Unboxing Occupational Bias: Grounded Debiasing of LLMs with U.S. Labor Data

Man is to computer programmer as woman is to homemaker? debiasing word embeddings

Bolukbasi, T.; Chang, K.-W.; Zou, J. Y.; Saligrama, V.; and Kalai, A. T. 2016 · 2016

Earlier work this paper cites.

Semantics derived automatically from language corpora contain human-like biases

Caliskan, A.; Bryson, J. J.; and Narayanan, A. 2017 · 2017

Earlier work this paper cites.

The pile: An 800gb dataset of diverse text for language modeling

Original

Gao, L.; Biderman, S.; Black, S.; Golding, L.; Hoppe, T.; Foster, C.; Phang, J.; He, H.; Thite, A.; Nabeshima, N.; et al. 2020 · 2020

Earlier work this paper cites.

Stereotyping Norwegian salmon: An inventory of pitfalls in fairness benchmark datasets

Blodgett, S. L.; Lopez, G.; Olteanu, A.; Sim, R.; and Wallach, H. 2021 · 2021

Earlier work this paper cites.

Bias out-of-the-box: An empirical analysis of intersectional occupational biases in popular generative language models

Kirk, H. R.; Jun, Y.; Volpin, F.; Iqbal, H.; Benussi, E.; Dreyer, F.; Shtedritski, A.; and Asano, Y. 2021 · 2021

Earlier work this paper cites.

The Falcon Series of Open Language Models

Original

Almazrouei, E.; Alobeidli, H.; Alshamsi, A.; Cappelli, A.; Cojocaru, R.; Debbah, M.; Étienne Goffinet; Hesslow, D.; Launay, J.; Malartic, Q.; Mazzotta, D.; Noune, B.; Pannier, B.; and Penedo, G. 2023 · 2023

Earlier work this paper cites.

Distilling Large Language Models using Skill-Occupation Graph Context for HR-Related Tasks

Original

Pezeshkpour, P.; Iso, H.; Lake, T.; Bhutani, N.; and Hruschka, E. 2023 · 2023

Earlier work this paper cites.

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

Wang, B.; Chen, W.; Pei, H.; Xie, C.; Kang, M.; Zhang, C.; Xu, C.; Xiong, Z.; Dutta, R.; Schaeffer, R.; et al. 2023 · 2023

Cited alongside, same era.

Large language models are not robust multiple choice selectors

Zheng, C.; Zhou, H.; Meng, F.; Zhou, J.; and Huang, M. 2023 · 2023

Cited alongside, same era.

GPT-NeoX-20B: An Open-Source Autoregressive Language Model

Original

Black, S.; Gao, L.; Wang, P.; Leahy, C.; Biderman, S.; Golding, L.; Hallahan, E.; Anthony, Q.; Hilton, B.; Phang, P.; Frieder, S.; McDonell, K.; Mishkin, P.; Purohit, S.; Thite, A.; Reynolds, L.; and Carlini, N. 2022b · 2024

Cited alongside, same era.

Auditing the Use of Language Models to Guide Hiring Decisions

Original

Gaebler, J. D.; Goel, S.; Huq, A.; and Tambe, P. 2024 · 2024

Cited alongside, same era.

Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes

OffsetBias: Leveraging Debiased Data for Tuning Evaluators

Original

Park, J.; Jwa, S.; Ren, M.; Kim, D.; and Choi, S. 2024 · 2024

Closest in time.

Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence

The White House. 2023 · 2024

Closest in time.

Current Population Survey: Table 11. Employed persons by detailed occupation, sex, race, and Hispanic or Latino ethnicity

U.S. Bureau of Labor Statistics. 2024 · 2024

Closest in time.

Undesirable biases in NLP: Addressing challenges of measurement

Van der Wal, O.; Bachmann, D.; Leidinger, A.; van Maanen, L.; Zuidema, W.; and Schulz, K. 2024 · 2024

Closest in time.

White Men Lead, Black Women Help: Uncovering Gender, Racial, and Intersectional Bias in Language Agency

Original

Wan, Y.; and Chang, K.-W. 2024 · 2024

Closest in time.