arXiv subjects

Eunjung Cho

Publications and source records attributed to Eunjung Cho.

9 recordsLinked to original sources

arXiv2026

NLP for Social Good: A Survey and Outlook of Challenges, Opportunities, and Responsible Deployment

Natural language processing (NLP) now shapes many aspects of our world, yet its potential for positive social impact is underexplored. This paper surveys work in ``NLP for Social Good" (NLP4SG) across nine domains relevant to global development and risk agendas, summarizing principal tasks and challenges. We analyze ACL Anthology trends, finding that inclusion and AI harms attract the most research, while domains such as poverty, peacebuilding, and environmental protection remain underexplored. Guided by our review, we outline opportunities for responsible and equitable NLP and conclude with a call for cross-disciplinary partnerships and human-centered approaches to ensure that future NLP technologies advance the public good.

cs.CL↗

arXiv2025

Modeling Motivated Reasoning in Law: Evaluating Strategic Role Conditioning in LLM Summarization

Large Language Models (LLMs) are increasingly used to generate user-tailored summaries, adapting outputs to specific stakeholders. In legal contexts, this raises important questions about motivated reasoning -- how models strategically frame information to align with a stakeholder's position within the legal system. Building on theories of legal realism and recent trends in legal practice, we investigate how LLMs respond to prompts conditioned on different legal roles (e.g., judges, prosecutors, attorneys) when summarizing judicial decisions. We introduce an evaluation framework grounded in legal fact and reasoning inclusion, also considering favorability towards stakeholders. Our results show that even when prompts include balancing instructions, models exhibit selective inclusion patterns that reflect role-consistent perspectives. These findings raise broader concerns about how similar alignment may emerge as LLMs begin to infer user roles from prior interactions or context, even without explicit role instructions. Our results underscore the need for role-aware evaluation of LLM summarization behavior in high-stakes legal settings.

cs.CL↗

arXiv2025

Hermit Kingdom Through the Lens of Multiple Perspectives: A Case Study of LLM Hallucination on North Korea

Hallucination in large language models (LLMs) remains a significant challenge for their safe deployment, particularly due to its potential to spread misinformation. Most existing solutions address this challenge by focusing on aligning the models with credible sources or by improving how models communicate their confidence (or lack thereof) in their outputs. While these measures may be effective in most contexts, they may fall short in scenarios requiring more nuanced approaches, especially in situations where access to accurate data is limited or determining credible sources is challenging. In this study, we take North Korea - a country characterised by an extreme lack of reliable sources and the prevalence of sensationalist falsehoods - as a case study. We explore and evaluate how some of the best-performing multilingual LLMs and specific language-based models generate information about North Korea in three languages spoken in countries with significant geo-political interests: English (United States, United Kingdom), Korean (South Korea), and Mandarin Chinese (China). Our findings reveal significant differences, suggesting that the choice of model and language can lead to vastly different understandings of North Korea, which has important implications given the global security challenges the country poses.

cs.CL↗

arXiv2024

Problem-Solving Guide: Predicting the Algorithm Tags and Difficulty for Competitive Programming Problems

The recent program development industries have required problem-solving abilities for engineers, especially application developers. However, AI-based education systems to help solve computer algorithm problems have not yet attracted attention, while most big tech companies require the ability to solve algorithm problems including Google, Meta, and Amazon. The most useful guide to solving algorithm problems might be guessing the category (tag) of the facing problems. Therefore, our study addresses the task of predicting the algorithm tag as a useful tool for engineers and developers. Moreover, we also consider predicting the difficulty levels of algorithm problems, which can be used as useful guidance to calculate the required time to solve that problem. In this paper, we present a real-world algorithm problem multi-task dataset, AMT, by mainly collecting problem samples from the most famous and large competitive programming website Codeforces. To the best of our knowledge, our proposed dataset is the most large-scale dataset for predicting algorithm tags compared to previous studies. Moreover, our work is the first to address predicting the difficulty levels of algorithm problems. We present a deep learning-based novel method for simultaneously predicting algorithm tags and the difficulty levels of an algorithm problem given. All datasets and source codes are available at https://github.com/sronger/PSG_Predicting_Algorithm_Tags_and_Difficulty.

