paper-with-me

Papers

Critical Perspectives: A Benchmark Revealing Pitfalls in PerspectiveAPI

2023-01-05 · Lorena Piedras, Lucas Rosenblatt, Julia Wilkins

Detecting "toxic" language in internet content is a pressing social and technical challenge. In this work, we focus on PERSPECTIVE from Jigsaw, a state-of-the-art tool that promises to score the "toxicity" of text, with a recent model update that claims impressive results (Lees et al., 2022). We seek to challenge certain normative claims about toxic language by proposing a new benchmark, Selected Adversarial SemanticS, or SASS. We evaluate PERSPECTIVE on SASS, and compare to low-effort alternatives, like zero-shot and few-shot GPT-3 prompt models, in binary classification settings. We find that PERSPECTIVE exhibits troubling shortcomings across a number of our toxicity categories. SASS provides a new tool for evaluating performance on previously undetected toxic language that avoids common normative pitfalls. Our work leads us to emphasize the importance of questioning assumptions made by tools already in deployment for toxicity detection in order to anticipate and prevent disparate harms.

📄 PDF Abstract BibTeX arXiv:2301.01874

Code (1)

lurosenb/sass 공식 구현

Tasks

Binary Classification

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Robust Scaling in Human Brain Dynamics Despite Latent Variables and Limited Sampling Distortions

2025-06-04 · Rubén Calvo, Carles Martorell, Adrián Roig, Miguel A. Muñoz

The idea that information-processing systems operate near criticality to enhance computational performance is supported by scaling signatures in brain activity. However, external signals raise the question of whether thi…

Cross-Lingual Pitfalls: Automatic Probing Cross-Lingual Weakness of Multilingual Large Language Models

2025-05-24 · Zixiang Xu, Yanbo Wang, Yue Huang, Xiuying Chen 외

Large Language Models (LLMs) have achieved remarkable success in Natural Language Processing (NLP), yet their cross-lingual performance consistency remains a significant challenge. This paper introduces a novel methodolo…

A Primer on Motion Capture with Deep Learning: Principles, Pitfalls and Perspectives

2020-09-01 · Alexander Mathis, Steffen Schneider, Jessy Lauer, Mackenzie W. Mathis

Extracting behavioral measurements non-invasively from video is stymied by the fact that it is a hard computational problem. Recent advances in deep learning have tremendously advanced predicting posture from videos dire…

Deep Learning

VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models

2025-04-21 · Weiye Xu, Jiahao Wang, Weiyun Wang, Zhe Chen 외

Visual reasoning is a core component of human intelligence and a critical capability for advanced multimodal models. Yet current reasoning evaluations of multimodal large language models (MLLMs) often rely on text descri…

AttributeVisual Reasoning

Leveraging Large Language Models and Topic Modeling for Toxicity Classification

2024-11-26 · Haniyeh Ehsani Oskouie, Christina Chance, Claire Huang, Margaret Capetz 외

Content moderation and toxicity classification represent critical tasks with significant social implications. However, studies have shown that major classification models exhibit tendencies to magnify or reduce biases an…

Classification