Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Gur-Arieh, Shira, Wang, Angelina, Fazelpour, Sina
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computers and Society Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina
di: Gao, Yuan, et al.
Pubblicazione: (2024)

Comparing Apples to Oranges: A Taxonomy for Navigating the Global Landscape of AI Regulation
di: Alanoca, Sacha, et al.
Pubblicazione: (2025)

Disciplining Deliberation: A Sociotechnical Perspective on Machine Learning Trade-offs
di: Fazelpour, Sina
Pubblicazione: (2024)

When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure
di: Xiao, Boyu, et al.
Pubblicazione: (2026)

Securing Educational LLMs: A Generalised Taxonomy of Attacks on LLMs and DREAD Risk Assessment
di: Zahid, Farzana, et al.
Pubblicazione: (2025)

The Value of Disagreement in AI Design, Evaluation, and Alignment
di: Fazelpour, Sina, et al.
Pubblicazione: (2025)

Aspirational Affordances of AI
di: Fazelpour, Sina, et al.
Pubblicazione: (2025)

Epistemic Diversity and Knowledge Collapse in Large Language Models
di: Wright, Dustin, et al.
Pubblicazione: (2025)

Mapping AI Risk Mitigations: Evidence Scan and Preliminary AI Risk Mitigation Taxonomy
di: Saeri, Alexander K., et al.
Pubblicazione: (2025)

Epistemic Deference to AI
di: Lange, Benjamin
Pubblicazione: (2025)

Should you use LLMs to simulate opinions? Quality checks for early-stage deliberation
di: Neumann, Terrence, et al.
Pubblicazione: (2025)

Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs
di: Cheng, Myra, et al.
Pubblicazione: (2026)

Uncovering Students' Inquiry Patterns in GenAI-Supported Clinical Practice: An Integration of Epistemic Network Analysis and Sequential Pattern Mining
di: Wei, Jiameng, et al.
Pubblicazione: (2025)

Aligning Trustworthy AI with Democracy: A Dual Taxonomy of Opportunities and Risks
di: Mentxaka, Oier, et al.
Pubblicazione: (2025)

When AI Fails, What Works? A Data-Driven Taxonomy of Real-World AI Risk Mitigation Strategies
di: Popchanovska, Evgenija, et al.
Pubblicazione: (2026)

Epistemic Control and the Normativity of Machine Learning-Based Science
di: Ratti, Emanuele
Pubblicazione: (2026)

Authenticity and exclusion: social media algorithms and the dynamics of belonging in epistemic communities
di: Akpinar, Nil-Jana, et al.
Pubblicazione: (2024)

Comparative analysis of privacy-preserving open-source LLMs regarding extraction of diagnostic information from clinical CMR imaging reports
di: Amirrajab, Sina, et al.
Pubblicazione: (2025)

LLM Agents in Law: Taxonomy, Applications, and Challenges
di: Liu, Shuang, et al.
Pubblicazione: (2026)

Epistemic Constitutionalism Or: how to avoid coherence bias
di: Loi, Michele
Pubblicazione: (2026)

The Polite Liar: Epistemic Pathology in Language Models
di: DeVilling, Bentley
Pubblicazione: (2025)

Coherent Without Grounding, Grounded Without Success: Observability and Epistemic Failure
di: Sartori, Camilo Chacón
Pubblicazione: (2026)

Academics and Generative AI: Empirical and Epistemic Indicators of Policy-Practice Voids
di: Ravenor, R. Yamamoto
Pubblicazione: (2025)

Pre-Deployment Information Sharing: A Zoning Taxonomy for Precursory Capabilities
di: Pistillo, Matteo, et al.
Pubblicazione: (2024)

Reconciling Different Theories of Learning with an Agent-based Model of Procedural Learning
di: Rismanchian, Sina, et al.
Pubblicazione: (2024)

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents
di: Li, Miles Q., et al.
Pubblicazione: (2026)

Red Teaming AI Policy: A Taxonomy of Avoision and the EU AI Act
di: Yew, Rui-Jie, et al.
Pubblicazione: (2025)

Measuring Machine Learning Harms from Stereotypes Requires Understanding Who Is Harmed by Which Errors in What Ways
di: Wang, Angelina, et al.
Pubblicazione: (2024)

Fairness Audits of Institutional Risk Models in Deployed ML Pipelines
di: McConvey, Kelly, et al.
Pubblicazione: (2026)

Responsible AI Adoption in the Public Sector: A Data-Centric Taxonomy of AI Adoption Challenges
di: Nikiforova, Anastasija, et al.
Pubblicazione: (2025)

Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings
di: Yang, Shujian, et al.
Pubblicazione: (2025)

Extending Interactive Science Exhibits into the Classroom using Anthropomorphized Chatbots and Bloom's Taxonomy
di: Golding, Yousuf
Pubblicazione: (2024)

Diverse, but Divisive: LLMs Can Exaggerate Gender Differences in Opinion Related to Harms of Misinformation
di: Neumann, Terrence, et al.
Pubblicazione: (2024)

Agentic AI in Healthcare & Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-based Agents
di: Vatsal, Shubham, et al.
Pubblicazione: (2026)

A Taxonomy and Review of Algorithms for Modeling and Predicting Human Driver Behavior
di: Bhattacharyya, Raunak P., et al.
Pubblicazione: (2020)

Tracing GenAI Literacy: Uncovering Student-AI Interaction Patterns in Academic Writing through Epistemic Network Analysis
di: Chen, Angxuan, et al.
Pubblicazione: (2026)

Risk-Adjusted Harm Scoring for Automated Red Teaming for LLMs in Financial Services
di: Dimino, Fabrizio, et al.
Pubblicazione: (2026)

The Manipulation Problem: Conversational AI as a Threat to Epistemic Agency
di: Rosenberg, Louis
Pubblicazione: (2023)

Classifying Epistemic Relationships in Human-AI Interaction: An Exploratory Approach
di: Yang, Shengnan, et al.
Pubblicazione: (2025)

Creative Loss: Ambiguity, Uncertainty and Indeterminacy
di: Holberton, Tom
Pubblicazione: (2024)