cs.CL↗

arXiv2024

Aligning Large Language Models with Diverse Political Viewpoints

Large language models such as ChatGPT exhibit striking political biases. If users query them about political information, they often take a normative stance. To overcome this, we align LLMs with diverse political viewpoints from 100,000 comments written by candidates running for national parliament in Switzerland. Models aligned with this data can generate more accurate political viewpoints from Swiss parties, compared to commercial models such as ChatGPT. We also propose a procedure to generate balanced overviews summarizing multiple viewpoints using such models. The replication package contains all code and data.

cs.CL↗

arXiv2024

Three Disclaimers for Safe Disclosure: A Cardwriter for Reporting the Use of Generative AI in Writing Process

Generative artificial intelligence (AI) and large language models (LLMs) are increasingly being used in the academic writing process. This is despite the current lack of unified framework for reporting the use of machine assistance. In this work, we propose "Cardwriter", an intuitive interface that produces a short report for authors to declare their use of generative AI in their writing process. The demo is available online, at https://cardwriter.vercel.app

cs.CY↗

arXiv2023

PaperCard for Reporting Machine Assistance in Academic Writing

Academic writing process has benefited from various technological developments over the years including search engines, automatic translators, and editing tools that review grammar and spelling mistakes. They have enabled human writers to become more efficient in writing academic papers, for example by helping with finding relevant literature more effectively and polishing texts. While these developments have so far played a relatively assistive role, recent advances in large-scale language models (LLMs) have enabled LLMs to play a more major role in the writing process, such as coming up with research questions and generating key contents. This raises critical questions surrounding the concept of authorship in academia. ChatGPT, a question-answering system released by OpenAI in November 2022, has demonstrated a range of capabilities that could be utilised in producing academic papers. The academic community will have to address relevant pressing questions, including whether Artificial Intelligence (AI) should be merited authorship if it made significant contributions in the writing process, or whether its use should be restricted such that human authorship would not be undermined. In this paper, we aim to address such questions, and propose a framework we name "PaperCard", a documentation for human authors to transparently declare the use of AI in their writing process.

cs.CY↗

arXiv2023

Effects of Fine Particulate Matter on Cardiovascular Disease Morbidity: A Study on Seven Metropolitan Cities in South Korea

Objectives: The primary purpose of this study is to analyze the relationship between the first occurrence of hospitalization for cardiovascular disease (CVD) and particulate matter less than 2.5 micrometre in diameter (PM2.5) exposure, considering average PM2.5 concentration and the frequency of high PM2.5 concentration simultaneously. Methods: We used large-scale cohort data from seven metropolitan cities in South Korea. We estimated hazard ratios (HRs) and 95% confidence intervals (CIs) using the Cox proportional-hazards model, including annual average PM2.5 and annual hours of PM2.5 concentration exceeding 55.5 microgram/m3 (FH55). Results: We found that the risk was elevated by 11.6% (95% CI, 9.7-13.6) for all CVD per 2.9 microgram/m3 increase of average PM2.5. In addition, a 94-h increase in FH55 increased the risk of all CVD by 3.8% (95% CI, 2.8-4.7). Regarding stroke, we found that people who were older and had a history of hypertension were more vulnerable to PM2.5 exposure. Conclusion: Based on the findings, we conclude that accurate forecasting, information dissemination, and timely warning of high concentrations of PM2.5 at the national level may reduce the risk of CVD occurrence.

q-bio.QM↗

arXiv2021

Estimating the economic value of ultrafine particles information: A contingent valuation method

Global concern regarding ultrafine particles (UFPs), which are particulate matter (PM) with a diameter of less than 100nm, is increasing. These particles-with more serious health effects than PM less than 2.5 micrometers (PM2.5)-are difficult to measure using the current methods because their characteristics are different from those of other air pollutants. Therefore, a new monitoring system is required to obtain accurate UFPs information, which will raise the financial burden of the government and people. In this study, we estimated the economic value of UFPs information by evaluating the willingness-to-pay (WTP) for the UFPs monitoring and reporting system. We used the contingent valuation method (CVM) and the one-and-one-half-bounded dichotomous choice (OOHBDC) spike model. We analyzed how the respondents' socio-economic variables, as well as their cognition level of PM, affected their WTP. Therefore, we collected WTP data of 1,040 Korean respondents through an online survey. The estimated mean WTP for building a UFPs monitoring and reporting system is KRW 6,958.55-7,222.55 (USD 6.22-6.45) per household per year. We found that people satisfied with the current air pollutant information, and generally possessing relatively greater knowledge of UFPs, have higher WTP for a UFPs monitoring and reporting system. The results can be used to establish new policies response to PM including UFPs.

econ.GN↗