Cover Image

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mohsin, Muhammad Ahmed, Bilal, Ahsan, Umer, Muhammad, Fox, Emily
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

$S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models
by: Bilal, Ahsan, et al.
Published: (2026)

Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Survey
by: Bilal, Ahsan, et al.
Published: (2025)

Continuous-Utility Direct Preference Optimization
by: Mohsin, Muhammad Ahmed, et al.
Published: (2026)

Epistemic Uncertainty for Test-Time Discovery
by: Riaz, Kainat, et al.
Published: (2026)

Meta-Reinforcement Learning for Fast and Data-Efficient Spectrum Allocation in Dynamic Wireless Networks
by: Giwa, Oluwaseyi, et al.
Published: (2025)

Resource Allocation for RIS-Assisted CoMP-NOMA Networks using Reinforcement Learning
by: Umer, Muhammad, et al.
Published: (2025)

Task and Perception-aware Distributed Source Coding for Correlated Speech under Bandwidth-constrained Channels
by: Bhattacharya, Sagnik, et al.
Published: (2025)

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

Canonical Optimization for MIMO MAC Design
by: Umer, Muhammad, et al.
Published: (2026)

Neural Gaussian Radio Fields for Channel Estimation
by: Umer, Muhammad, et al.
Published: (2025)

PENDULUM: A Benchmark for Assessing Sycophancy in Multimodal Large Language Models
by: Rahman, A. B. M. Ashikur, et al.
Published: (2025)

Moral Sycophancy in Vision Language Models
by: Rabby, Shadman, et al.
Published: (2026)

What If We Allocate Test-Time Compute Adaptively?
by: Bilal, Ahsan, et al.
Published: (2026)

Under Pressure: Emotional Framing Induces Measurable Behavioral Shifts and Structured Internal Geometry in Small Language Models
by: Usman, Rana Muhammad
Published: (2026)

Continual Learning for Wireless Channel Prediction
by: Mohsin, Muhammad Ahmed, et al.
Published: (2025)

General Preference Reinforcement Learning
by: Umer, Muhammad, 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)

Utilizing AI and Machine Learning for Predictive Analysis of Post-Treatment Cancer Recurrence
by: Qayyum, Muhammad Umer, et al.
Published: (2025)

Sycophancy in Large Language Models: Causes and Mitigations
by: Malmqvist, Lars
Published: (2024)

When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models
by: Li, Jiechen, et al.
Published: (2026)

An Overlooked Role of Context-Sensitive Dendrites
by: Raza, Mohsin, et al.
Published: (2024)

Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure
by: Lamparth, Max, et al.
Published: (2026)

Sacred or Secular? Religious Bias in AI-Generated Financial Advice
by: Khan, Muhammad Salar, et al.
Published: (2025)

Hierarchical Deep Reinforcement Learning for Adaptive Resource Management in Integrated Terrestrial and Non-Terrestrial Networks
by: Mohsin, Muhammad Ahmed, et al.
Published: (2025)

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

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

Context-sensitive neocortical neurons transform the effectiveness and efficiency of neural information processing
by: Ahmed, Khubaib, et al.
Published: (2022)

Scalable Machines with Intrinsic Higher Mental-State Dynamics
by: Adeel, Ahsan, et al.
Published: (2026)

OnRL-RAG: Real-Time Personalized Mental Health Dialogue System
by: Bilal, Ahsan, et al.
Published: (2025)

On the Fundamental Limits of LLMs at Scale
by: Mohsin, Muhammad Ahmed, et al.
Published: (2025)

Benchmarking and Mitigating Sycophancy in Medical Vision Language Models
by: Xu, Juangui, et al.
Published: (2025)

Natural Language Processing for Analyzing Electronic Health Records and Clinical Notes in Cancer Research: A Review
by: Bilal, Muhammad, et al.
Published: (2024)

What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Construct
by: Ye, Meryl, et al.
Published: (2026)

How RLHF Amplifies Sycophancy
by: Shapira, Itai, et al.
Published: (2026)

6G Twin: Hybrid Gaussian Radio Fields for Channel Estimation and Non-Linear Precoder Design for Radio Access Networks
by: Mohsin, Muhammad Ahmed, et al.
Published: (2025)

An Ensemble Learning Approach towards Waste Segmentation in Cluttered Environment
by: Jafar, Maimoona, et al.
Published: (2026)

Mitigating Hallucinations Using Ensemble of Knowledge Graph and Vector Store in Large Language Models to Enhance Mental Health Support
by: Muqtadir, Abdul, et al.
Published: (2024)

Conditional Prior-based Non-stationary Channel Estimation Using Accelerated Diffusion Models
by: Mohsin, Muhammad Ahmed, et al.
Published: (2025)

Qalb: Largest State-of-the-Art Urdu Large Language Model for 230M Speakers with Systematic Continued Pre-training
by: Hassan, Muhammad Taimoor, et al.
Published: (2026)

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