awesomelist.dev

Discover All lists Trending MCP server

Categories

AI & ML12 APIs & Data4 Databases3 Design5 DevOps & Cloud3 Game Dev5 Languages21 Learn & Career10 Meta & General11 Mobile4 Security & Ops10 Web15

103 lists indexed

GitHub snapshot · refreshed today

awesomelist.dev

REPOSITORY

Home › AI & ML › Awesome NLP › StereoSet

S

StereoSet

github.com ↗

measuring stereotypical bias in pretrained LMs.

Visit repository ↗← Back to Awesome NLP

READMEView on GitHub ↗

Bias, Fairness, Safety in NLP

Category

AI & ML

More from Bias, Fairness, Safety in NLP

AAlignment Faking in Large Language Models(Anthropic, 2024) - models strategically complying during training.

CCrowS-Pairssocial bias measurement in masked LMs.

EEmergent Misalignment(2025) - finetuning on a narrow task (insecure code) unexpectedly produces broad alignment failures across unrelated domains.

HHolisticBiasbias measurement across many demographic axes.

IIndicSafe(2026) - multilingual safety benchmark across 12 Indic languages; reveals 12.8% cross-language agreement, with over-refusal in low-resource scripts.

RRealToxicityPromptstoxicity in LM generation.

SSafeDialBench(2025) - multilingual (Chinese/English) safety benchmark of 4000+ multi-turn dialogues across 22 scenarios and 7 jailbreak strategies.

SSycophancy in Language Modelsmodels tailoring answers to user beliefs.

All lists Trending MCP server Sitemap

103 lists · 61.4k projects · refreshed today

esc

↵ to searchesc to close

awesomelist.dev

Discover All lists Trending MCP server