paper-with-me

홈 › Papers

Ask-Before-Detection: Identifying and Mitigating Conformity Bias in LLM-Powered Error Detector for Math Word Problem Solutions

2024-12-22 · Hang Li, Tianlong Xu, Kaiqi Yang, Yucheng Chu, Yanling Chen, Yichi Song, Qingsong Wen, Hui Liu

The rise of large language models (LLMs) offers new opportunities for automatic error detection in education, particularly for math word problems (MWPs). While prior studies demonstrate the promise of LLMs as error detectors, they overlook the presence of multiple valid solutions for a single MWP. Our preliminary analysis reveals a significant performance gap between conventional and alternative solutions in MWPs, a phenomenon we term conformity bias in this work. To mitigate this bias, we introduce the Ask-Before-Detect (AskBD) framework, which generates adaptive reference solutions using LLMs to enhance error detection. Experiments on 200 examples of GSM8K show that AskBD effectively mitigates bias and improves performance, especially when combined with reasoning-enhancing techniques like chain-of-thought prompting.

📄 PDF Abstract BibTeX arXiv:2412.16838

Code (0)

등록된 구현이 없습니다.

Tasks

GSM8KMathvalid

Similar Papers 제목 키워드 기반

Debiased Contrastive Representation Learning for Mitigating Dual Biases in Recommender Systems

2024-08-19 · Zhirong Huang, Shichao Zhang, Debo Cheng, Jiuyong Li 외

In recommender systems, popularity and conformity biases undermine recommender effectiveness by disproportionately favouring popular items, leading to their over-representation in recommendation lists and causing an unba…

Contrastive LearningDiversityRecommendation SystemsRepresentation Learning

Towards Trustworthy Audio Deepfake Detection: A Systematic Framework for Diagnosing and Mitigating Gender Bias

2026-05-09 · Aishwarya Fursule, Shruti Kshirsagar, Anderson R. Avila arxiv

Audio deepfake detection systems are increasingly deployed in high-stakes security applications, yet their fairness across demographic groups remains critically underexamined. Prior work measures gender disparity but doe…

Audio Deepfake Detection

Passivity-based Analysis and Design for Population Dynamics with Conformity Biases

2021-11-20 · Shunya Yamashita, Kodai Irifune, Takeshi Hatanaka, Yasuaki Wasa 외

This paper addresses mechanisms for boundedly rational decision makers in discrete choice problem. First, we introduce two mathematical models of population dynamics with conformity biases. We next analyze the models in …

Detecting Melanoma Fairly: Skin Tone Detection and Debiasing for Skin Lesion Classification

2022-02-06 · Peter J. Bevan, Amir Atapour-Abarghouei

Convolutional Neural Networks have demonstrated human-level performance in the classification of melanoma and other skin lesions, but evident performance disparities between differing skin tones should be addressed befor…

Lesion ClassificationSkin Lesion Classification

UPV at CheckThat! 2021: Mitigating Cultural Differences for Identifying Multilingual Check-worthy Claims

2021-09-19 · Ipek Baris Schlicht, Angel Felipe Magnossão de Paula, Paolo Rosso

Identifying check-worthy claims is often the first step of automated fact-checking systems. Tackling this task in a multilingual setting has been understudied. Encoding inputs with multilingual text representations could…

Fact CheckingLanguage Identification