Mitigating Selection Bias with Node Pruning and Auxiliary Options

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.

Annotation Sensitivity: Training Data Collection Methods Affect Model Performance

When training data are collected from human annotators, the design of the annotation instrument, the instructions given to annotators, the characteristics of the annotators, and their interactions can impact training data. This study demonstrates that design choices made when creating an annotation instrument also impact the models trained on the resulting annotations. We introduce the term annotation sensitivity to refer to the impact of annotation data collection methods on the annotations themselves and on downstream model performance and predictions. We collect annotations of hate speech and offensive language in five experimental conditions of an annotation instrument, randomly assigning annotators to conditions. We then fine-tune BERT models on each of the five resulting datasets and evaluate model performance on a holdout portion of each condition. We find considerable differences between the conditions for 1) the share of hate speech/offensive language annotations, 2) model performance, 3) model predictions, and 4) model learning curves. Our results emphasize the crucial role played by the annotation instrument which has received little attention in the machine learning literature. We call for additional research into how and why the instrument impacts the annotations to inform the development of best practices in instrument design.