Bias in Bios

Jennifer Chayes · Christian Borgs · Alexandra Chouldechova · Krishnaram Kenthapadi · Adam Tauman Kalai

337 citations0/0 files storedACM Conference on Fairness, Accountability, and Transparency (FAccT)

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Ethics and Social Impacts of AI Hate Speech and Cyberbullying Detection Names, Identity, and Discrimination Research

Abstract

We present a large-scale study of gender bias in occupation classification, a task where the use of machine learning may lead to negative outcomes on peoples' lives. We analyze the potential allocation harms that can result from semantic representation bias. To do so, we study the impact on occupation classification of including explicit gender indicators---such as first names and pronouns---in different semantic representations of online biographies. Additionally, we quantify the bias that remains when these indicators are "scrubbed," and describe proxy behavior that occurs in the absence of explicit gender indicators. As we demonstrate, differences in true positive rates between genders are correlated with existing gender imbalances in occupations, which may compound these imbalances.

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

No public copy is stored for this record, so only the metadata is cited.

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 337 citations exist upstream.

References

2012Fairness through awareness 2014Big Data's Disparate Impact 2018Word embeddings quantify 100 years of gender and ethnic stereotypes 2018Measuring and Mitigating Unintended Bias in Text Classification 2004Women in Economics: Moving Up or Falling Off the Academic Career Ladder?2017Measuring Fairness in Ranked Outputs 2018Equity of Attention

Cited by

2023Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale 2020Social Biases in NLP Models as Barriers for Persons with Disabilities 2021Problematic Machine Behavior 2021Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases 2021Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases 2024Towards trustworthy LLMs: a review on debiasing and dehallucinating in large language models 2023“Kelly is a Warm Person, Joseph is a Role Model”: Gender Biases in LLM-Generated Reference Letters

Explore the map →

Papers that cite the same references — the relational fallback while embeddings are still backfilling.

Imported from OpenAlex (CC0) — nothing here is generated.