:: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Authors:	Ye, Meryl, Ibrahim, Lujain, Bo, Jessica Y., Cheng, Myra, Mattsson, Ida, Vennemeyer, Daniel, Kraut, Robert, Rathje, Steve
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	https://arxiv.org/abs/2605.21778
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Thinking beyond the anthropomorphic paradigm benefits LLM research
by: Ibrahim, Lujain, et al.
Published: (2025)

Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs
by: Vennemeyer, Daniel, et al.
Published: (2025)

Characterizing and modeling harms from interactions with design patterns in AI interfaces
by: Ibrahim, Lujain, et al.
Published: (2024)

Extinction Risks from AI: Invisible to Science?
by: Kovarik, Vojtech, et al.
Published: (2024)

ELEPHANT: Measuring and understanding social sycophancy in LLMs
by: Cheng, Myra, et al.
Published: (2025)

What's in a Niche? Migration Patterns in Online Communities
by: Van Koevering, Katherine, et al.
Published: (2024)

Sycophantic AI makes human interaction feel more effortful and less satisfying over time
by: Ibrahim, Lujain, et al.
Published: (2026)

Explainable AI models for predicting liquefaction-induced lateral spreading
by: Hsiao, Cheng-Hsi, et al.
Published: (2024)

Investigating the effect of CPT in lateral spreading prediction using Explainable AI
by: Hsiao, Cheng-Hsi, et al.
Published: (2025)

Epistemic Fragility in Large Language Models: Prompt Framing Systematically Modulates Misinformation Correction
by: Krastev, Sekoul, et al.
Published: (2025)

The Rise of AI Companions: Interaction with AI Companions and Psychological Well-being
by: Zhang, Yutong, et al.
Published: (2025)

Towards interactive evaluations for interaction harms in human-AI systems
by: Ibrahim, Lujain, et al.
Published: (2024)

Training language models to be warm and empathetic makes them less reliable and more sycophantic
by: Ibrahim, Lujain, et al.
Published: (2025)

Barriers and Facilitators to Pharmacist‐Led Deprescribing of Antihypertensives in Long‐Term Care: A Survey‐Based Study
by: Ana Vucenovic, et al.
Published: (2025)

Digital Youth with Disabilities
by: Alper, Meryl
Published: (2019)

Alliance du Pacifique: enjeu de l’esthétique de la résolution des différends
by: Méryl Thiel
Published: (2017)

False memories
by: Xavier, Meryl
Published: (2025)

Beauvoir in Time
by: Altman, Meryl
Published: (2021)

Beauvoir in Time (Volume 348)
by: Altman, Meryl
Published: (2021)

Women in today’s fisheries economy
by: Williams, Meryl
Published: (2015)

A general multi-scale description of metastable adaptive motion across fitness valleys
by: Esser, Manuel, et al.
Published: (2021)

Effective growth rates in a periodically changing environment: From mutation to invasion
by: Esser, Manuel, et al.
Published: (2023)

Crossing a fitness valley in a changing environment: With and without pit stop
by: Esser, Manuel, et al.
Published: (2025)

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

Precise Ranging: Modeling Bias and Variance of Double-Sided Two-Way Ranging with TDoA Extraction under Multipath and NLOS Effects
by: Rathje, Patrick, et al.
Published: (2024)

Time Difference of Arrival Extraction from Two-Way Ranging
by: Rathje, Patrick, et al.
Published: (2022)

Diagnosing and Mitigating Sycophancy and Skepticism in LLM Causal Judgment
by: Chang, Edward Y.
Published: (2026)

The association between quality of habitual diet and mental health status among Iraqi women attending primary health care centers
by: Lujain Anwar Alkhazrajy
Published: (2020)

De la estrella amarilla a la estrella roja: el antisemitismo, el anticomunismo y los judíos de Hungría
by: Donna Meryl Goldsteín
Published: (1995)

Review: A brave start
by: Williams, Meryl J.
Published: (2019)

Analysis 1: SDG5, gender equal fisheries
by: Williams, Meryl J.
Published: (2017)

Offloading Score: Measuring AI Reliance Through Counterfactual Workflows
by: Padmakumar, Vishakh, et al.
Published: (2026)

CountPath: Automating Fragment Counting in Digital Pathology
by: Vieira, Ana Beatriz, et al.
Published: (2025)

GuessingGame: Measuring the Informativeness of Open-Ended Questions in Large Language Models
by: Hutson, Dylan, et al.
Published: (2025)

Verbalizing LLMs' assumptions to explain and control sycophancy
by: Cheng, Myra, et al.
Published: (2026)

Not Your Typical Sycophant: The Elusive Nature of Sycophancy in Large Language Models
by: Natan, Shahar Ben, et al.
Published: (2026)

Domain-informed explainable boosting machines for trustworthy lateral spread predictions
by: Hsiao, Cheng-Hsi, et al.
Published: (2026)

Seismic capacity models for earth dams and their use in developing fragility curves
by: Jingwen He, et al.
Published: (2024)

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition
by: Mohsin, Muhammad Ahmed, et al.
Published: (2026)

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