English
Related papers

Related papers: Obfuscation Rules for Detecting and Detoxifying Ko…

200 papers

Latent-space monitors aim to detect undesirable behaviours in Large Language Models by leveraging their internal representations rather than relying solely on black-box outputs. These methods have shown promise in identifying behaviours…

Machine Learning · Computer Science 2026-02-27 Rohan Gupta , Erik Jenner

This paper introduces EVOKE (Emotion Vocabulary of Korean and English), a Korean-English parallel dataset of emotion words. The dataset offers comprehensive coverage of emotion words in each language, in addition to many-to-many…

Computation and Language · Computer Science 2026-04-13 Yoonwon Jung , Hagyeong Shin , Benjamin K. Bergen

Recent advances in self-supervised learning have dramatically improved the state of the art on a wide variety of tasks. However, research in language model pre-training has mostly focused on natural languages, and it is unclear whether…

Computation and Language · Computer Science 2021-10-29 Baptiste Roziere , Marie-Anne Lachaux , Marc Szafraniec , Guillaume Lample

Natural language inference (NLI) and semantic textual similarity (STS) are key tasks in natural language understanding (NLU). Although several benchmark datasets for those tasks have been released in English and a few other languages, there…

Computation and Language · Computer Science 2020-10-06 Jiyeon Ham , Yo Joong Choe , Kyubyong Park , Ilji Choi , Hyungjoon Soh

Language models (LMs) must be both safe and equitable to be responsibly deployed in practice. With safety in mind, numerous detoxification techniques (e.g., Dathathri et al. 2020; Krause et al. 2020) have been proposed to mitigate toxic LM…

Computation and Language · Computer Science 2021-04-14 Albert Xu , Eshaan Pathak , Eric Wallace , Suchin Gururangan , Maarten Sap , Dan Klein

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…

Computation and Language · Computer Science 2024-07-08 Eunsu Kim , Juyoung Suk , Philhoon Oh , Haneul Yoo , James Thorne , Alice Oh

Pre-trained language models (LMs) are shown to easily generate toxic language. In this work, we systematically explore domain-adaptive training to reduce the toxicity of language models. We conduct this study on three dimensions: training…

Computation and Language · Computer Science 2022-10-25 Boxin Wang , Wei Ping , Chaowei Xiao , Peng Xu , Mostofa Patwary , Mohammad Shoeybi , Bo Li , Anima Anandkumar , Bryan Catanzaro

A well-formulated benchmark plays a critical role in spurring advancements in the natural language processing (NLP) field, as it allows objective and precise evaluation of diverse models. As modern language models (LMs) have become more…

Computation and Language · Computer Science 2022-04-12 Dohyeong Kim , Myeongjun Jang , Deuk Sin Kwon , Eric Davis

Training against white-box deception detectors has been proposed as a way to make AI systems honest. However, such training risks models learning to obfuscate their deception to evade the detector. Prior work has studied obfuscation only in…

Machine Learning · Computer Science 2026-05-28 Mohammad Taufeeque , Stefan Heimersheim , Adam Gleave , Chris Cundy

We propose the Data Contamination Quiz (DCQ), a simple and effective approach to detect data contamination in large language models (LLMs) and estimate the amount of it. Specifically, we frame data contamination detection as a series of…

Computation and Language · Computer Science 2025-04-29 Shahriar Golchin , Mihai Surdeanu

Detecting toxic content using language models is important but challenging. While large language models (LLMs) have demonstrated strong performance in understanding Chinese, recent studies show that simple character substitutions in toxic…

Computation and Language · Computer Science 2025-06-02 Shujian Yang , Shiyao Cui , Chuanrui Hu , Haicheng Wang , Tianwei Zhang , Minlie Huang , Jialiang Lu , Han Qiu

Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that defenses such as outlier detection, clean-data regularization,…

Cryptography and Security · Computer Science 2026-05-27 Zedian Shao , Charles Fleming , Teodora Baluta

The instruction-following capabilities of large language models (LLMs) are pivotal for numerous applications, from conversational agents to complex reasoning systems. However, current evaluations predominantly focus on English models,…

Computation and Language · Computer Science 2025-10-20 Dongjun Kim , Chanhee Park , Chanjun Park , Heuiseok Lim

Lack of moderation in online communities enables participants to incur in personal aggression, harassment or cyberbullying, issues that have been accentuated by extremist radicalisation in the contemporary post-truth politics scenario. This…

Computation and Language · Computer Science 2018-01-08 Nestor Rodriguez , Sergio Rojas-Galeano

This paper describes word {segmentation} granularity in Korean language processing. From a word separated by blank space, which is termed an eojeol, to a sequence of morphemes in Korean, there are multiple possible levels of word…

Computation and Language · Computer Science 2023-09-08 Jungyeul Park , Mija Kim

The necessity of language-specific tokenizers intuitively appears crucial for effective natural language processing, yet empirical analyses on their significance and underlying reasons are lacking. This study explores how language-specific…

Computation and Language · Computer Science 2025-02-24 Jean Seo , Jaeyoon Kim , SungJoo Byun , Hyopil Shin

Online hate speech detection has become an important issue due to the growth of online content, but resources in languages other than English are extremely limited. We introduce K-MHaS, a new multi-label dataset for hate speech detection…

Computation and Language · Computer Science 2022-10-03 Jean Lee , Taejun Lim , Heejun Lee , Bogeun Jo , Yangsok Kim , Heegeun Yoon , Soyeon Caren Han

Recent advancements in large language models(LLMs), such as GPT-4 and GPT-4o, have shown exceptional performance, especially in languages with abundant resources like English, thanks to extensive datasets that ensure robust training.…

Computation and Language · Computer Science 2024-11-15 Jin Yang , Zhiqiang Wang , Yanbin Lin , Zunduo Zhao

Large language models (LLMs) exhibit impressive language capabilities but remain vulnerable to malicious prompts and jailbreaking attacks. Existing knowledge editing methods for LLM detoxification face two major challenges. First, they…

Computation and Language · Computer Science 2025-05-29 Yifan Lu , Jing Li , Yigeng Zhou , Yihui Zhang , Wenya Wang , Xiucheng Li , Meishan Zhang , Fangming Liu , Jun Yu , Min Zhang

Existing toxic detection models face significant limitations, such as lack of transparency, customization, and reproducibility. These challenges stem from the closed-source nature of their training data and the paucity of explanations for…

Computation and Language · Computer Science 2025-01-24 Tinh Son Luong , Thanh-Thien Le , Thang Viet Doan , Linh Ngo Van , Thien Huu Nguyen , Diep Thi-Ngoc Nguyen
‹ Prev 1 3 4 5 6 7 10 Next ›