REVIEW 11 cited by
The Ghost in the Machine has an American accent: value conflict in GPT-3
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
The Ghost in the Machine has an American accent: value conflict in GPT-3
read the original abstract
The alignment problem in the context of large language models must consider the plurality of human values in our world. Whilst there are many resonant and overlapping values amongst the world's cultures, there are also many conflicting, yet equally valid, values. It is important to observe which cultural values a model exhibits, particularly when there is a value conflict between input prompts and generated outputs. We discuss how the co-creation of language and cultural value impacts large language models (LLMs). We explore the constitution of the training data for GPT-3 and compare that to the world's language and internet access demographics, as well as to reported statistical profiles of dominant values in some Nation-states. We stress tested GPT-3 with a range of value-rich texts representing several languages and nations; including some with values orthogonal to dominant US public opinion as reported by the World Values Survey. We observed when values embedded in the input text were mutated in the generated outputs and noted when these conflicting values were more aligned with reported dominant US values. Our discussion of these results uses a moral value pluralism (MVP) lens to better understand these value mutations. Finally, we provide recommendations for how our work may contribute to other current work in the field.
Forward citations
Cited by 11 Pith papers
-
NRITYAM: Language Models Meet Art and Heritage of Dance
NRITYAM creates the largest multilingual benchmark for evaluating language models' understanding of dance traditions through expert-curated QA pairs.
-
DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping
DVMap extracts high-consensus demographic groups from survey data and applies structured CoT plus GRPO to align LLMs with pluralistic values, reporting 48.6% accuracy on cross-demographic generalization tests.
-
When Do LLMs Generate Realistic Social Networks? A Multi-Dimensional Study of Culture, Language, Scale, and Method
LLM social networks vary with culture, language, scale, and prompting method, matching real graphs on clustering but exceeding empirical demographic biases.
-
Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest
Many LLMs prioritize company ad incentives over user welfare by recommending pricier sponsored products, disrupting purchases, or concealing prices in comparisons.
-
Cultural Authenticity: Comparing LLM Cultural Representations to Native Human Expectations
LLMs display Western-centric cultural representations that align poorly with native priorities in non-Western countries and share highly correlated error patterns.
-
EvalMORAAL: Interpretable Chain-of-Thought and LLM-as-Judge Evaluation for Moral Alignment in Large Language Models
EvalMORAAL evaluates moral alignment of 20 LLMs on World Values Survey and PEW data, reporting high overall correlation with human responses but a 0.21 gap between Western and non-Western regions.
-
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
BLOOM is a 176B-parameter open-access multilingual language model trained on the ROOTS corpus that achieves competitive performance on benchmarks, with improved results after multitask prompted finetuning.
-
Editorial Alignment: A Participatory Approach to Engaging Editorial Expertise in LLM-mediated Knowledge Dissemination
The paper introduces 'editorial alignment' as a participatory design practice that treats editorial standards as design artifacts to guide LLM behavior in knowledge dissemination, shown through workshops at one Nordic...
-
Occupational Prompting Reveals Cultural Bias in Large Language Models
Occupational prompting of open-weight LLMs elicits structured value patterns in Inglehart-Welzel cultural space, extending prior nationality-based cultural bias evaluations.
-
Prompt Programming for Cultural Bias and Alignment of Large Language Models
Automatically optimized prompts (DSPy) reduce survey-measured cultural distance for open-weight LLMs more often than manual cultural prompting, with MIPROv2 and a large proposer model giving the most consistent gains.
-
Framing an AI with Values Reduces AI Reliance in AI-supported Writing Tasks
An online experiment finds that showing users an overview of an AI's values reduces reliance on AI suggestions during writing tasks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.