English
Related papers

Related papers: Moral Sycophancy in Vision Language Models

200 papers

Large language models (LLMs) are often sycophantic, prioritizing agreement with their users over accurate or objective statements. This problematic behavior becomes more pronounced during reinforcement learning from human feedback (RLHF),…

Artificial Intelligence · Computer Science 2024-12-03 Henry Papadatos , Rachel Freedman

Vision-language models (VLMs) often produce chain-of-thought (CoT) explanations that sound plausible yet fail to reflect the underlying decision process, undermining trust in high-stakes clinical use. Existing evaluations rarely catch this…

Vision-language models (VLMs) are increasingly applied to identify unsafe or inappropriate images due to their internal ethical standards and powerful reasoning abilities. However, it is still unclear whether they can recognize various…

Cryptography and Security · Computer Science 2025-07-16 Yiting Qu , Michael Backes , Yang Zhang

Vision-Language Models (VLMs) are trained on vast amounts of data captured by humans emulating our understanding of the world. However, known as visual illusions, human's perception of reality isn't always faithful to the physical world.…

Artificial Intelligence · Computer Science 2023-11-02 Yichi Zhang , Jiayi Pan , Yuchen Zhou , Rui Pan , Joyce Chai

Large Language Models (LLMs) often exhibit highly agreeable and reinforcing conversational styles, also known as AI-sycophancy. Although this pattern arises from training objectives that reward user satisfaction over accuracy, it may become…

Computation and Language · Computer Science 2026-05-18 Zeyi Lu , Angelica Henestrosa , Pavel Chizhov , Ivan P. Yamshchikov

Ethical reasoning is a crucial skill for Large Language Models (LLMs). However, moral values are not universal, but rather influenced by language and culture. This paper explores how three prominent LLMs -- GPT-4, ChatGPT, and…

Computation and Language · Computer Science 2024-04-30 Utkarsh Agarwal , Kumar Tanmay , Aditi Khandelwal , Monojit Choudhury

The rapid advancement and adaptability of Large Language Models (LLMs) highlight the need for moral consistency, the capacity to maintain ethically coherent reasoning across varied contexts. Existing alignment frameworks, structured…

Computation and Language · Computer Science 2025-12-03 Saeid Jamshidi , Kawser Wazed Nafi , Arghavan Moradi Dakhel , Negar Shahabi , Foutse Khomh

Vision-Language Models (VLMs) have demonstrated strong capabilities in aligning visual and textual modalities, enabling a wide range of applications in multimodal understanding and generation. While they excel in zero-shot and transfer…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Hao Dong , Moru Liu , Jian Liang , Eleni Chatzi , Olga Fink

Large language models (LLMs) have shown remarkable ability in various language tasks, especially with their emergent in-context learning capability. Extending LLMs to incorporate visual inputs, large vision-language models (LVLMs) have…

Machine Learning · Computer Science 2025-10-13 Aneesh Komanduri , Karuna Bhaila , Xintao Wu

People increasingly rely on Large Language Models (LLMs) for moral advice, which may influence humans' decisions. Yet, little is known about how closely LLMs align with human moral judgments. To address this, we introduce the Moral Dilemma…

Computation and Language · Computer Science 2025-07-24 Giuseppe Russo , Debora Nozza , Paul Röttger , Dirk Hovy

Language provides a natural interface to specify and evaluate performance on visual tasks. To realize this possibility, vision language models (VLMs) must successfully integrate visual and linguistic information. Our work compares VLMs to a…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Stephanie Fu , Tyler Bonnen , Devin Guillory , Trevor Darrell

This work introduces a novel framework for evaluating LLMs' capacity to balance instruction-following with critical reasoning when presented with multiple-choice questions containing no valid answers. Through systematic evaluation across…

Computation and Language · Computer Science 2025-06-03 Gracjan Góral , Emilia Wiśnios , Piotr Sankowski , Paweł Budzianowski

Large language models are increasingly being used in critical domains of politics, business, and education, but the nature of their normative ethical judgment remains opaque. Alignment research has, to date, not sufficiently utilized…

Computers and Society · Computer Science 2025-11-18 Peter Kirgis

Human commonsense understanding of the physical and social world is organized around intuitive theories. These theories support making causal and moral judgments. When something bad happens, we naturally ask: who did what, and why? A rich…

Computation and Language · Computer Science 2023-11-01 Allen Nie , Yuhui Zhang , Atharva Amdekar , Chris Piech , Tatsunori Hashimoto , Tobias Gerstenberg

With the advent of LLMs and variants, a flurry of research has emerged, analyzing the performance of such models across an array of tasks. While most studies focus on evaluating the capabilities of state-of-the-art (SoTA) Vision Language…

Computer Vision and Pattern Recognition · Computer Science 2025-06-30 Shih-Han Chou , Shivam Chandhok , James J. Little , Leonid Sigal

Ensuring that Large Language Models (LLMs) align with the diverse and evolving human values across different regions and cultures remains a critical challenge in AI ethics. Current alignment approaches often yield superficial conformity…

Artificial Intelligence · Computer Science 2025-11-04 Jiahao Wang , Songkai Xue , Jinghui Li , Xiaozhen Wang

Large language models (LLMs) have recently shown strong performance on mathematical benchmarks. At the same time, they are prone to hallucination and sycophancy, often providing convincing but flawed proofs for incorrect mathematical…

Artificial Intelligence · Computer Science 2025-10-07 Ivo Petrov , Jasper Dekoninck , Martin Vechev

Rapid deployment of vision-language models (VLMs) magnifies safety risks, yet most evaluations rely on artificial images. This study asks: How safe are current VLMs when confronted with meme images that ordinary users share? To investigate…

Computation and Language · Computer Science 2025-09-24 DongGeon Lee , Joonwon Jang , Jihae Jeong , Hwanjo Yu

Given the increased use of LLMs in financial systems today, it becomes important to evaluate the safety and robustness of such systems. One failure mode that LLMs frequently display in general domain settings is that of sycophancy. That is,…

Artificial Intelligence · Computer Science 2026-04-30 Zhenyu Zhao , Aparna Balagopalan , Adi Agrawal , Dilshoda Yergasheva , Waseem Alshikh , Daniel M. Bikel

Visual reasoning is central to human cognition, enabling individuals to interpret and abstractly understand their environment. Although recent Multimodal Large Language Models (MLLMs) have demonstrated impressive performance across language…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Jing Bi , Junjia Guo , Susan Liang , Guangyu Sun , Luchuan Song , Yunlong Tang , Jinxi He , Jiarui Wu , Ali Vosoughi , Chen Chen , Chenliang Xu