Publications

2024

1. Preprint

   When Does Classical Chinese Help? Quantifying Cross-Lingual Transfer in Hanja and Kanbun

   Seyoung Song, Haneul Yoo, Jiho Jin, Kyunghyun Cho, and Alice Oh

   arXiv preprint, 2024

   Abs arXiv Code

   Historical and linguistic connections within the Sinosphere have led researchers to use Classical Chinese resources for cross-lingual transfer when processing historical documents from Korea and Japan. In this paper, we question the assumption of cross-lingual transferability from Classical Chinese to Hanja and Kanbun, the ancient written languages of Korea and Japan, respectively. Our experiments across machine translation, named entity recognition, and punctuation restoration tasks show minimal impact of Classical Chinese datasets on language model performance for ancient Korean documents written in Hanja, with performance differences within ±0.0068 F1-score for sequence labeling tasks and up to +0.84 BLEU score for translation. These limitations persist consistently across various model sizes, architectures, and domain-specific datasets. Our analysis reveals that the benefits of Classical Chinese resources diminish rapidly as local language data increases for Hanja, while showing substantial improvements only in extremely low-resource scenarios for both Korean and Japanese historical documents. These mixed results emphasize the need for careful empirical validation rather than assuming benefits from indiscriminate cross-lingual transfer.

2. Preprint

   Code-Switching Curriculum Learning for Multilingual Transfer in LLMs

   Haneul Yoo, Cheonbok Park, Sangdoo Yun, Alice Oh, and Hwaran Lee

   arXiv preprint, 2024

   Abs arXiv

   Large language models (LLMs) now exhibit near human-level performance in various tasks, but their performance drops drastically after a handful of high-resource languages due to the imbalance in pre-training data. Inspired by the human process of second language acquisition, particularly code-switching (the practice of language alternation in a conversation), we propose code-switching curriculum learning (CSCL) to enhance cross-lingual transfer for LLMs. CSCL mimics the stages of human language learning by progressively training models with a curriculum consisting of 1) token-level code-switching, 2) sentence-level code-switching, and 3) monolingual corpora. Using Qwen 2 as our underlying model, we demonstrate the efficacy of the CSCL in improving language transfer to Korean, achieving significant performance gains compared to monolingual continual pre-training methods. Ablation studies reveal that both token- and sentence-level code-switching significantly enhance cross-lingual transfer and that curriculum learning amplifies these effects. We also extend our findings into various languages, including Japanese (high-resource) and Indonesian (low-resource), and using two additional models (Gemma 2 and Phi 3.5). We further show that CSCL mitigates spurious correlations between language resources and safety alignment, presenting a robust, efficient framework for more equitable language transfer in LLMs. We observe that CSCL is effective for low-resource settings where high-quality, monolingual corpora for language transfer are hardly available.

3. Preprint

   MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertainty

   Yongjin Yang, Haneul Yoo, and Hwaran Lee

   arXiv preprint, 2024

   Abs arXiv

   Although large language models (LLMs) are capable of performing various tasks, they still suffer from producing plausible but incorrect responses. To improve the reliability of LLMs, recent research has focused on uncertainty quantification to predict whether a response is correct or not. However, most uncertainty quantification methods have been evaluated on questions requiring a single clear answer, ignoring the existence of data uncertainty that arises from irreducible randomness. Instead, these methods only consider model uncertainty, which arises from a lack of knowledge. In this paper, we investigate previous uncertainty quantification methods under the presence of data uncertainty. Our contributions are two-fold: 1) proposing a new Multi-Answer Question Answering dataset, MAQA, consisting of world knowledge, mathematical reasoning, and commonsense reasoning tasks to evaluate uncertainty quantification regarding data uncertainty, and 2) assessing 5 uncertainty quantification methods of diverse white- and black-box LLMs. Our findings show that entropy and consistency-based methods estimate the model uncertainty well even under data uncertainty, while other methods for white- and black-box LLMs struggle depending on the tasks. Additionally, methods designed for white-box LLMs suffer from overconfidence in reasoning tasks compared to simple knowledge queries. We believe our observations will pave the way for future work on uncertainty quantification in realistic setting.

