Cover Image

Interaction Context Often Increases Sycophancy in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jain, Shomik, Park, Charlotte, Viana, Matt, Wilson, Ashia, Calacci, Dana
Format:	Preprint
Published:	2025
Subjects:	Human-Computer Interaction
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

As an AI Language Model, "Yes I Would Recommend Calling the Police": Norm Inconsistency in LLM Decision-Making
by: Jain, Shomik, et al.
Published: (2024)

Surveillance, Spacing, Screaming and Scabbing: How Digital Technology Facilitates Union Busting
by: Reiber, Frederick, et al.
Published: (2026)

Insights from an experiment crowdsourcing data from thousands of US Amazon users: The importance of transparency, money, and data use
by: Berke, Alex, et al.
Published: (2024)

Rideshare Transparency: Translating Gig Worker Insights on AI Platform Design to Policy
by: Rao, Varun Nagaraj, et al.
Published: (2024)

The Illusion of Agreement with ChatGPT: Sycophancy and Beyond
by: Noshin, Kazi, et al.
Published: (2026)

Sycophancy is an Educational Safety Risk: Why LLM Tutors Need Sycophancy Benchmarks
by: Kasneci, Enkelejda, et al.
Published: (2026)

Alignment has a Fantasia Problem
by: Jo, Nathanael, et al.
Published: (2026)

Be Friendly, Not Friends: How LLM Sycophancy Shapes User Trust
by: Sun, Yuan, et al.
Published: (2025)

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

Alignment Without Understanding: A Message- and Conversation-Centered Approach to Understanding AI Sycophancy
by: Du, Lihua, et al.
Published: (2025)

GPTFootprint: Increasing Consumer Awareness of the Environmental Impacts of LLMs
by: Graves, Nora, et al.
Published: (2025)

QuaLLM: An LLM-based Framework to Extract Quantitative Insights from Online Forums
by: Rao, Varun Nagaraj, et al.
Published: (2024)

cVIL: Class-Centric Visual Interactive Labeling
by: Matt, Matthias, et al.
Published: (2024)

Accounting for Sycophancy in Language Model Uncertainty Estimation
by: Sicilia, Anthony, et al.
Published: (2024)

Beyond the Single Turn: Reframing Refusals as Dynamic Experiences Embedded in the Context of Mental Health Support Interactions with LLMs
by: Tang, Ningjing, et al.
Published: (2026)

FareShare: A Tool for Labor Organizers to Estimate Lost Wages and Contest Arbitrary AI and Algorithmic Deactivations
by: Rao, Varun Nagaraj, et al.
Published: (2025)

Challenging Disability and Interaction Norms in XR: Cooling Down the Empathy Machine in Waiting for Hands
by: Duarte, Yesica, et al.
Published: (2025)

FairFare: A Tool for Crowdsourcing Rideshare Data to Empower Labor Organizers
by: Calacci, Dana, et al.
Published: (2025)

Scalable Class-Centric Visual Interactive Labeling
by: Matt, Matthias, et al.
Published: (2025)

Designing Culturally Aligned AI Systems For Social Good in Non-Western Contexts
by: Dennison, Deepak Varuvel, et al.
Published: (2025)

Intelligent Interaction Strategies for Context-Aware Cognitive Augmentation
by: Xiangrong, et al.
Published: (2025)

ContextVis: Envision Contextual Learning and Interaction with Generative Models
by: Shui, Bo, et al.
Published: (2024)

Creo: From One-Shot Image Generation to Progressive, Co-Creative Ideation
by: De Simone, Zoe, et al.
Published: (2026)

An HCI-Centric Survey and Taxonomy of Human-Generative-AI Interactions
by: Shi, Jingyu, et al.
Published: (2023)

Intersectional Sycophancy: How Perceived User Demographics Shape False Validation in Large Language Models
by: Maltbie, Benjamin, et al.
Published: (2026)

ContextQ: Generated Questions to Support Meaningful Parent-Child Dialogue While Co-Reading
by: Smith, Griffin Dietz, et al.
Published: (2024)

Toward Multimodal Privacy in XR: Design and Evaluation of Composite Privatization Methods for Gaze and Body Tracking Data
by: Ibragimov, Azim, et al.
Published: (2025)

GUIDAETA -- A Versatile Interactions Dataset with extensive Context Information and Metadata
by: Lengauer, Stefan, et al.
Published: (2025)

From Fixed to Flexible: Shaping AI Personality in Context-Sensitive Interaction
by: Jayasiriwardene, Shakyani, et al.
Published: (2026)

SycoEval-EM: Sycophancy Evaluation of Large Language Models in Simulated Clinical Encounters for Emergency Care
by: Peng, Dongshen, et al.
Published: (2026)

LLMartini: Seamless and Interactive Leveraging of Multiple LLMs through Comparison and Composition
by: Shi, Yingtian, et al.
Published: (2025)

When Benchmarks Talk: Re-Evaluating Code LLMs with Interactive Feedback
by: Pan, Jane, et al.
Published: (2025)

The Human Visual System Can Inspire New Interaction Paradigms for LLMs
by: Robinson, Diana, et al.
Published: (2025)

Policy Prototyping for LLMs: Pluralistic Alignment via Interactive and Collaborative Policymaking
by: Feng, K. J. Kevin, et al.
Published: (2024)

An Interactive Tool for Simulating Mid-Air Ultrasound Tactons on the Skin
by: Lim, Chungman, et al.
Published: (2024)

Proactive AI Adoption can be Threatening: When Help Backfires
by: Harari, Dana, et al.
Published: (2025)

HeartbeatCam: Self-Triggered Photo Elicitation of Stress Events Using Wearable Sensing
by: Zhou, Boyang, et al.
Published: (2026)

M-CALLM: Multi-level Context Aware LLM Framework for Group Interaction Prediction
by: Romero, Diana, et al.
Published: (2025)

Generative Lecture: Making Lecture Videos Interactive with LLMs and AI Clone Instructors
by: Jo, Hye-Young, et al.
Published: (2025)

Examining the Effects of Immersive and Non-Immersive Presenter Modalities on Engagement and Social Interaction in Co-located Augmented Presentations
by: Gottsacker, Matt, et al.
Published: (2025)