Related papers: Obfuscation Rules for Detecting and Detoxifying Ko…
Syntactic elements, such as word order and case markers, are fundamental in natural language processing. Recent studies show that syntactic information boosts language model performance and offers clues for people to understand their…
In this study, we introduce KOPL, a novel framework for handling Korean OOV words with Phoneme representation Learning. Our work is based on the linguistic property of Korean as a phonemic script, the high correlation between phonemes and…
The opacity in developing large language models (LLMs) is raising growing concerns about the potential contamination of public benchmarks in the pre-training data. Existing contamination detection methods are typically based on the text…
The widespread dissemination of toxic content on social media poses a serious threat to both online environments and public discourse, highlighting the urgent need for detoxification methods that effectively remove toxicity while preserving…
The widespread dissemination of toxic online posts is increasingly damaging to society. However, research on detecting toxic language in Chinese has lagged significantly. Existing datasets lack fine-grained annotation of toxic types and…
Due to the fact that Korean is a highly agglutinative, character-rich language, previous work on Korean morphological analysis typically employs the use of sub-character features known as graphemes or otherwise utilizes comprehensive prior…
Large Language Models (LLMs) and Vision Language Models (VLMs) have recently shown promising capabilities in various scientific domain. In particular, these advances have opened new opportunities in drug discovery, where the ability to…
Transformer-based language models are able to generate fluent text and be efficiently adapted across various natural language generation tasks. However, language models that are pretrained on large unlabeled web text corpora have been shown…
As malicious users increasingly employ phonetic substitution to evade hate speech detection, researchers have investigated such strategies. However, two key challenges remain. First, existing studies have overlooked the Korean language,…
Detoxifying offensive language while preserving the speaker's original intent is a challenging yet critical goal for improving the quality of online interactions. Although large language models (LLMs) show promise in rewriting toxic…
This article describes an exclusively resource-based method of morphological annotation of written Korean text. Korean is an agglutinative language. Our annotator is designed to process text before the operation of a syntactic parser. In…
The goal of homomorphic encryption is to encrypt data such that another party can operate on it without being explicitly exposed to the content of the original data. We introduce an idea for a privacy-preserving transformation on natural…
This report introduces \texttt{EEVE-Korean-v1.0}, a Korean adaptation of large language models that exhibit remarkable capabilities across English and Korean text understanding. Building on recent highly capable but English-centric LLMs,…
Prior works on detoxification are scattered in the sense that they do not cover all aspects of detoxification needed in a real-world scenario. Notably, prior works restrict the task of developing detoxification models to only a seen subset…
The advent of social media in recent years has fed into some highly undesirable phenomena such as proliferation of offensive language, hate speech, sexist remarks, etc. on the Internet. In light of this, there have been several efforts to…
Language models (LMs) can reproduce (or amplify) toxic language seen during training, which poses a risk to their practical application. In this paper, we conduct extensive experiments to study this phenomenon. We analyze the impact of…
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…
Korean is often referred to as a low-resource language in the research community. While this claim is partially true, it is also because the availability of resources is inadequately advertised and curated. This work curates and reviews a…
Text detoxification is the task of transferring the style of text from toxic to neutral. While here are approaches yielding promising results in monolingual setup, e.g., (Dale et al., 2021; Hallinan et al., 2022), cross-lingual transfer for…
Existing question answering systems mainly focus on dealing with text data. However, much of the data produced daily is stored in the form of tables that can be found in documents and relational databases, or on the web. To solve the task…