paper-with-me

Papers

Mitigating Selection Bias with Node Pruning and Auxiliary Options

2024-09-27 · Hyeong Kyu Choi, Weijie Xu, Chi Xue, Stephanie Eckman, Chandan K. Reddy

Large language models (LLMs) often show unwarranted preference for certain choice options when responding to multiple-choice questions, posing significant reliability concerns in LLM-automated systems. To mitigate this selection bias problem, previous solutions utilized debiasing methods to adjust the model's input and/or output. Our work, in contrast, investigates the model's internal representation of the selection bias. Specifically, we introduce a novel debiasing approach, Bias Node Pruning (BNP), which eliminates the linear layer parameters that contribute to the bias. Furthermore, we present Auxiliary Option Injection (AOI), a simple yet effective input modification technique for debiasing, which is compatible even with black-box LLMs. To provide a more systematic evaluation of selection bias, we review existing metrics and introduce Choice Kullback-Leibler Divergence (CKLD), which addresses the insensitivity of the commonly used metrics to label imbalance. Experiments show that our methods are robust and adaptable across various datasets when applied to three LLMs.

📄 PDF Abstract BibTeX arXiv:2409.18857

Code (0)

등록된 구현이 없습니다.

Tasks

Multiple-choiceSelection bias

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge Distillation

2021-06-15 · Cody Blakeney, Nathaniel Huish, Yan Yan, Ziliang Zong

In recent years the ubiquitous deployment of AI has posed great concerns in regards to algorithmic bias, discrimination, and fairness. Compared to traditional forms of bias or discrimination caused by humans, algorithmic…

FairnessKnowledge Distillation

Catalyst: a Novel Regularizer for Structured Pruning with Auxiliary Extension of Parameter Space

2025-07-10 · Jaeheun Jung, Donghun Lee arxiv

Structured pruning aims to reduce the size and computational cost of deep neural networks by removing entire filters or channels. The traditional regularizers such as L1 or Group Lasso and its variants lead to magnitude-…

Randomized Pruning: Efficiently Calculating Expectations in Large Dynamic Programs

2009-12-01 · NeurIPS 2009 12 · Alexandre Bouchard-Côté, Slav Petrov, Dan Klein

Pruning can massively accelerate the computation of feature expectations in large models. However, any single pruning mask will introduce bias. We present a novel approach which employs a randomized sequence of pruning…

CSGNN: Conquering Noisy Node labels via Dynamic Class-wise Selection

2023-11-20 · YiFan Li, Zhen Tan, Kai Shu, Zongsheng Cao 외

Graph Neural Networks (GNNs) have emerged as a powerful tool for representation learning on graphs, but they often suffer from overfitting and label noise issues, especially when the data is scarce or imbalanced. Differe…

MemorizationRepresentation Learning

Breaking through Deterministic Barriers: Randomized Pruning Mask Generation and Selection

2023-10-19 · Jianwei Li, Weizhi Gao, Qi Lei, Dongkuan Xu

It is widely acknowledged that large and sparse models have higher accuracy than small and dense models under the same model size constraints. This motivates us to train a large model and then remove its redundant neuron…