English
Related papers

Related papers: Tracing Moral Foundations in Large Language Models

200 papers

Alignment safety research assumes that ethical instructions improve model behavior, but how language models internally process such instructions remains unknown. We conducted over 600 multi-agent simulations across four models (Llama 3.3…

Computation and Language · Computer Science 2026-04-02 Hiroki Fukui

People acquire concepts through rich physical and social experiences and use them to understand and navigate the world. In contrast, large language models (LLMs), trained solely through next-token prediction on text, exhibit strikingly…

Computation and Language · Computer Science 2025-11-11 Ningyu Xu , Qi Zhang , Chao Du , Qiang Luo , Xipeng Qiu , Xuanjing Huang , Menghan Zhang

Supervised fine-tuning (SFT) is a critical step in aligning large language models (LLMs) with human instructions and values, yet many aspects of SFT remain poorly understood. We trained a wide range of base models on a variety of datasets…

Computation and Language · Computer Science 2025-10-31 Yuto Harada , Yusuke Yamauchi , Yusuke Oda , Yohei Oseki , Yusuke Miyao , Yu Takagi

Large language models (LLMs) increasingly exhibit behaviors suggesting awareness of their evaluation context, often adapting their reasoning strategies in benchmark settings. Prior work has shown that such evaluation awareness can distort…

Computation and Language · Computer Science 2026-05-12 Yanshi Li , Xueru Bai , Shuman Liu , Haibo Zhang , Anxiang Zeng

Large Language Models significantly influence social interactions, decision-making, and information dissemination, underscoring the need to understand the implicit socio-cognitive attitudes, referred to as "worldviews", encoded within these…

Computation and Language · Computer Science 2025-12-30 Jiatao Li , Yanheng Li , Xiaojun Wan

Large language models (LLMs) are trained on vast amounts of data to generate natural language, enabling them to perform tasks like text summarization and question answering. These models have become popular in artificial intelligence (AI)…

As LLMs excel on standard reading comprehension benchmarks, attention is shifting toward evaluating their capacity for complex abstract reasoning and inference. Literature-based benchmarks, with their rich narrative and moral depth, provide…

Computation and Language · Computer Science 2025-09-17 Matteo Marcuzzo , Alessandro Zangari , Andrea Albarelli , Jose Camacho-Collados , Mohammad Taher Pilehvar

Large language models (LLMs) are increasingly used as substitutes for human subjects in behavioral simulations, including synthetic social network generation. Yet it remains unclear how their relational outputs depend on prompt design,…

Social and Information Networks · Computer Science 2026-05-14 Sai Hemanth Kilaru , Sriram Theerdh Manikyala , Raghav Upadhyay , Sri Sai Kumar Ramavath , Srivika Nunavathu , Dalal Alharthi

Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply "biased" or "unbiased." This binary framing misses the gradual,…

Machine Learning · Computer Science 2026-05-06 Yash Aggarwal , Atmika Gorti , Vinija Jain , Aman Chadha , Krishnaprasad Thirunarayan , Manas Gaur

Large language models (LLMs) excel at handling human queries, but they can occasionally generate flawed or unexpected responses. Understanding their internal states is crucial for understanding their successes, diagnosing their failures,…

Computation and Language · Computer Science 2025-02-24 Xuansheng Wu , Jiayi Yuan , Wenlin Yao , Xiaoming Zhai , Ninghao Liu

This study enhances stance detection on social media by incorporating deeper psychological attributes, specifically individuals' moral foundations. These theoretically-derived dimensions aim to provide a comprehensive profile of an…

Computation and Language · Computer Science 2024-10-01 Hong Zhang , Quoc-Nam Nguyen , Prasanta Bhattacharya , Wei Gao , Liang Ze Wong , Brandon Siyuan Loh , Joseph J. P. Simons , Jisun An

Multimodal Large Language Models (MLLMs) are increasingly deployed in human-facing roles where personality perception is critical, yet existing benchmarks evaluate this capability solely on numerical Big Five score prediction, leaving open…

Artificial Intelligence · Computer Science 2026-05-22 Caixin Kang , Tianyu Yan , Sitong Gong , Mingfang Zhang , Liangyang Ouyang , Ruicong Liu , Bo Zheng , Huchuan Lu , Kaipeng Zhang , Yoichi Sato , Yifei Huang

Large Language Models (LLMs) display strikingly different generalization behaviors: supervised fine-tuning (SFT) often narrows capability, whereas reinforcement-learning (RL) tuning tends to preserve it. The reasons behind this divergence…

Machine Learning · Computer Science 2026-01-01 Haoyue Bai , Yiyou Sun , Wenjie Hu , Shi Qiu , Maggie Ziyu Huan , Peiyang Song , Robert Nowak , Dawn Song

Altruism is fundamental to human societies, fostering cooperation and social cohesion. Recent studies suggest that large language models (LLMs) can display human-like prosocial behavior, but the internal computations that produce such…

General Economics · Economics 2026-04-22 Shuhuai Zhang , Shu Wang , Zijun Yao , Chuanhao Li , Xiaozhi Wang , Songfa Zhong , Tracy Xiao Liu

Extracting moral sentiment from text is a vital component in understanding public opinion, social movements, and policy decisions. The Moral Foundation Theory identifies five moral foundations, each associated with a positive and negative…

Computation and Language · Computer Science 2021-09-13 Shamik Roy , Maria Leonor Pacheco , Dan Goldwasser

Self-correction is one of the most amazing emerging capabilities of Large Language Models (LLMs), enabling LLMs to self-modify an inappropriate output given a natural language feedback which describes the problems of that output. Moral…

Computation and Language · Computer Science 2025-03-04 Guangliang Liu , Zhiyu Xue , Xitong Zhang , Rongrong Wang , Kristen Marie Johnson

Ensuring the moral reasoning capabilities of Large Language Models (LLMs) is a growing concern as these systems are used in socially sensitive tasks. Nevertheless, current evaluation benchmarks present two major shortcomings: a lack of…

Uncovering latent values and opinions embedded in large language models (LLMs) can help identify biases and mitigate potential harm. Recently, this has been approached by prompting LLMs with survey questions and quantifying the stances in…

Computation and Language · Computer Science 2025-09-01 Dustin Wright , Arnav Arora , Nadav Borenstein , Srishti Yadav , Serge Belongie , Isabelle Augenstein

As large language models (LLMs) become more deeply integrated into various sectors, understanding how they make moral judgments has become crucial, particularly in the realm of autonomous driving. This study utilized the Moral Machine…

Computation and Language · Computer Science 2024-02-08 Kazuhiro Takemoto

Large language models are increasingly used as computational tools for modeling human-like behavior. We introduce a behavioral induction framework that modifies model policies through fine-tuning on structured decision-making tasks: using…

Computation and Language · Computer Science 2026-05-22 Nicola Milano , Davide Marocco