Identifying Fairness Issues in Automatically Generated Testing Content
원문 초록
Natural language generation tools are powerful and effective for generating content. However, language models are known to display bias and fairness issues, making them impractical to deploy for many use cases. We here focus on how fairness issues impact automatically generated test content, which can have stringent requirements to ensure the test measures only what it was intended to measure. Specifically, we review test content generated for a large-scale standardized English proficiency test with the goal of identifying content that only pertains to a certain subset of the test population as well as content that has the potential to be upsetting or distracting to some test takers. Issues like these could inadvertently impact a test taker's score and thus should be avoided. This kind of content does not reflect the more commonly-acknowledged biases, making it challenging even for modern models that contain safeguards. We build a dataset of 601 generated texts annotated for fairness and explore a variety of methods for classification: fine-tuning, topic-based classification, and prompting, including few-shot and self-correcting prompts. We find that combining prompt self-correction and few-shot learning performs best, yielding an F1 score of 0.79 on our held-out test set, while much smaller BERT- and topic-based models have competitive performance on out-of-domain data.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
A Reproducibility Study of Product-side Fairness in Bundle Recommendation
Making Language Model a Hierarchical Classifier and Generator
Mitigating Object Hallucinations via Sentence-Level Early Intervention
The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs
Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarking
Fairness-Aware Grouping for Continuous Sensitive Variables: Application for Debiasing Face Analysis with respect to Skin Tone
토론
이 논문과 연결된 포럼 글이 아직 없습니다.