4. Workshop

   Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding

   Haneul Yoo, Yongjin Yang, and Hwaran Lee

   Red Teaming Gen AI @ NeurIPS, 2024

   Abs arXiv Code

   Recent studies in large language models (LLMs) shed light on their multilingual ability and safety, beyond conventional tasks in language modeling. Still, current benchmarks reveal their inability to comprehensively evaluate them and are excessively dependent on manual annotations. In this paper, we introduce code-switching red-teaming (CSRT), a simple yet effective red-teaming technique that simultaneously tests multilingual understanding and safety of LLMs. We release the CSRT dataset, which comprises 315 code-switching queries combining up to 10 languages and eliciting a wide range of undesirable behaviors. Through extensive experiments with ten state-of-the-art LLMs, we demonstrate that CSRT significantly outperforms existing multilingual red-teaming techniques, achieving 46.7% more attacks than existing methods in English. We analyze the harmful responses toward the CSRT dataset concerning various aspects under ablation studies with 16K samples, including but not limited to scaling laws, unsafe behavior categories, and input conditions for optimal data generation. Additionally, we validate the extensibility of CSRT, by generating code-switching attack prompts with monolingual data.

5. Workshop

   DREsS: Dataset for Rubric-based Essay Scoring on EFL Writing

   Haneul Yoo, Jieun Han, So-Yeon Ahn, and Alice Oh

   FM-EduAssess @ NeurIPS, 2024

   Abs arXiv Website

   Automated essay scoring (AES) is a useful tool in English as a Foreign Language (EFL) writing education, offering real-time essay scores for students and instructors. However, previous AES models were trained on essays and scores irrelevant to the practical scenarios of EFL writing education and usually provided a single holistic score due to the lack of appropriate datasets. In this paper, we release DREsS, a large-scale, standard dataset for rubric-based automated essay scoring. DREsS comprises three sub-datasets: DREsS_New, DREsS_Std., and DREsS_CASE. We collect DREsS_New, a real-classroom dataset with 1.7K essays authored by EFL undergraduate students and scored by English education experts. We also standardize existing rubric-based essay scoring datasets as DREsS_Std. We suggest CASE, a corruption-based augmentation strategy for essays, which generates 20K synthetic samples of DREsS_CASE and improves the baseline results by 45.44%. DREsS will enable further research to provide a more accurate and practical AES system for EFL writing education.

6. Workshop

   LLM-as-a-tutor in EFL Writing Education: Focusing on Evaluation of Student-LLM Interaction

   Jieun Han, Haneul Yoo, Junho Myung, Minsun Kim, Hyunseung Lim, Yoonsu Kim, Tak Yeon Lee, Hwajung Hong, Juho Kim, So-Yeon Ahn, and Alice Oh

   CustomNLP4U @ EMNLP, 2024

   Abs arXiv PDF

   In the context of English as a Foreign Language (EFL) writing education, LLM-as-a-tutor can assist students by providing real-time feedback on their essays. However, challenges arise in assessing LLM-as-a-tutor due to differing standards between educational and general use cases. To bridge this gap, we integrate pedagogical principles to assess student-LLM interaction. First, we explore how LLMs can function as English tutors, providing effective essay feedback tailored to students. Second, we propose three metrics to evaluate LLM-as-a-tutor specifically designed for EFL writing education, emphasizing pedagogical aspects. In this process, EFL experts evaluate the feedback from LLM-as-a-tutor regarding quality and characteristics. On the other hand, EFL learners assess their learning outcomes from interaction with LLM-as-a-tutor. This approach lays the groundwork for developing LLMs-as-a-tutor tailored to the needs of EFL learners, advancing the effectiveness of writing education in this context.

7. Workshop

   Designing Prompt Analytics Dashboards to Analyze Student-ChatGPT Interactions in EFL Writing

   Minsun Kim, SeonGyeom Kim, Suyoun Lee, Yoosang Yoon, Junho Myung, Haneul Yoo, Hyungseung Lim, Jieun Han, Yoonsu Kim, So-Yeon Ahn, Juho Kim, Alice Oh, Hwajung Hong, and Tak Yeon Lee

   CustomNLP4U @ EMNLP, 2024

   Abs arXiv

   While ChatGPT has significantly impacted education by offering personalized resources for students, its integration into educational settings poses unprecedented risks, such as inaccuracies and biases in AI-generated content, plagiarism and over-reliance on AI, and privacy and security issues. To help teachers address such risks, we conducted a two-phase iterative design process that comprises surveys, interviews, and prototype demonstration involving six EFL (English as a Foreign Language) teachers, who integrated ChatGPT into semester-long English essay writing classes. Based on the needs identified during the initial survey and interviews, we developed a prototype of Prompt Analytics Dashboard (PAD) that integrates the essay editing history and chat logs between students and ChatGPT. Teacher’s feedback on the prototype informs additional features and unmet needs for designing future PAD, which helps them (1) analyze contextual analysis of student behaviors, (2) design an overall learning loop, and (3) develop their teaching skills.

