG rely heavily on expensive human-annotated distractor labels. In this paper, we propose an unsupervised DG framework, leveraging Large Language Models (LLMs) as cost-effective annotators to enhance the DG capability of smaller student models. Specially, to perform knowledge distilling, we propose a dual task training strategy that integrates pseudo distractors from LLMs and the original answer in-formation as the objective targets with a two-stage training process. Moreover, we devise a counterfactual contrastive decoding mechanism for increasing the distracting capability of the DG model. Experiments show that our unsupervised generation method with Bart-base greatly surpasses GPT-3.5-turbo performance with only 200 times fewer model parameters. Our proposed unsupervised DG method offers a cost-effective framework for practical reading comprehension applications, without the need of laborious distractor annotation and costly large-size models |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_01306 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unsupervised Distractor Generation via Large Language Model Distilling and Counterfactual Contrastive Decoding Qu, Fanyi Sun, Hao Wu, Yunfang Computation and Language Within the context of reading comprehension, the task of Distractor Generation (DG) aims to generate several incorrect options to confuse readers. Traditional supervised methods for DG rely heavily on expensive human-annotated distractor labels. In this paper, we propose an unsupervised DG framework, leveraging Large Language Models (LLMs) as cost-effective annotators to enhance the DG capability of smaller student models. Specially, to perform knowledge distilling, we propose a dual task training strategy that integrates pseudo distractors from LLMs and the original answer in-formation as the objective targets with a two-stage training process. Moreover, we devise a counterfactual contrastive decoding mechanism for increasing the distracting capability of the DG model. Experiments show that our unsupervised generation method with Bart-base greatly surpasses GPT-3.5-turbo performance with only 200 times fewer model parameters. Our proposed unsupervised DG method offers a cost-effective framework for practical reading comprehension applications, without the need of laborious distractor annotation and costly large-size models |
| title | Unsupervised Distractor Generation via Large Language Model Distilling and Counterfactual Contrastive Decoding |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.01306 |