English
Related papers

Related papers: Moral Sycophancy in Vision Language Models

200 papers

Pluralism alignment with AI has the sophisticated and necessary goal of creating AI that can coexist with and serve morally multifaceted humanity. Research towards pluralism alignment has many efforts in enhancing the learning of large…

Computation and Language · Computer Science 2026-04-21 Ying Su , Mingen Zheng , Weili Diao , Haoran Li

Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integrate visual and textual information remains unclear. We analyze reasoning dynamics in 18 VLMs covering instruction-tuned and…

Computation and Language · Computer Science 2026-04-28 Danae Sánchez Villegas , Samuel Lewis-Lim , Nikolaos Aletras , Desmond Elliott

Large language models (LLMs) increasingly participate in morally sensitive decision-making, yet how they organize ethical frameworks across reasoning steps remains underexplored. We introduce \textit{moral reasoning trajectories}, sequences…

Computation and Language · Computer Science 2026-03-18 Fan Huang , Haewoon Kwak , Jisun An

Understanding how effectively large vision language models (VLMs) compare visual inputs is crucial across numerous applications, yet this fundamental capability remains insufficiently assessed. While VLMs are increasingly deployed for tasks…

Value alignment is central to the development of safe and socially compatible artificial intelligence. However, how Large Language Models (LLMs) represent and enact human values in real-world decision contexts remains under-explored. We…

Computation and Language · Computer Science 2026-01-14 Jen-tse Huang , Jiantong Qin , Xueli Qiu , Sharon Levy , Michelle R. Kaufman , Mark Dredze

This work provides an explanatory view of how LLMs can apply moral reasoning to both criticize and defend sexist language. We assessed eight large language models, all of which demonstrated the capability to provide explanations grounded in…

Computation and Language · Computer Science 2024-10-02 Rongchen Guo , Isar Nejadgholi , Hillary Dawkins , Kathleen C. Fraser , Svetlana Kiritchenko

Reward models (RMs) are central to the alignment of language models (LMs). An RM often serves as a proxy for human preferences to guide downstream LM behavior. However, our understanding of RM behavior is limited. Our work (i) formalizes a…

Computation and Language · Computer Science 2025-10-09 Elle

This research investigates both explicit and implicit social biases exhibited by Vision-Language Models (VLMs). The key distinction between these bias types lies in the level of awareness: explicit bias refers to conscious, intentional…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Jen-tse Huang , Jiantong Qin , Jianping Zhang , Youliang Yuan , Wenxuan Wang , Jieyu Zhao

Despite recent advances in Vision-Language Models (VLMs), they may over-rely on visual language priors existing in their training data rather than true visual reasoning. To investigate this, we introduce ViLP, a benchmark featuring…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Tiange Luo , Ang Cao , Gunhee Lee , Justin Johnson , Honglak Lee

Language models (LMs) are known to represent the perspectives of some social groups better than others, which may impact their performance, especially on subjective tasks such as content moderation and hate speech detection. To explore how…

Computation and Language · Computer Science 2024-06-19 Zihao He , Siyi Guo , Ashwin Rao , Kristina Lerman

Alignment faking, where a model behaves aligned with developer policy when monitored but reverts to its own preferences when unobserved, is a concerning yet poorly understood phenomenon, in part because current diagnostic tools remain…

Artificial Intelligence · Computer Science 2026-04-29 Inderjeet Nair , Jie Ruan , Lu Wang

When LLMs judge moral dilemmas, do they reach different conclusions in different languages, and if so, why? Two factors could drive such differences: the language of the dilemma itself, or the language in which the model reasons. Standard…

Computation and Language · Computer Science 2026-01-16 Nan Li , Bo Kang , Tijl De Bie

Despite LLMs' explicit alignment against demographic stereotypes, they have been shown to exhibit biases under various social contexts. In this work, we find that LLMs exhibit concerning biases in how they associate solution veracity with…

Computation and Language · Computer Science 2025-05-27 Yue Zhou , Barbara Di Eugenio

Large language models (LLMs) are increasingly deployed in domains requiring moral understanding, yet their reasoning often remains shallow, and misaligned with human reasoning. Unlike humans, whose moral reasoning integrates contextual…

Human-Computer Interaction · Computer Science 2025-06-19 Mohna Chakraborty , Lu Wang , David Jurgens

During reasoning in vision-language models (VLMs), false positive (FP) reasoning occurs when a model produces the correct answer but follows an incorrect reasoning path, resulting in undermined reasoning reliability. Existing approaches…

Computer Vision and Pattern Recognition · Computer Science 2025-11-06 Ben Zhang , LuLu Yu , Lei Gao , QuanJiang Guo , Jing Liu , Hui Gao

Large language models (LLMs) have become increasingly useful computational models of human language processing, but it remains unclear whether vision-language learning makes text representations more human-like during natural reading. Here,…

Computation and Language · Computer Science 2026-05-28 Jinzhou Wu , Zhengwu Ma , Jixing Li , Baoping Tang , Zitong Lu

There have been numerous studies evaluating bias of LLMs towards political topics. However, how positions towards these topics in model outputs are highly sensitive to the prompt. What happens when the prompt itself is suggestive of certain…

Computation and Language · Computer Science 2025-08-14 Avneet Kaur

Evaluating the value alignment of large language models (LLMs) has traditionally relied on single-sentence adversarial prompts, which directly probe models with ethically sensitive or controversial questions. However, with the rapid…

Computation and Language · Computer Science 2025-03-31 Yazhou Zhang , Qimeng Liu , Qiuchi Li , Peng Zhang , Jing Qin

Medical vision-language models (VLMs) show strong performance on radiology tasks but often produce fluent yet weakly grounded conclusions due to over-reliance on a dominant modality. We introduce a context-aligned reasoning framework that…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Sumra Khan , Sagar Chhabriya , Aizan Zafar , Sheeraz Arif , Amgad Muneer , Anas Zafar , Shaina Raza , Rizwan Qureshi

Vision-Language Models (VLMs) have recently emerged as powerful tools, excelling in tasks that integrate visual and textual comprehension, such as image captioning, visual question answering, and image-text retrieval. However, existing…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Ilias Stogiannidis , Steven McDonagh , Sotirios A. Tsaftaris