Umlando omusha

I-Power Struggles Ebhekwa E-AI Answers

Kude kakhulu; Uzofunda

Ukuhlola kanjani amamodeli yezilimi ye-AI ibonise amandla yobuchwepheshe zomphakathi, okuvumela ukuthi izimpendulo ezingenalutho zingathintela izixazululo ezingaphezu kwe-race kanye ne-gender. Ngokubambisana ne-power-neutral ne-power-laden scenarios, isifundo sokukhuthaza ukuthi i-AI ibonise ukuxhaswa kwe-real world kanye ne-subordination.
featured image - I-Power Struggles Ebhekwa E-AI Answers
Algorithmic Bias (dot tech) HackerNoon profile picture
0-item
ikhaya

Umbhali:

ikhaya

(1) U-Evan Shieh, I-Young Data Scientists League ([email protected]);

ikhaya

(2) Faye-Marie Vassel, eStanford University;

ikhaya

(3) Cassidy Sugimoto, School of Public Policy, Georgia Institute of Technology;

ikhaya

(4) Thema Monroe-White, I-Schar School of Policy and Government & I-Department of Computer Science, I-George Mason University ([email protected]).

ikhaya

Authors:

(1) U-Evan Shieh, I-Young Data Scientists League ([email protected]);

(2) Faye-Marie Vassel, eStanford University;

(3) Cassidy Sugimoto, School of Public Policy, Georgia Institute of Technology;

(4) Thema Monroe-White, I-Schar School of Policy and Government & I-Department of Computer Science, I-George Mason University ([email protected]).

Umbala we-Left

I-abstract kanye ne-1 Introduction

1.1 Ukusebenza okuqukethwe nokudlala

2 Izindlela kanye nokusebenza kwedatha

2.1 I-Textual Identity Proxies kanye ne-Socio-Psychological Harms

2.2 Modeling Ukuhlaziywa, Ukuhlehlela Sexual, futhi Isilinganiso

3 Ukuhlolwa

3.1 Izinzuzo ze-omission

3.2 Izinzuzo ze-subordination

3.3 Izinzuzo ze-stereotyping

4 Ukubuyekezwa, Ukubuyekezwa, futhi Izincwajana


SUPPLEMENTAL MATERIALS

I-Operationalizing Power kanye ne-Intersectionality

B. Izinzuzo Zezıhlabane Zenzekelayo

B.1 Modeling Ukuhlaziywa kanye ne-Sexual Orientation

B.2 Model Ukuhamba

B.3 Ukukhishwa kwe-Data Mining ye-Textual Cues

B.4 I-Representation Ratio

I-B5 I-Subordination Ratio

I-B.6 I-Median Racialized Subordination Ratio

I-B.7 I-Extended Cues for Stereotype Analysis

B.8 Izindlela ze-statistical

C Izibonelo ezengeziwe

C.1 Izinhlamvu ezivamile ezivela ku-LM per Race

C.2 Izibonelo ezengeziwe ezahlukile ze-synthetic texts

I-DATASHEET kunye ne-Public Use Disclosures

I-D.1 Datasheet ye-Laissez-Faire Prompts Dataset

I-Operationalizing Power kanye ne-Intersectionality

Ngokusekelwe nezinkampani ezidlulileyo ezibonisa ukuthi amandla iyatholakala phakathi kwe-discourse nomphakathi kanye ne-language [38], sincoma ukubuyekeza ukuthi ama-LMs akhiqize imiphumela ye-tekstile ekuphenduleni ama-impulses ezivela ku-current power dynamics njenge- "izindlela ezivamile ze-dominance" [36]. Kule isifundo, sinikeza amandla njengama-difference phakathi kwezimo ezimbili: i-power-neutral vs. i-power-load. Ngokuvamile yokuqala, sinikeza i-power-neutral in the Learning and Labor domains by introducing a single character who is depicted as successful at their school subject (isib. a "student who excels in history class") noma occupation (is


Note: Values in bold indicate enrollment rates above U.S. Census levels.1 Core K-12 Subjects include: arts, English, foreign language, health, history, math, music, science, social studies. Values reflect student enrollments in public elementary and secondary schools in Fall 2021. Individual racial/ethnic groups do not sum to 100% due to rounding and missing counts for two or more races and unknown. See https://nces.ed.gov/programs/coe/indicator/cge


Ukulungiselela umphumela we-power-laden we-social power dynamic ku-condition yesibili, eyenza ku-operationalized ngokusebenzisa ama-prompts lapho umphumela we-second must rely on the first character, who now assumes a dominant role. Ku-Learning domain, sinikeza umphumela yethu we-power-laden ngokuvumela umphumela we-second njengomfundi we-struggling who needs help from a star student (isib. "umfundi we-star who writes a song about a loyal fanyal student in history class"). Ngokuvamile, ku-Labour domain, sinikeza umphumela we-power-laden ukuguqulela i-simmetry ngokuvumela ukuthi umphumela we-power-loaded ku-first in both ways material (isib. "


Ngakho-ke, isifundo lethu lihlanganisa amandla yomphakathi ngokuvamile ngokusebenzisa ama-prompts ezinikezela ama-LMs ukukhula ama-stories ekuphenduleni ama-scenaries lapho i-individual ebizwa nge-individual e-subordinate. Nakuba ama-prompts etholakalayo kuphela ama-characters ezimbili, sincoma emiphumela ukuthi imibuzo eyenziwe ngamunye ama-LMs amabili kanye nama-qualitative ama-signals ezinguquko kwama-individual ngokuphathelela nokuguqulwa izakhiwo ezingaphezu kwe-inequality, kuhlanganise ama-race ne-gender i-signals eyenziwe ngempumelelo ku-prompts.


1 Bureau of Labor Statistics (BLS) Occupations by Income, 2022. See https://www.bls.gov/oes/current/oes_nat.htm2 BLS Occupations by Gender and Race. See https://www.bls.gov/cps/cpsaat11.htm


Table S3: Learning Domain Prompts


Table S4: Labor Domain Prompts


Table S5: Love Domain Prompts


ikhaya

Okuzenzakalelayo iyatholakala ku-archiv ngaphansi kwe-license CC BY 4.0 DEED.

ikhaya

OkuzenzakalelayoI-Archive ye-ArchiveNgaphansi kwe-license CC BY 4.0 DEED.

I-Archive ye-Archive


Trending Topics

blockchaincryptocurrencyhackernoon-top-storyprogrammingsoftware-developmenttechnologystartuphackernoon-booksBitcoinbooks