An official website of the United States government
Large language models (LLMs) are being increasingly integrated into everyday products and services, such as coding tools and writing assistants. As these embedded AI applications are deployed globally, there is a growing concern that the AI models underlying these applications prioritize Western values. This paper investigates what happens when a Western-centric AI model provides writing suggestions to users from a different cultural background. We conducted a cross-cultural controlled experiment with 118 participants from India and the United States who completed culturally grounded writing tasks with and without AI suggestions. Our analysis reveals that AI provided greater efficiency gains for Americans compared to Indians. Moreover, AI suggestions led Indian participants to adopt Western writing styles, altering not just what is written but also how it is written. These findings show that Western-centric AI models homogenize writing toward Western norms, diminishing nuances that differentiate cultural expression.
more »
« less
Implicit Values Embedded in How Humans and LLMs Complete Subjective Everyday Tasks
Large language models (LLMs) can underpin AI assistants that help users with everyday tasks, such as by making recommendations or performing basic computation. Despite AI assistants’ promise, little is known about the implicit values these assistants display while completing subjective everyday tasks. Humans may consider values like environmentalism, charity, and diversity. To what extent do LLMs exhibit these values in completing everyday tasks? How do they compare with humans? We answer these questions by auditing how six popular LLMs complete 30 everyday tasks, comparing LLMs to each other and to 100 human crowdworkers from the US. We find LLMs often do not align with humans, nor with other LLMs, in the implicit values exhibited.
more »
« less
- Award ID(s):
- 2229876
- PAR ID:
- 10662043
- Publisher / Repository:
- Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
- Date Published:
- Page Range / eLocation ID:
- 16731-16754
- Format(s):
- Medium: X
- Location:
- Suzhou, China
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Artificial Intelligence, intelligence demonstrated by machines, has emerged as one of the most convenient and personable applications of everyday life. Specifically, AI powers digital personal assistants to answer user questions and automate everyday tasks. AI Assistants listen continuously to answer the user, even when not in use. Why is this a problem? For a hacker, this makes any digital assistant a potential listening device, a major security and privacy issue. While some companies are handling this situation well, others are falling behind as their AI components are slowly dying in the consumer market. Which digital assistant is best and most secure you may ask? This paper will first detail how each AI assistant works from a technical perspective. Then based on survey results, this paper will detail how AI Assistants rank in terms of overall security and performancemore » « less
-
Navigating dilemmas involving conflicting values is challenging even for humans in high-stakes domains, let alone for AI, yet prior work has been limited to everyday scenarios. To close this gap, we introduce CLASH (Character perspective-based LLM Assessments in Situations with High-stakes), a meticulously curated dataset consisting of 345 high-impact dilemmas along with 3,795 individual perspectives of diverse values. CLASH enables the study of critical yet underexplored aspects of value-based decision-making processes, including understanding of decision ambivalence and psychological discomfort as well as capturing the temporal shifts of values in the perspectives of characters. By benchmarking 14 non-thinking and thinking models, we uncover several key findings. (1) Even strong proprietary models, such as GPT-5 and Claude-4-Sonnet, struggle with ambivalent decisions, achieving only 24.06 and 51.01 accuracy. (2) Although LLMs reasonably predict psychological discomfort, they do not adequately comprehend perspectives involving value shifts. (3) Cognitive behaviors that are effective in the math-solving and game strategy domains do not transfer to value reasoning. Instead, new failure patterns emerge, including early commitment and overcommitment. (4) The steerability of LLMs towards a given value is significantly correlated with their value preferences. (5) Finally, LLMs exhibit greater steerability when reasoning from a third-party perspective, although certain values (e.g., safety) benefit uniquely from first-person framing.more » « less
-
Introduction: Recent AI advances, particularly the introduction of large language models (LLMs), have expanded the capacity to automate various tasks, including the analysis of text. This capability may be especially helpful in education research, where lack of resources often hampers the ability to perform various kinds of analyses, particularly those requiring a high level of expertise in a domain and/or a large set of textual data. For instance, we recently coded approximately 10,000 state K-12 computer science standards, requiring over 200 hours of work by subject matter experts. If LLMs are capable of completing a task such as this, the savings in human resources would be immense. Research Questions: This study explores two research questions: (1) How do LLMs compare to humans in the performance of an education research task? and (2) What do errors in LLM performance on this task suggest about current LLM capabilities and limitations? Methodology: We used a random sample of state K-12 computer science standards. We compared the output of three LLMs – ChatGPT, Llama, and Claude – to the work of human subject matter experts in coding the relationship between each state standard and a set of national K-12 standards. Specifically, the LLMs and the humans determined whether each state standard was identical to, similar to, based on, or different from the national standards and (if it was not different) which national standard it resembled. Results: Each of the LLMs identified a different national standard than the subject matter expert in about half of instances. When the LLM identified the same standard, it usually categorized the type of relationship (i.e., identical to, similar to, based on) in the same way as the human expert. However, the LLMs sometimes misidentified ‘identical’ standards. Discussion: Our results suggest that LLMs are not currently capable of matching human performance on the task of classifying learning standards. The mis-identification of some state standards as identical to national standards – when they clearly were not – is an interesting error, given that traditional computing technologies can easily identify identical text. Similarly, some of the mismatches between the LLM and human performance indicate clear errors on the part of the LLMs. However, some of the mismatches are difficult to assess, given the ambiguity inherent in this task and the potential for human error. We conclude the paper with recommendations for the use of LLMs in education research based on these findings.more » « less
-
Recent advances in Natural Language Interfaces (NLIs) and Large Language Models (LLMs) have transformed the way we tackle NLP tasks, shifting the focus towards a more Pragmatics-based perspective. This shift enables more natural interactions between humans and voice assistants, which have historically been difficult to achieve. Pragmatics involves understanding how users often speak out of turn, interrupt one another, or provide relevant information without being explicitly asked (maxim of quantity). To explore this, we developed a digital assistant that continuously listens to conversations and proactively generates relevant visualizations during data exploration tasks. In a within-subject study, participants interacted with both proactive and non-proactive versions of a voice assistant while exploring the Hawaii Climate Data Portal (HCDP). Results suggest that interaction with the proactive assistant increased the total number of utterances and discoveries, facilitated quicker and more reliable insights, and led to greater usage of the system’s chart capabilities. Our study highlights the potential of proactive AI in NLIs and identifies key challenges in its implementation, offering insights for future research.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Conference Paper:
- The DOI is not currently available.
