Pith. sign in

REVIEW 1 cited by

Unsupervised Distractor Generation via Large Language Model Distilling and Counterfactual Contrastive Decoding

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.01306 v1 pith:R2Z3IZYE submitted 2024-06-03 cs.CL

classification cs.CL
keywords distractorunsupervisedgenerationmodelmodelscapabilitycomprehensioncontrastive
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Mitigating Easy Option Bias in Multiple-Choice Question Answering

    cs.CV 2025-08 conditional novelty 6.0 of 10

    In six VQA benchmarks, models can often choose the correct option from image plus options alone, and the GroundAttack toolkit generates visually plausible hard negatives to remove this shortcut.

Pith tools