8. Workshop

   CHOP: Integrating ChatGPT into EFL Oral Presentation Practice

   Jungyoub Cha, Jieun Han, Haneul Yoo, and Alice Oh

   LLM Workshop @ EDM, 2024

   Abs arXiv

   English as a Foreign Language (EFL) students often struggle to deliver oral presentations due to a lack of reliable resources and the limited effectiveness of instructors’ feedback. Large Language Model (LLM) can offer new possibilities to assist students’ oral presentations with real-time feedback. This paper investigates how ChatGPT can be effectively integrated into EFL oral presentation practice to provide personalized feedback. We introduce a novel learning platform, CHOP (ChatGPT-based Interactive Platform for Oral Presentation Practice), and evaluate its effectiveness with 13 EFL students. By collecting student-ChatGPT interaction data and expert assessments of the feedback quality, we identify the platform’s strengths and weaknesses. We also analyze learners’ perceptions and key design factors. Based on these insights, we suggest further development opportunities and design improvements for the education community.

9. LREC-COLING

   CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Korean

   Eunsu Kim, Juyoung Suk, Philhoon Oh, Haneul Yoo, James Thorne, and Alice Oh

   LREC-COLING, 2024

   Abs arXiv PDF Code

   Despite the rapid development of large language models (LLMs) for the Korean language, there remains an obvious lack of benchmark datasets that test the requisite Korean cultural and linguistic knowledge. Because many existing Korean benchmark datasets are derived from the English counterparts through translation, they often overlook the different cultural contexts. For the few benchmark datasets that are sourced from Korean data capturing cultural knowledge, only narrow tasks such as hate speech detection are offered. To address this gap, we introduce a benchmark of Cultural and Linguistic Intelligence in Korean (CLIcK), a dataset comprising 1,995 QA pairs. CLIcK sources its data from official Korean exams and textbooks, partitioning the questions into eleven categories under the two main categories of language and culture. For each instance in click, we provide fine-grained annotation of which cultural and linguistic knowledge is required to correctly answer the question. Using CLIcK, we test 13 language models to assess their performance. Our evaluation uncovers insights into their performances across the categories, as well as the diverse factors affecting their comprehension. CLIcK offers the first large-scale comprehensive Korean-centric analysis of LLMs’ proficiency in Korean language and culture.

10. LREC-COLING

    RECIPE4U: Student-ChatGPT Interaction Dataset in EFL Writing Education

    Jieun Han*, Haneul Yoo*, Junho Myung, Minsun Kim, Tak Yeon Lee, So-Yeon Ahn, and Alice Oh

    LREC-COLING, 2024

    Abs arXiv PDF Website

    The integration of generative AI in education is expanding, yet empirical analyses of large-scale and real-world interactions between students and AI systems still remain limited. Addressing this gap, we present RECIPE4U (RECIPE for University), a dataset sourced from a semester-long experiment with 212 college students in English as Foreign Language (EFL) writing courses. During the study, students engaged in dialogues with ChatGPT to revise their essays. RECIPE4U includes comprehensive records of these interactions, including conversation logs, students’ intent, students’ self-rated satisfaction, and students’ essay edit histories. In particular, we annotate the students’ utterances in RECIPE4U with 13 intention labels based on our coding schemes. We establish baseline results for two subtasks in task-oriented dialogue systems within educational contexts: intent detection and satisfaction estimation. As a foundational step, we explore student-ChatGPT interaction patterns through RECIPE4U and analyze them by focusing on students’ dialogue, essay data statistics, and students’ essay edits. We further illustrate potential applications of RECIPE4U dataset for enhancing the incorporation of LLMs in educational frameworks. RECIPE4U is publicly available at this https URL.

11. Tech Report

    HyperCLOVA X Technical Report

    HyperCLOVA X Team

    arXiv preprint, 2024

    Abs arXiv Website

    We introduce HyperCLOVA X, a family of large language models (LLMs) tailored to the Korean language and culture, along with competitive capabilities in English, math, and coding. HyperCLOVA X was trained on a balanced mix of Korean, English, and code data, followed by instruction-tuning with high-quality human-annotated datasets while abiding by strict safety guidelines reflecting our commitment to responsible AI. The model is evaluated across various benchmarks, including comprehensive reasoning, knowledge, commonsense, factuality, coding, math, chatting, instruction-following, and harmlessness, in both Korean and English. HyperCLOVA X exhibits strong reasoning capabilities in Korean backed by a deep understanding of the language and cultural nuances. Further analysis of the inherent bilingual nature and its extension to multilingualism highlights the model’s cross-lingual proficiency and strong generalization ability to untargeted languages, including machine translation between several language pairs and cross-lingual inference tasks. We believe that HyperCLOVA X can provide helpful guidance for regions or countries in developing their sovereign LLMs.

