# Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs

arXiv: https://arxiv.org/abs/2410.11302 · HTML: https://mlsanity.com/paper/2410.11302/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 34 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration](https://mlsanity.com/paper/2311.04257/) (2023)
- [InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model](https://mlsanity.com/paper/2401.16420/) (2024)
- [InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition](https://mlsanity.com/paper/2309.15112/) (2023)
- [Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization](https://mlsanity.com/paper/2311.16839/) (2023)
- [Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs](https://mlsanity.com/paper/2407.21771/) (2024)
- [Question Decomposition Improves the Faithfulness of Model-Generated Reasoning](https://mlsanity.com/paper/2307.11768/) (2023)
- [SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model](https://mlsanity.com/paper/2406.12030/) (2024)
- [From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning](https://mlsanity.com/paper/2409.01658/) (2024)
- [Prompt Leakage effect and defense strategies for multi-turn LLM interactions](https://mlsanity.com/paper/2404.16251/) (2024)
- [Probing Multimodal Large Language Models for Global and Local Semantic Representations](https://mlsanity.com/paper/2402.17304/) (2024)

## Built on by (most cited first, 15 of 15)

- [How RLHF Amplifies Sycophancy](https://mlsanity.com/paper/2602.01002/) (2026)
- [Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs](https://mlsanity.com/paper/2506.07180/) (2025)
- [Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories](https://mlsanity.com/paper/2509.16742/) (2025)
- [EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models](https://mlsanity.com/paper/2509.20146/) (2025)
- [Benchmarking and Mitigating Sycophancy in Medical Vision Language Models](https://mlsanity.com/paper/2509.21979/) (2025)
- [PENDULUM: A Benchmark for Assessing Sycophancy in Multimodal Large Language Models](https://mlsanity.com/paper/2512.19350/) (2025)
- [Moral Sycophancy in Vision Language Models](https://mlsanity.com/paper/2602.08311/) (2026)
- [To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs](https://mlsanity.com/paper/2603.18373/) (2026)
- [Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs](https://mlsanity.com/paper/2605.13737/) (2026)
- [Exploring and Mitigating Fawning Hallucinations in Large Language Models](https://mlsanity.com/paper/2509.00869/) (2025)
- [Stress Tests REVEAL Fragile Temporal and Visual Grounding in Video-Language Models](https://mlsanity.com/paper/2602.11244/) (2026)
- [Caved or Convinced: Temporal Sampling Gates Claim Deference in Video Large Language Models](https://mlsanity.com/paper/2608.03160/) (2026)
- [Looking Again: Measuring Sycophancy in the Reasoning Chains of Multimodal Models Under Pressure](https://mlsanity.com/paper/2608.28623/) (2026)
- [ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment in Vision-Language Models](https://mlsanity.com/paper/2607.20092/) (2026)
- [PRISM-VLM: A Multi-Axis Discriminative Benchmark for Compact Vision-Language Models](https://mlsanity.com/paper/2609.27395/) (2026)

## Abstract (arXiv)

In the study of LLMs, sycophancy represents a prevalent hallucination that poses significant challenges to these models. Specifically, LLMs often fail to adhere to original correct responses, instead blindly agreeing with users' opinions, even when those opinions are incorrect or malicious. However, research on sycophancy in visual language models (VLMs) has been scarce. In this work, we extend the exploration of sycophancy from LLMs to VLMs, introducing the MM-SY benchmark to evaluate this phenomenon. We present evaluation results from multiple representative models, addressing the gap in sycophancy research for VLMs. To mitigate sycophancy, we propose a synthetic dataset for training and employ methods based on prompts, supervised fine-tuning, and DPO. Our experiments demonstrate that these methods effectively alleviate sycophancy in VLMs. Additionally, we probe VLMs to assess the semantic impact of sycophancy and analyze the attention distribution of visual tokens. Our findings indicate that the ability to prevent sycophancy is predominantly observed in higher layers of the model. The lack of attention to image knowledge in these higher layers may contribute to sycophancy, and enhancing image attention at high layers proves beneficial in mitigating this issue.