paper-with-me

홈 › Papers

Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity

2022-09-24 · Gabriel Simmons

Large Language Models (LLMs) have demonstrated impressive capabilities in generating fluent text, as well as tendencies to reproduce undesirable social biases. This study investigates whether LLMs reproduce the moral biases associated with political groups in the United States, an instance of a broader capability herein termed moral mimicry. This hypothesis is explored in the GPT-3/3.5 and OPT families of Transformer-based LLMs. Using tools from Moral Foundations Theory, it is shown that these LLMs are indeed moral mimics. When prompted with a liberal or conservative political identity, the models generate text reflecting corresponding moral biases. This study also explores the relationship between moral mimicry and model size, and similarity between human and LLM moral word use.

📄 PDF Abstract BibTeX arXiv:2209.12106

Code (0)

등록된 구현이 없습니다.

Tasks

Language Modelling

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Attention 설명 없음
OPT OPT is a suite of decoder-only pre-trained transformers ranging from 125M to 175B parameters. The model uses an AdamW optimizer and weight decay of 0.1. It follows a linear…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Tracing Moral Foundations in Large Language Models

2026-01-09 · Chenxiao Yu, Bowen Yi, Farzan Karimi-Malekabadi, Suhaib Abdurahman 외 arxiv

Large language models often produce human-like moral judgments, but it is unclear whether this reflects an internal conceptual structure or superficial ``moral mimicry.'' Using Moral Foundations Theory (MFT) as an analyt…

The Pluralistic Moral Gap: Understanding Judgment and Value Differences between Humans and Large Language Models

2025-07-23 · Giuseppe Russo, Debora Nozza, Paul Röttger, Dirk Hovy arxiv

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 introduc…

MOKA: Moral Knowledge Augmentation for Moral Event Extraction

2023-11-16 · Xinliang Frederick Zhang, Winston Wu, Nick Beauchamp, Lu Wang

News media often strive to minimize explicit moral language in news articles, yet most articles are dense with moral values as expressed through the reported events themselves. However, values that are reflected in the i…

ArticlesEvent ExtractionMoral Scenarios

Jailbreaking Large Language Models with Morality Attacks

2026-04-18 · Ying Su, Mingen Zheng, Weili Diao, Haoran Li arxiv

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 le…

Large Language Models are as persuasive as humans, but how? About the cognitive effort and moral-emotional language of LLM arguments

2024-04-14 · Carlos Carrasco-Farre

Large Language Models (LLMs) are already as persuasive as humans. However, we know very little about how they do it. This paper investigates the persuasion strategies of LLMs, comparing them with human-generated argument…

Persuasion Strategies