12. TACL

    KoBBQ: Korean Bias Benchmark for Question Answering

    Jiho Jin*, Jiseon Kim*, Nayeon Lee*, Haneul Yoo*, Alice Oh, and Hwaran Lee

    TACL (IF=9.194) , 2024

    Abs arXiv PDF Code Website

    Warning: This paper contains examples of stereotypes and biases.The Bias Benchmark for Question Answering (BBQ) is designed to evaluate social biases of language models (LMs), but it is not simple to adapt this benchmark to cultural contexts other than the US because social biases depend heavily on the cultural context. In this paper, we present KoBBQ, a Korean bias benchmark dataset, and we propose a general framework that addresses considerations for cultural adaptation of a dataset. Our framework includes partitioning the BBQ dataset into three classes—Simply-Transferred (can be used directly after cultural translation), Target-Modified (requires localization in target groups), and Sample-Removed (does not fit Korean culture)—and adding four new categories of bias specific to Korean culture. We conduct a large-scale survey to collect and validate the social biases and the targets of the biases that reflect the stereotypes in Korean culture. The resulting KoBBQ dataset comprises 268 templates and 76,048 samples across 12 categories of social bias. We use KoBBQ to measure the accuracy and bias scores of several state-of-the-art multilingual LMs. The results clearly show differences in the bias of LMs as measured by KoBBQ and a machine-translated version of BBQ, demonstrating the need for and utility of a well-constructed, culturally aware social bias benchmark.

2023

1. ACL

   Rethinking Annotation: Can Language Learners Contribute?

   Haneul Yoo, Rifki Afina Putri, Changyoon Lee, Youngin Lee, So-Yeon Ahn, Dongyeop Kang, and Alice Oh

   ACL, 2023

   Abs arXiv PDF

   Researchers have traditionally recruited native speakers to provide annotations for the widely used benchmark datasets. But there are languages for which recruiting native speakers is difficult, and it would help to get learners of those languages to annotate the data. In this paper, we investigate whether language learners can contribute annotations to the benchmark datasets. In a carefully controlled annotation experiment, we recruit 36 language learners, provide two types of additional resources (dictionaries and machine-translated sentences), and perform mini-tests to measure their language proficiency. We target three languages, English, Korean, and Indonesian, and four NLP tasks, sentiment analysis, natural language inference, named entity recognition, and machine reading comprehension. We find that language learners, especially those with intermediate or advanced language proficiency, are able to provide fairly accurate labels with the help of additional resources. Moreover, we show that data annotation improves learners’ language proficiency in terms of vocabulary and grammar. The implication of our findings is that broadening the annotation task to include language learners can open up the opportunity to build benchmark datasets for languages for which it is difficult to recruit native speakers.

2. L@S

   RECIPE: How to Integrate ChatGPT into EFL Writing Education

   Jieun Han*, Haneul Yoo*, Yoonsu Kim, Junho Myung, Minsun Kim, Hyunseung Lim, Juho Kim, Tak Yeon Lee, Hwajung Hong, So-Yeon Ahn, and Alice Oh

   ACM Learning @ Scale (L@S) Work-in-Progress, 2023

   Abs arXiv PDF

   The integration of generative AI in the field of education is actively being explored. In particular, ChatGPT has garnered significant interest, offering an opportunity to examine its effectiveness in English as a foreign language (EFL) education. To address this need, we present a novel learning platform called RECIPE (Revising an Essay with ChatGPT on an Interactive Platform for EFL learners). Our platform features two types of prompts that facilitate conversations between ChatGPT and students: (1) a hidden prompt for ChatGPT to take an EFL teacher role and (2) an open prompt for students to initiate a dialogue with a self-written summary of what they have learned. We deployed this platform for 213 undergraduate and graduate students enrolled in EFL writing courses and seven instructors. For this study, we collect students’ interaction data from RECIPE, including students’ perceptions and usage of the platform, and user scenarios are examined with the data. We also conduct a focus group interview with six students and an individual interview with one EFL instructor to explore design opportunities for leveraging generative AI models in the field of EFL education.

