Image de couverture de livre

Taxonomizing Representational Harms using Speech Act Theory

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Corvi, Emily, Washington, Hannah, Reed, Stefanie, Atalla, Chad, Chouldechova, Alexandra, Dow, P. Alex, Garcia-Gathright, Jean, Pangakis, Nicholas, Sheng, Emily, Vann, Dan, Vogel, Matthew, Wallach, Hanna
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Computers and Society
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Shared Standard for Valid Measurement of Generative AI Systems' Capabilities, Risks, and Impacts
par: Chouldechova, Alexandra, et autres
Publié: (2024)

AI-Assisted Systematization for Evaluating GenAI Systems
par: Agarwal, Dhruv, et autres
Publié: (2026)

Position: Evaluating Generative AI Systems Is a Social Science Measurement Challenge
par: Wallach, Hanna, et autres
Publié: (2025)

Evaluating Generative AI Systems is a Social Science Measurement Challenge
par: Wallach, Hanna, et autres
Publié: (2024)

Understanding and Meeting Practitioner Needs When Measuring Representational Harms Caused by LLM-Based Systems
par: Harvey, Emma, et autres
Publié: (2025)

Gaps Between Research and Practice When Measuring Representational Harms Caused by LLM-Based Systems
par: Harvey, Emma, et autres
Publié: (2024)

Dimensions of Generative AI Evaluation Design
par: Dow, P. Alex, et autres
Publié: (2024)

A Framework for Evaluating LLMs Under Task Indeterminacy
par: Guerdan, Luke, et autres
Publié: (2024)

Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teaming
par: Chouldechova, Alexandra, et autres
Publié: (2026)

Validating LLM-as-a-Judge Systems under Rating Indeterminacy
par: Guerdan, Luke, et autres
Publié: (2025)

Do Responsible AI Artifacts Advance Stakeholder Goals? Four Key Barriers Perceived by Legal and Civil Stakeholders
par: Kawakami, Anna, et autres
Publié: (2024)

Keeping Humans in the Loop: Human-Centered Automated Annotation with Generative AI
par: Pangakis, Nicholas, et autres
Publié: (2024)

Knowledge Distillation in Automated Annotation: Supervised Text Classification with LLM-Generated Training Labels
par: Pangakis, Nicholas, et autres
Publié: (2024)

"One-Size-Fits-All"? Examining Expectations around What Constitute "Fair" or "Good" NLG System Behaviors
par: Lucy, Li, et autres
Publié: (2023)

Effects of Generative AI Errors on User Reliance Across Task Difficulty
par: Anthis, Jacy Reese, et autres
Publié: (2026)

Remote Reference Consultations Are Here to Stay
par: Reed, Emily
Publié: (2021)

The Impact of Differential Feature Under-reporting on Algorithmic Fairness
par: Akpinar, Nil-Jana, et autres
Publié: (2024)

A structured regression approach for evaluating model performance across intersectional subgroups
par: Herlihy, Christine, et autres
Publié: (2024)

Alignment Drift in Multimodal LLMs: A Two-Phase, Longitudinal Evaluation of Harm Across Eight Model Releases
par: Ford, Casey, et autres
Publié: (2026)

Careless Whisper: Speech-to-Text Hallucination Harms
par: Koenecke, Allison, et autres
Publié: (2024)

Algorithm-Assisted Decision Making and Racial Disparities in Housing: A Study of the Allegheny Housing Assessment Tool
par: Cheng, Lingwei, et autres
Publié: (2024)

Leveraging Expert Consistency to Improve Algorithmic Decision Support
par: De-Arteaga, Maria, et autres
Publié: (2021)

Abstraction Induces the Brain Alignment of Language and Speech Models
par: Cheng, Emily, et autres
Publié: (2026)

Do Prevalent Bias Metrics Capture Allocational Harms from LLMs?
par: Cyberey, Hannah, et autres
Publié: (2024)

Harmful Speech Detection by Language Models Exhibits Gender-Queer Dialect Bias
par: Dorn, Rebecca, et autres
Publié: (2024)

Anecdoctoring: Automated Red-Teaming Across Language and Place
par: Cuevas, Alejandro, et autres
Publié: (2025)

Position: It's Time to Act on the Risk of Efficient Personalized Text Generation
par: Iofinova, Eugenia, et autres
Publié: (2025)

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
par: Andriushchenko, Maksym, et autres
Publié: (2024)

Not My Voice! A Taxonomy of Ethical and Safety Harms of Speech Generators
par: Hutiri, Wiebke, et autres
Publié: (2024)

SpeechAct: Towards Generating Whole-body Motion from Speech
par: Zhang, Jinsong, et autres
Publié: (2023)

A Perspective on Crowdsourcing and Human-in-the-Loop Workflows in Precision Health
par: Washington, Peter
Publié: (2023)

GRAID: Synthetic Data Generation with Geometric Constraints and Multi-Agentic Reflection for Harmful Content Detection
par: Rad, Melissa Kazemi, et autres
Publié: (2025)

Supervised Fine-Tuning LLMs to Behave as Pedagogical Agents in Programming Education
par: Ross, Emily, et autres
Publié: (2025)

Towards Generalizable Generic Harmful Speech Datasets for Implicit Hate Speech Detection
par: Almohaimeed, Saad, et autres
Publié: (2025)

Raising the Bar of AI-generated Image Detection with CLIP
par: Cozzolino, Davide, et autres
Publié: (2023)

Towards Pedagogical LLMs with Supervised Fine Tuning for Computing Education
par: Vassar, Alexandra, et autres
Publié: (2024)

MGen: Millions of Naturally Occurring Generics in Context
par: Cilleruelo, Gustavo, et autres
Publié: (2025)

Tracking the Temporal Dynamics of News Coverage of Catastrophic and Violent Events
par: Lugos, Emily, et autres
Publié: (2026)

Evaluating Retrieval Augmented Generative Models for Document Queries in Transportation Safety
par: Melton, Chad, et autres
Publié: (2025)

Musical Phrase Segmentation via Grammatical Induction
par: Perkins, Reed, et autres
Publié: (2024)