Using Natural Sentences for Understanding Biases in Language Models
Evaluation of biases in language models is often limited to synthetically generated datasets. This dependence traces back to the need for a prompt-style dataset to trigger specific behaviors of language models. In this paper, we address this gap by creating a prompt dataset with respect to occupations collected from real-world natural sentences present in Wikipedia. We aim to understand the differences between using template-based prompts and natural sentence prompts when studying gender-occupation biases in language models. We find bias evaluations are very sensitive to the design choices of template prompts, and we propose using natural sentence prompts for systematic evaluations to step away from design choices that could introduce bias in the observations.
Code (1)
Tasks
SentenceSimilar Papers 제목 키워드 기반
Using Natural Sentence Prompts for Understanding Biases in Language Models
Evaluation of biases in language models is often limited to synthetically generated datasets. This dependence traces back to the need of prompt-style dataset to trigger specific behaviors of language models. In this pape…
SentenceUsing Natural Sentence Prompts for Understanding Biases in Language Models
Evaluation of biases in language models is often limited to synthetically generated datasets. This dependence traces back to the need of prompt-style dataset to trigger specific behaviors of language models. In this pape…
SentenceBTC-SAM: Leveraging LLMs for Generation of Bias Test Cases for Sentiment Analysis Models
Sentiment Analysis (SA) models harbor inherent social biases that can be harmful in real-world applications. These biases are identified by examining the output of SA models for sentences that only vary in the identity g…
Sentiment AnalysisPriorless Recurrent Networks Learn Curiously
Recently, domain-general recurrent neural networks, without explicit linguistic inductive biases, have been shown to successfully reproduce a range of human language behaviours, such as accurately predicting number agree…
Language AcquisitionSentenceInvestigating Biases in Textual Entailment Datasets
The ability to understand logical relationships between sentences is an important task in language understanding. To aid in progress for this task, researchers have collected datasets for machine learning and evaluation …
BIG-bench Machine LearningNatural Language InferenceQuestion AnsweringVisual Question Answering+1