Related papers: Moral Sycophancy in Vision Language Models

Moral reasoning is fundamental to safe Artificial Intelligence (AI), yet ensuring its consistency across modalities becomes critical as AI systems evolve from text-based assistants to embodied agents. Current safety techniques demonstrate…

LLMs can be socially sycophantic, affirming users when they ask questions like "am I in the wrong?" rather than providing genuine assessment. We hypothesize that this behavior arises from incorrect assumptions about the user, like…

Vision-language models (VLMs) are increasingly deployed as evaluators in tasks requiring nuanced image understanding, yet their reliability in scoring alignment between images and text descriptions remains underexplored. We investigate…

When VLMs answer correctly, do they genuinely rely on visual information? We introduce a Tri-Layer Diagnostic Framework with three per-sample metrics: Latent Anomaly Detection, Visual Necessity Score, and Competition Score, which…

Visual language models (VLMs) have the potential to transform medical workflows. However, the deployment is limited by sycophancy. Despite this serious threat to patient safety, a systematic benchmark remains lacking. This paper addresses…

LLM-powered conversational agents are increasingly influencing our decision-making, raising concerns about "sycophancy" - the tendency for LLMs to excessively agree with users even at the expense of truthfulness. While prior work has…

Sycophancy, an excessive tendency of AI models to agree with user input at the expense of factual accuracy or in contradiction of visual evidence, poses a critical and underexplored challenge for multimodal large language models (MLLMs).…

Human moral judgment is context-dependent and modulated by interpersonal relationships. As large language models (LLMs) increasingly function as decision-support systems, determining whether they encode these social nuances is critical. We…

This position paper argues that sycophancy in LLMs is a boundary failure between social alignment and epistemic integrity. Existing work often operationalizes sycophancy through external behavior such as agreement with incorrect user…

Large language models (LLMs) increasingly find their way into the most diverse areas of our everyday lives. They indirectly influence people's decisions or opinions through their daily use. Therefore, understanding how and which moral…

Humans display significant uncertainty when confronted with moral dilemmas, yet the extent of such uncertainty in machines and AI agents remains underexplored. Recent studies have confirmed the overly confident tendencies of…

Sycophancy, the tendency of LLM-based chatbots to express excessive agreement with their users, even when inappropriate, is emerging as a significant risk in human-AI interactions. However, the extent to which this affects human-LLM…

Recently Multimodal Large Language Models (MLLMs) have achieved considerable advancements in vision-language tasks, yet produce potentially harmful or untrustworthy content. Despite substantial work investigating the trustworthiness of…

Vision-Language Models (VLMs) continue to struggle to make morally salient judgments in multimodal and socially ambiguous contexts. Prior works typically rely on binary or pairwise supervision, which often fail to capture the continuous and…

Vision-Language Models (VLMs) excel in integrating visual and textual information for vision-centric tasks, but their handling of inconsistencies between modalities is underexplored. We investigate VLMs' modality preferences when faced with…

As large language models (LLMs) increasingly participate in tasks with ethical and societal stakes, a critical question arises: do they exhibit an emergent "moral mind" - a consistent structure of moral preferences guiding their decisions -…

LLMs are known to exhibit sycophancy: agreeing with and flattering users, even at the cost of correctness. Prior work measures sycophancy only as direct agreement with users' explicitly stated beliefs that can be compared to a ground truth.…

Existing behavioral alignment techniques for Large Language Models (LLMs) often neglect the discrepancy between surface compliance and internal unaligned representations, leaving LLMs vulnerable to long-tail risks. More crucially, we posit…

Vision Language Models (VLMs) are increasingly deployed across downstream tasks, yet their training data often encode social biases that surface in outputs. Unlike humans, who interpret images through contextual and social cues, VLMs…

Multimodal large language models (MLLMs) have demonstrated extraordinary capabilities in conducting conversations based on image inputs. However, we observe that MLLMs exhibit a pronounced form of visual sycophantic behavior. While similar…