paper-with-me

홈 › Papers

Using Natural Sentences for Understanding Biases in Language Models

2022-05-12 · Sarah Alnegheimish, Alicia Guo, Yi Sun

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.

📄 PDF Abstract BibTeX arXiv:2205.06303

Code (1)

aliciasun/natural-prompts 공식 구현 pytorch

Tasks

Sentence

Similar Papers 제목 키워드 기반

Using Natural Sentence Prompts for Understanding Biases in Language Models

2022-01-16 · ACL ARR January 2022 1 · Anonymous

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…

Sentence

Using Natural Sentence Prompts for Understanding Biases in Language Models

2022-07-01 · NAACL 2022 7 · Sarah Alnegheimish, Alicia Guo, Yi Sun

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…

Sentence

BTC-SAM: Leveraging LLMs for Generation of Bias Test Cases for Sentiment Analysis Models

2025-09-28 · Zsolt T. Kardkovacs, Lynda Djennane, Anna Field, Boualem Benatallah 외 arxiv

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 Analysis

Priorless Recurrent Networks Learn Curiously

2020-12-01 · COLING 2020 8 · Jeff Mitchell, Jeffrey Bowers

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 AcquisitionSentence

Investigating Biases in Textual Entailment Datasets

2019-06-23 · Shawn Tan, Yikang Shen, Chin-wei Huang, Aaron Courville

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