Imagen de Portada

Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shah, Arya, Mishra, Deepali, Silpasuwanchai, Chaklam
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SycoPhantasy: Quantifying Sycophancy and Hallucination in Small Open Weight VLMs for Vision-Language Scoring of Fantasy Characters
por: Shah, Arya, et al.
Publicado: (2026)

Gaslight, Gatekeep, V1-V3: Early Visual Cortex Alignment Shields Vision-Language Models from Sycophantic Manipulation
por: Shah, Arya, et al.
Publicado: (2026)

From Overload to Convergence: Supporting Multi-Issue Human-AI Negotiation with Bayesian Visualization
por: Parmar, Mehul, et al.
Publicado: (2026)

Barriers in Integrating Medical Visual Question Answering into Radiology Workflows: A Scoping Review and Clinicians' Insights
por: Mishra, Deepali, et al.
Publicado: (2025)

To Tell The Truth: Language of Deception and Language Models
por: Hazra, Sanchaita, et al.
Publicado: (2023)

Reasoning Isn't Enough: Examining Truth-Bias and Sycophancy in LLMs
por: Barkett, Emilio, et al.
Publicado: (2025)

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains
por: Yi, Zihao, et al.
Publicado: (2025)

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

Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems
por: Kasprova, Vira, et al.
Publicado: (2026)

Sycophancy in Large Language Models: Causes and Mitigations
por: Malmqvist, Lars
Publicado: (2024)

Measuring Agreeableness Bias in Multimodal Models
por: Lim, Jaehyuk, et al.
Publicado: (2024)

Show, Don't Tell: Evaluating Large Language Models Beyond Textual Understanding with ChildPlay
por: de Carvalho, Gonçalo Hora, et al.
Publicado: (2024)

Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
por: Denison, Carson, et al.
Publicado: (2024)

Quantifying Risk Propensities of Large Language Models: Ethical Focus and Bias Detection through Role-Play
por: Zeng, Yifan, et al.
Publicado: (2024)

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

Role-Playing Evaluation for Large Language Models
por: Boudouri, Yassine El, et al.
Publicado: (2025)

Beacon: Single-Turn Diagnosis and Mitigation of Latent Sycophancy in Large Language Models
por: Pandey, Sanskar, et al.
Publicado: (2025)

Sycophancy in Vision-Language Models: A Systematic Analysis and an Inference-Time Mitigation Framework
por: Zhao, Yunpu, et al.
Publicado: (2024)

One Instruction Does Not Fit All: How Well Do Embeddings Align Personas and Instructions in Low-Resource Indian Languages?
por: Shah, Arya, et al.
Publicado: (2026)

Towards Understanding Sycophancy in Language Models
por: Sharma, Mrinank, et al.
Publicado: (2023)

RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
por: Wang, Zekun Moore, et al.
Publicado: (2023)

Sycophancy Hides Linearly in the Attention Heads
por: Genadi, Rifo, et al.
Publicado: (2026)

BASIL: Bayesian Assessment of Sycophancy in LLMs
por: Atwell, Katherine, et al.
Publicado: (2025)

Role-Playing Agents Driven by Large Language Models: Current Status, Challenges, and Future Trends
por: Wang, Ye, et al.
Publicado: (2026)

The Oscars of AI Theater: A Survey on Role-Playing with Language Models
por: Chen, Nuo, et al.
Publicado: (2024)

RPGBENCH: Evaluating Large Language Models as Role-Playing Game Engines
por: Yu, Pengfei, et al.
Publicado: (2025)

On the Decision-Making Abilities in Role-Playing using Large Language Models
por: Shen, Chenglei, et al.
Publicado: (2024)

Self-Blinding and Counterfactual Self-Simulation Mitigate Biases and Sycophancy in Large Language Models
por: Christian, Brian, et al.
Publicado: (2026)

VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing
por: Xu, Jiacheng, et al.
Publicado: (2026)

PARROT: Persuasion and Agreement Robustness Rating of Output Truth -- A Sycophancy Robustness Benchmark for LLMs
por: Çelebi, Yusuf, et al.
Publicado: (2025)

Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs
por: Wang, Kai, et al.
Publicado: (2026)

Orca: Enhancing Role-Playing Abilities of Large Language Models by Integrating Personality Traits
por: Huang, Yuxuan
Publicado: (2024)

Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning
por: Chen, Zhongzhi, et al.
Publicado: (2023)

On the Relationship between Truth and Political Bias in Language Models
por: Fulay, Suyash, et al.
Publicado: (2024)

RoleCraft-GLM: Advancing Personalized Role-Playing in Large Language Models
por: Tao, Meiling, et al.
Publicado: (2023)

Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models
por: Costa, Davi Bastos, et al.
Publicado: (2025)

Truth Knows No Language: Evaluating Truthfulness Beyond English
por: Figueras, Blanca Calvo, et al.
Publicado: (2025)

Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents
por: Qian, Cheng, et al.
Publicado: (2024)

Rehearse With User: Personalized Opinion Summarization via Role-Playing based on Large Language Models
por: Zhang, Yanyue, et al.
Publicado: (2025)

LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play
por: Lu, Li-Chun, et al.
Publicado: (2024)