Image de couverture de livre

Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Reese, May Lynn, Zeneli, Markela, Ng, Mindy, Haimes, Jacob, Damien, Andreea, Stade, Elizabeth
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants
par: Sturgeon, Benjamin, et autres
Publié: (2025)

Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics
par: Timm, Jasper, et autres
Publié: (2025)

Who Judges the Judge? LLM Jury-on-Demand: Building Trustworthy LLM Evaluation Systems
par: Li, Xiaochuan, et autres
Publié: (2025)

Measuring Mental Health Variables in Computational Research: Toward Validated, Dimensional, and Transdiagnostic Approaches
par: Shani, Chen, et autres
Publié: (2025)

Chord Colourizer: A Near Real-Time System for Visualizing Musical Key
par: Haimes, Paul
Publié: (2025)

Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models
par: Verga, Pat, et autres
Publié: (2024)

Building Sustainable Urban Futures: The Crucial Role of Urban Food Policy
par: Alessandro Banterle, et autres
Publié: (2025)

Demonstrative Evidence and the Use of Algorithms in Jury Trials
par: Rogers, Rachel, et autres
Publié: (2023)

View From Above: A Framework for Evaluating Distribution Shifts in Model Behavior
par: Chopra, Tanush, et autres
Publié: (2024)

MEQA: A Meta-Evaluation Framework for Question & Answer LLM Benchmarks
par: Veuthey, Jaime Raldua, et autres
Publié: (2025)

Rethinking CyberSecEval: An LLM-Aided Approach to Evaluation Critique
par: Hariharan, Suhas, et autres
Publié: (2024)

Video - Cultivating Psychological Safety during Disaster Response: Enhancing Resilience and Psychological Recovery
par: Andreea Blezneag
Publié: (2025)

Approximating Human Preferences Using a Multi-Judge Learned System
par: Sprejer, Eitán, et autres
Publié: (2025)

Search Smarter, Not Harder: A Scalable, High-Quality Zoned Neutral Atom Compiler
par: Stade, Yannick, et autres
Publié: (2025)

YouTube vs. GEMA
par: Stade, Philip
Publié: (2022)

The Point-Boundary Art Gallery Problem is $\exists\mathbb{R}$-hard
par: Stade, Jack
Publié: (2022)

Two Tiling is Undecidable
par: Stade, Jack
Publié: (2025)

NP-membership for the boundary-boundary art-gallery problem
par: Stade, Jack
Publié: (2025)

Masked IRL: LLM-Guided Reward Disambiguation from Demonstrations and Language
par: Hwang, Minyoung, et autres
Publié: (2025)

Evaluating Metrics for Safety with LLM-as-Judges
par: Clegg, Kester, et autres
Publié: (2025)

CD-ROM End-User Instruction: Issues and Challenges.
par: Reese, Jean
Publié: (1993)

Benchmark Inflation: Revealing LLM Performance Gaps Using Retro-Holdouts
par: Haimes, Jacob, et autres
Publié: (2024)

Juris
Publié: (2017)

User Perceptions vs. Proxy LLM Judges: Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios
par: Wu, Xiaoyuan, et autres
Publié: (2025)

Know Thy Judge: On the Robustness Meta-Evaluation of LLM Safety Judges
par: Eiras, Francisco, et autres
Publié: (2025)

Evaluating Precise Geolocation Inference Capabilities of Vision Language Models
par: Jay, Neel, et autres
Publié: (2025)

Vox Juris
Publié: (2018)

Ratio Juris
Publié: (2018)

Jury Trial
par: Igor Yurievich NIKODIMOV
Publié: (2020)

Psychosis and Near Psychosis
par: Marcus, Eric
Publié: (2025)

"AI Psychosis" in Context: How Conversation History Shapes LLM Responses to Delusional Beliefs
par: Nicholls, Luke, et autres
Publié: (2026)

Self‐Reported Cognitive Bias in Psychosis: Further Validation of the Cognitive Biases Questionnaire for Psychosis (CBQ‐P) and the Davos Assessment of Cognitive Biases (DACOBS) in a Large Iranian Clinical and Non‐Clinical Sample
par: Mohammad Aminaee, et autres
Publié: (2025)

Vibe Coding on Trial: Operating Characteristics of Unanimous LLM Juries
par: Ullah, Muhammad Aziz, et autres
Publié: (2026)

Comparing Human and LLM Generated Code: The Jury is Still Out!
par: Licorish, Sherlock A., et autres
Publié: (2025)

Hardness of Packing, Covering and Partitioning Simple Polygons with Unit Squares
par: Abrahamsen, Mikkel, et autres
Publié: (2024)

A Pilot Study of the Peer Supported Family Intervention, Psychosis Recovery by Enabling Adult Carers at Home (Psychosis‐REACH) in an Early Psychosis Clinic
par: Melanie Lean, et autres
Publié: (2026)

Finger Acrometastasis as the Initial Presentation of Advanced Lung Adenocarcinoma
par: May Lynn Chan, et autres
Publié: (2026)

Criterion Validity of LLM-as-Judge for Business Outcomes in Conversational Commerce
par: Chen, Liang, et autres
Publié: (2026)

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

LLM4VV: Exploring LLM-as-a-Judge for Validation and Verification Testsuites
par: Sollenberger, Zachariah, et autres
Publié: (2024)