paper-with-me

Papers

Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Models

2021-04-18 · NAACL (GeBNLP) 2022 7 · Tejas Srinivasan, Yonatan Bisk

Numerous works have analyzed biases in vision and pre-trained language models individually - however, less attention has been paid to how these biases interact in multimodal settings. This work extends text-based bias analysis methods to investigate multimodal language models, and analyzes intra- and inter-modality associations and biases learned by these models. Specifically, we demonstrate that VL-BERT (Su et al., 2020) exhibits gender biases, often preferring to reinforce a stereotype over faithfully describing the visual scene. We demonstrate these findings on a controlled case-study and extend them for a larger set of stereotypically gendered entities.

📄 PDF Abstract BibTeX arXiv:2104.08666

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

VL-BERT VL-BERT is pre-trained on a large-scale image-captions dataset together with text-only corpus. The input to the model are either words from the input sentences or…

Similar Papers 제목 키워드 기반

Better Best of Both Worlds Bounds for Bandits with Switching Costs

2022-06-07 · Idan Amir, Guy Azov, Tomer Koren, Roi Livni

We study best-of-both-worlds algorithms for bandits with switching cost, recently addressed by Rouyer, Seldin and Cesa-Bianchi, 2021. We introduce a surprisingly simple and effective algorithm that simultaneously achieve…

The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning

2022-03-12 · Jessica Hullman, Sayash Kapoor, Priyanka Nanayakkara, Andrew Gelman 외

Recent arguments that machine learning (ML) is facing a reproducibility and replication crisis suggest that some published claims in ML research cannot be taken at face value. These concerns inspire analogies to the repl…

Causal InferenceInductive Learning

A Blackbox Approach to Best of Both Worlds in Bandits and Beyond

2023-02-20 · Christoph Dann, Chen-Yu Wei, Julian Zimmert

Best-of-both-worlds algorithms for online learning which achieve near-optimal regret in both the adversarial and the stochastic regimes have received growing attention recently. Existing techniques often require careful …

Multi-Armed Bandits

Towards Understanding Gender-Seniority Compound Bias in Natural Language Generation

2022-05-19 · LREC 2022 6 · Samhita Honnavalli, Aesha Parekh, Lily Ou, Sophie Groenwold 외

Women are often perceived as junior to their male counterparts, even within the same job titles. While there has been significant progress in the evaluation of gender bias in natural language processing (NLP), existing s…

Text Generation

Best of Both Distortion Worlds

2023-05-30 · Vasilis Gkatzelis, Mohamad Latifian, Nisarg Shah

We study the problem of designing voting rules that take as input the ordinal preferences of $n$ agents over a set of $m$ alternatives and output a single alternative, aiming to optimize the overall happiness of the agen…