Copertina

Decoding Safety Feedback from Diverse Raters: A Data-driven Lens on Responsiveness to Severity

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Mishra, Pushkar, Rastogi, Charvi, Pfohl, Stephen R., Parrish, Alicia, Teh, Tian Huey, Patel, Roma, Diaz, Mark, Wang, Ding, Paganini, Michela, Prabhakaran, Vinodkumar, Aroyo, Lora, Rieser, Verena
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computers and Society Human-Computer Interaction
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

"Just a strange pic": Evaluating 'safety' in GenAI Image safety annotation tasks from diverse annotators' perspectives
di: Wang, Ding, et al.
Pubblicazione: (2025)

Insights on Disagreement Patterns in Multimodal Safety Perception across Diverse Rater Groups
di: Rastogi, Charvi, et al.
Pubblicazione: (2024)

Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models
di: Rastogi, Charvi, et al.
Pubblicazione: (2025)

GRASP: A Disagreement Analysis Framework to Assess Group Associations in Perspectives
di: Prabhakaran, Vinodkumar, et al.
Pubblicazione: (2023)

From Seed to Harvest: Augmenting Human Creativity with AI for Red-teaming Text-to-Image Models
di: Quaye, Jessica, et al.
Pubblicazione: (2025)

Value Profiles for Encoding Human Variation
di: Sorensen, Taylor, et al.
Pubblicazione: (2025)

Taxonomy of User Needs and Actions
di: Shelby, Renee, et al.
Pubblicazione: (2025)

Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South
di: Rastogi, Charvi, et al.
Pubblicazione: (2026)

Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation
di: Quaye, Jessica, et al.
Pubblicazione: (2024)

Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models
di: Ibrahim, Lujain, et al.
Pubblicazione: (2025)

A Comprehensive Framework to Operationalize Social Stereotypes for Responsible AI Evaluations
di: Davani, Aida, et al.
Pubblicazione: (2025)

D3CODE: Disentangling Disagreements in Data across Cultures on Offensiveness Detection and Evaluation
di: Davani, Aida Mostafazadeh, et al.
Pubblicazione: (2024)

SeeGULL Multilingual: a Dataset of Geo-Culturally Situated Stereotypes
di: Bhutani, Mukul, et al.
Pubblicazione: (2024)

Risks of Cultural Erasure in Large Language Models
di: Qadri, Rida, et al.
Pubblicazione: (2025)

GeniL: A Multilingual Dataset on Generalizing Language
di: Davani, Aida Mostafazadeh, et al.
Pubblicazione: (2024)

Towards Geo-Culturally Grounded LLM Generations
di: Lertvittayakumjorn, Piyawat, et al.
Pubblicazione: (2025)

Yesterday's News: Benchmarking Multi-Dimensional Out-of-Distribution Generalization of Misinformation Detection Models
di: Verhoeven, Ivo, et al.
Pubblicazione: (2024)

SAFARI: A Community-Engaged Approach and Dataset of Stereotype Resources in the Sub-Saharan African Context
di: Verma, Aishwarya, et al.
Pubblicazione: (2026)

ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation
di: Jha, Akshita, et al.
Pubblicazione: (2024)

Consistency is Key: Disentangling Label Variation in Natural Language Processing with Intra-Annotator Agreement
di: Abercrombie, Gavin, et al.
Pubblicazione: (2023)

DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers
di: Langedijk, Anna, et al.
Pubblicazione: (2023)

Understanding and evaluating computer vision models through the lens of counterfactuals
di: Shukla, Pushkar
Pubblicazione: (2025)

Principled Evaluation with Human Labels: One Rater at a Time and Rater Equivalence
di: Resnick, Paul, et al.
Pubblicazione: (2021)

A Randomized Controlled Trial on Anonymizing Reviewers to Each Other in Peer Review Discussions
di: Rastogi, Charvi, et al.
Pubblicazione: (2024)

Cultural Compass: A Framework for Organizing Societal Norms to Detect Violations in Human-AI Conversations
di: Cheng, Myra, et al.
Pubblicazione: (2026)

Multi-Rater Calibrated Segmentation Models
di: Riera-Marín, Meritxell, et al.
Pubblicazione: (2026)

Adaptive Data Collection for Latin-American Community-sourced Evaluation of Stereotypes (LACES)
di: Ivetta, Guido, et al.
Pubblicazione: (2025)

Rater Cohesion and Quality from a Vicarious Perspective
di: Pandita, Deepak, et al.
Pubblicazione: (2024)

Positive Alignment: Artificial Intelligence for Human Flourishing
di: Laukkonen, Ruben, et al.
Pubblicazione: (2026)

A Multivariate to Bivariate Reduction for Noncommutative Rank and Related Results
di: Arvind, Vikraman, et al.
Pubblicazione: (2024)

On Efficient Noncommutative Polynomial Factorization via Higman Linearization
di: Arvind, V., et al.
Pubblicazione: (2022)

Beyond Aesthetics: Cultural Competence in Text-to-Image Models
di: Kannen, Nithish, et al.
Pubblicazione: (2024)

JuICE: A Benchmark for Evaluating LLM-Judge in Identifying Cultural Errors
di: Jin, Jiho, et al.
Pubblicazione: (2026)

High-quality Data-to-Text Generation for Severely Under-Resourced Languages with Out-of-the-box Large Language Models
di: Lorandi, Michela, et al.
Pubblicazione: (2024)

Community Notes are Vulnerable to Rater Bias and Manipulation
di: Truong, Bao Tran, et al.
Pubblicazione: (2025)

LearnLens: LLM-Enabled Personalised, Curriculum-Grounded Feedback with Educators in the Loop
di: Zhao, Runcong, et al.
Pubblicazione: (2025)

Malaysian English News Decoded: A Linguistic Resource for Named Entity and Relation Extraction
di: Chanthran, Mohan Raj, et al.
Pubblicazione: (2024)

Scaling Cultural Resources for Improving Generative Models
di: Stepanyan, Hayk, et al.
Pubblicazione: (2025)

MetaScoreLens: Evaluating User Feedback Across Digital Entertainment Systems
di: Ellington, Christian, et al.
Pubblicazione: (2025)

Through the Judge's Eyes: Inferred Thinking Traces Improve Reliability of LLM Raters
di: Zhang, Xingjian, et al.
Pubblicazione: (2025)