Image de couverture de livre

Sycophancy in Vision-Language Models: A Systematic Analysis and an Inference-Time Mitigation Framework

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhao, Yunpu, Zhang, Rui, Xiao, Junbin, Ke, Changxin, Hou, Ruibo, Hao, Yifan, Li, Ling
Format:	Preprint
Publié:	2024
Sujets:	Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Object-Level Verbalized Confidence Calibration in Vision-Language Models via Semantic Perturbation
par: Zhao, Yunpu, et autres
Publié: (2025)

Sycophancy in Large Language Models: Causes and Mitigations
par: Malmqvist, Lars
Publié: (2024)

Beacon: Single-Turn Diagnosis and Mitigation of Latent Sycophancy in Large Language Models
par: Pandey, Sanskar, et autres
Publié: (2025)

Not Your Typical Sycophant: The Elusive Nature of Sycophancy in Large Language Models
par: Natan, Shahar Ben, et autres
Publié: (2026)

Assessing and Understanding Creativity in Large Language Models
par: Zhao, Yunpu, et autres
Publié: (2024)

Self-Blinding and Counterfactual Self-Simulation Mitigate Biases and Sycophancy in Large Language Models
par: Christian, Brian, et autres
Publié: (2026)

Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
par: Denison, Carson, et autres
Publié: (2024)

Benchmarking and Mitigating Sycophancy in Medical Vision Language Models
par: Xu, Juangui, et autres
Publié: (2025)

Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation
par: Zhang, Yichi, et autres
Publié: (2025)

Accounting for Sycophancy in Language Model Uncertainty Estimation
par: Sicilia, Anthony, et autres
Publié: (2024)

MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models
par: Hu, Jingyu, et autres
Publié: (2025)

Towards Understanding Sycophancy in Language Models
par: Sharma, Mrinank, et autres
Publié: (2023)

Moral Sycophancy in Vision Language Models
par: Rabby, Shadman, et autres
Publié: (2026)

Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models
par: Shah, Arya, et autres
Publié: (2026)

BASIL: Bayesian Assessment of Sycophancy in LLMs
par: Atwell, Katherine, et autres
Publié: (2025)

Sycophancy Hides Linearly in the Attention Heads
par: Genadi, Rifo, et autres
Publié: (2026)

Internal Reasoning vs. External Control: A Thermodynamic Analysis of Sycophancy in Large Language Models
par: Chang, Edward Y.
Publié: (2025)

Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy
par: Jiang, Eric Hanchen, et autres
Publié: (2025)

Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models
par: Liu, Qin, et autres
Publié: (2024)

Fake News Detection and Manipulation Reasoning via Large Vision-Language Models
par: Jin, Ruihan, et autres
Publié: (2024)

Improving LLM Reasoning through Interpretable Role-Playing Steering
par: Wang, Anyi, et autres
Publié: (2025)

Defining and Evaluating Decision and Composite Risk in Language Models Applied to Natural Language Inference
par: Shen, Ke, et autres
Publié: (2024)

A Systematic Analysis of Biases in Large Language Models
par: Zhang, Xulang, et autres
Publié: (2025)

TimeSense:Making Large Language Models Proficient in Time-Series Analysis
par: Zhang, Zhirui, et autres
Publié: (2025)

A Systematic Study of Compositional Syntactic Transformer Language Models
par: Zhao, Yida, et autres
Publié: (2025)

Augmented Vision-Language Models: A Systematic Review
par: Davis, Anthony C, et autres
Publié: (2025)

Unraveling and Mitigating Retriever Inconsistencies in Retrieval-Augmented Large Language Models
par: Li, Mingda, et autres
Publié: (2024)

Detecting and Mitigating Hateful Content in Multimodal Memes with Vision-Language Models
par: Van, Minh-Hao, et autres
Publié: (2025)

TDBench: A Benchmark for Top-Down Image Understanding with Reliability Analysis of Vision-Language Models
par: Hou, Kaiyuan, et autres
Publié: (2025)

Reasoning Isn't Enough: Examining Truth-Bias and Sycophancy in LLMs
par: Barkett, Emilio, et autres
Publié: (2025)

Can Vision-Language Models Solve Visual Math Equations?
par: Choudhury, Monjoy Narayan, et autres
Publié: (2025)

A Markov Categorical Framework for Language Modeling
par: Zhang, Yifan
Publié: (2025)

TrueBrief: Faithful Summarization through Small Language Models
par: Lakara, Kumud, et autres
Publié: (2025)

dInfer: An Efficient Inference Framework for Diffusion Language Models
par: Ma, Yuxin, et autres
Publié: (2025)

High-Quality Data Augmentation for Low-Resource NMT: Combining a Translation Memory, a GAN Generator, and Filtering
par: Liu, Hengjie, et autres
Publié: (2024)

CRANE: Causal Relevance Analysis of Language-Specific Neurons in Multilingual Large Language Models
par: Le, Yifan, et autres
Publié: (2026)

Unplug and Play Language Models: Decomposing Experts in Language Models at Inference Time
par: Yang, Nakyeong, et autres
Publié: (2024)

Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review
par: Abbasli, Toghrul, et autres
Publié: (2025)

From Sycophancy to Sensemaking: Premise Governance for Human-AI Decision Making
par: Jain, Raunak
Publié: (2026)

GenTKG: Generative Forecasting on Temporal Knowledge Graph with Large Language Models
par: Liao, Ruotong, et autres
Publié: (2023)