2022

1. Findings

   Translating Hanja Historical Documents to Contemporary Korean and English

   Juhee Son*, Jiho Jin*, Haneul Yoo, JinYeong Bak, Kyunghyun Cho, and Alice Oh

   EMNLP Findings, 2022

   Abs arXiv PDF Website

   The Annals of Joseon Dynasty (AJD) contain the daily records of the Kings of Joseon, the 500-year kingdom preceding the modern nation of Korea.The Annals were originally written in an archaic Korean writing system, ‘Hanja’, and were translated into Korean from 1968 to 1993.The resulting translation was however too literal and contained many archaic Korean words; thus, a new expert translation effort began in 2012. Since then, the records of only one king have been completed in a decade.In parallel, expert translators are working on English translation, also at a slow pace and produced only one king’s records in English so far.Thus, we propose H2KE, a neural machine translation model, that translates historical documents in Hanja to more easily understandable Korean and to English.Built on top of multilingual neural machine translation, H2KE learns to translate a historical document written in Hanja, from both a full dataset of outdated Korean translation and a small dataset of more recently translated contemporary Korean and English.We compare our method against two baselines:a recent model that simultaneously learns to restore and translate Hanja historical documentand a Transformer based model trained only on newly translated corpora.The experiments reveal that our method significantly outperforms the baselines in terms of BLEU scores for both contemporary Korean and English translations.We further conduct extensive human evaluation which shows that our translation is preferred over the original expert translations by both experts and non-expert Korean speakers.

2. Findings

   HUE: Pretrained Model and Dataset for Understanding Hanja Documents of Ancient Korea

   Haneul Yoo, Jiho Jin, Juhee Son, JinYeong Bak, Kyunghyun Cho, and Alice Oh

   NAACL Findings, 2022

   Abs arXiv PDF Code

   Historical records in Korea before the 20th century were primarily written in Hanja, an extinct language based on Chinese characters and not understood by modern Korean or Chinese speakers. Historians with expertise in this time period have been analyzing the documents, but that process is very difficult and time-consuming, and language models would significantly speed up the process. Toward building and evaluating language models for Hanja, we release the Hanja Understanding Evaluation dataset consisting of chronological attribution, topic classification, named entity recognition, and summary retrieval tasks. We also present BERT-based models continued training on the two major corpora from the 14th to the 19th centuries: the Annals of the Joseon Dynasty and Diaries of the Royal Secretariats. We compare the models with several baselines on all tasks and show there are significant improvements gained by training on the two corpora. Additionally, we run zero-shot experiments on the Daily Records of the Royal Court and Important Officials (DRRI). The DRRI dataset has not been studied much by the historians, and not at all by the NLP community.

2021

1. Findings

   Knowledge-Enhanced Evidence Retrieval for Counterargument Generation

   Yohan Jo, Haneul Yoo, JinYeong Bak, Alice Oh, Chris Reed, and Eduard Hovy

   EMNLP Findings, 2021

   Abs arXiv PDF Code

   Finding counterevidence to statements is key to many tasks, including counterargument generation. We build a system that, given a statement, retrieves counterevidence from diverse sources on the Web. At the core of this system is a natural language inference (NLI) model that determines whether a candidate sentence is valid counterevidence or not. Most NLI models to date, however, lack proper reasoning abilities necessary to find counterevidence that involves complex inference. Thus, we present a knowledge-enhanced NLI model that aims to handle causality- and example-based inference by incorporating knowledge graphs. Our NLI model outperforms baselines for NLI tasks, especially for instances that require the targeted inference. In addition, this NLI model further improves the counterevidence retrieval system, notably finding complex counterevidence better.

2020

1. Domestic

   Image-based Deep Learning Approach for EEG Signal Classification

   Haneul Yoo, Jungryul Seo, and Kyung-Ah Sohn

   KICS Summer Conference, 2020
2. Domestic

   Proposal and Simulation of Optimal Electric Vehicle Routing Algorithm

   Moonsuk Choi, Inji Choi, Minhae Jang, and Haneul Yoo

   KEPCO Journal on Electric Power and Energy, 2020

   Abs PDF

   Scheduling of electric vehicles and optimizing for charging waiting time have been critical. Meanwhile, it is challengeable to exploit the fluctuating data from electric vehicles in real-time. We introduce an optimal routing algorithm and a simulator with electric vehicles obeying the Poisson distribution of the observed information about time, space and energy-demand. Electric vehicle routing is updated in every cycle even it is already set. Also, we suggest an electric vehicle routing algorithm for minimizing total trip time, considering a threshold of the waiting time. Total trip time and charging waiting time are decreased 34.3% and 86.4% respectively, compared to the previous algorithm. It can be applied to the information service of charging stations and utilized as a reservation service.