Buchumschlag

Ask don't tell: Reducing sycophancy in large language models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Dubois, Magda, Ududec, Cozmin, Summerfield, Christopher, Luettgau, Lennart
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Human-Computer Interaction Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

HiBayES: A Hierarchical Bayesian Modeling Framework for AI Evaluation Statistics
von: Luettgau, Lennart, et al.
Veröffentlicht: (2025)

One-shot emergency psychiatric triage across 15 frontier AI chatbots
von: Weilnhammer, Veith, et al.
Veröffentlicht: (2026)

Technological folie à deux: Feedback Loops Between AI Chatbots and Mental Illness
von: Dohnány, Sebastian, et al.
Veröffentlicht: (2025)

People readily follow personal advice from AI but it does not improve their well-being
von: Luettgau, Lennart, et al.
Veröffentlicht: (2025)

From keywords to semantics: Perceptions of large language models in data discovery
von: Halstead, Maura E, et al.
Veröffentlicht: (2025)

Medical large language models are easily distracted
von: Vishwanath, Krithik, et al.
Veröffentlicht: (2025)

Agentic publications: redesigning scientific publishing in the age of thinking large language models
von: Pugliese, Roberto, et al.
Veröffentlicht: (2025)

Neural steering vectors reveal dose and exposure-dependent impacts of human-AI relationships
von: Kirk, Hannah Rose, et al.
Veröffentlicht: (2025)

Beyond touch-based human-machine interface: Control your machines in natural language by utilizing large language models and OPC UA
von: Hofmann, Bernd, et al.
Veröffentlicht: (2025)

Vulnerability-Amplifying Interaction Loops: a systematic failure mode in AI chatbot mental-health interactions
von: Weilnhammer, Veith, et al.
Veröffentlicht: (2026)

Medication counseling with large language models: balancing flexibility and rigidity
von: Sabel, Joar, et al.
Veröffentlicht: (2025)

Creativity Benchmark: A benchmark for marketing creativity for large language models
von: Bhat, Ninad, et al.
Veröffentlicht: (2025)

Artificial intelligence can persuade people to take political actions
von: Hackenburg, Kobi, et al.
Veröffentlicht: (2026)

Conversational AI increases political knowledge as effectively as self-directed internet search
von: Luettgau, Lennart, et al.
Veröffentlicht: (2025)

Generics in science communication: Misaligned interpretations across laypeople, scientists, and large language models
von: Peters, Uwe, et al.
Veröffentlicht: (2026)

Fact-checking information from large language models can decrease headline discernment
von: DeVerna, Matthew R., et al.
Veröffentlicht: (2023)

The role of large language models in UI/UX design: A systematic literature review
von: Ahmed, Ammar, et al.
Veröffentlicht: (2025)

Ask, Clarify, Optimize: Human-LLM Agent Collaboration for Smarter Inventory Control
von: Duan, Yaqi, et al.
Veröffentlicht: (2025)

Why human-AI relationships need socioaffective alignment
von: Kirk, Hannah Rose, et al.
Veröffentlicht: (2025)

"Better Ask for Forgiveness than Permission": Practices and Policies of AI Disclosure in Freelance Work
von: Hwang, Angel Hsing-Chi, et al.
Veröffentlicht: (2026)

A large-scale evaluation of commonsense knowledge in humans and large language models
von: Nguyen, Tuan Dung, et al.
Veröffentlicht: (2025)

Automated stereotactic radiosurgery planning using a human-in-the-loop reasoning large language model agent
von: Nusrat, Humza, et al.
Veröffentlicht: (2025)

May I Ask a Follow-up Question? Understanding the Benefits of Conversations in Neural Network Explainability
von: Zhang, Tong, et al.
Veröffentlicht: (2023)

Malinowski in the Age of AI: Can large language models create a text game based on an anthropological classic?
von: Hoffmann, Michael Peter, et al.
Veröffentlicht: (2024)

Assessing the nature of large language models: A caution against anthropocentrism
von: Speed, Ann
Veröffentlicht: (2023)

Humans overrely on overconfident language models, across languages
von: Rathi, Neil, et al.
Veröffentlicht: (2025)

Enhancing behavioral nudges with large language model-based iterative personalization: A field experiment on electricity and hot-water conservation
von: Li, Zonghan, et al.
Veröffentlicht: (2026)

Can AI grade your essays? A comparative analysis of large language models and teacher ratings in multidimensional essay scoring
von: Seßler, Kathrin, et al.
Veröffentlicht: (2024)

A validity-guided workflow for robust large language model research in psychology
von: Lin, Zhicheng
Veröffentlicht: (2025)

Evidence of a log scaling law for political persuasion with large language models
von: Hackenburg, Kobi, et al.
Veröffentlicht: (2024)

Lessons from a Chimp: AI "Scheming" and the Quest for Ape Language
von: Summerfield, Christopher, et al.
Veröffentlicht: (2025)

What Students Ask, How a Generative AI Assistant Responds: Exploring Higher Education Students' Dialogues on Learning Analytics Feedback
von: Uzun, Yildiz, et al.
Veröffentlicht: (2026)

Evaluating the Impact of a Specialized LLM on Physician Experience in Clinical Decision Support: A Comparison of Ask Avo and ChatGPT-4
von: Jung, Daniel, et al.
Veröffentlicht: (2024)

Mind What You Ask For: Emotional and Rational Faces of Persuasion by Large Language Models
von: Mieleszczenko-Kowszewicz, Wiktoria, et al.
Veröffentlicht: (2025)

Performance of leading large language models in May 2025 in Membership of the Royal College of General Practitioners-style examination questions: a cross-sectional analysis
von: Armitage, Richard
Veröffentlicht: (2025)

The Social Sycophancy Scale: A psychometrically validated measure of sycophancy
von: Rehani, Jean, et al.
Veröffentlicht: (2026)

The opportunities and risks of large language models in mental health
von: Lawrence, Hannah R., et al.
Veröffentlicht: (2024)

The production of meaning in the processing of natural language
von: Agostino, Christopher J., et al.
Veröffentlicht: (2026)

"What if she doesn't feel the same?" What Happens When We Ask AI for Relationship Advice
von: Manchanda, Niva, et al.
Veröffentlicht: (2025)

''I don't want to break it'': An Exploration of Perceived Fragility in Shape-Changing Interfaces
von: Mackamul, Eva, et al.
Veröffentlicht: (2026)