Related papers: Obfuscation Rules for Detecting and Detoxifying Ko…

Large language models (LLMs) have demonstrated remarkable performance in the legal domain, with GPT-4 even passing the Uniform Bar Exam in the U.S. However their efficacy remains limited for non-standardized tasks and tasks in languages…

Research in toxicity detection in natural language processing for the speech modality (audio-based) is quite limited, particularly for languages other than English. To address these limitations and lay the groundwork for truly multilingual…

This document gives a brief description of Korean data prepared for the SPMRL 2013 shared task. A total of 27,363 sentences with 350,090 tokens are used for the shared task. All constituent trees are collected from the KAIST Treebank and…

Finetuning can significantly modify the behavior of large language models, including introducing harmful or unsafe behaviors. To study these risks, researchers develop model organisms: models finetuned to exhibit specific known behaviors…

Word embedding has become a fundamental component to many NLP tasks such as named entity recognition and machine translation. However, popular models that learn such embeddings are unaware of the morphology of words, so it is not directly…

Tasks such as solving arithmetic equations, evaluating truth tables, and completing syllogisms are handled well by large language models (LLMs) in their standard form, but they often fail when the same problems are posed in logically…

Pretrained neural language models (LMs) are prone to generating racist, sexist, or otherwise toxic language which hinders their safe deployment. We investigate the extent to which pretrained LMs can be prompted to generate toxic language,…

The Open Ko-LLM Leaderboard has been instrumental in benchmarking Korean Large Language Models (LLMs), yet it has certain limitations. Notably, the disconnect between quantitative improvements on the overly academic leaderboard benchmarks…

Studies have shown that toxic behavior can cause contributors to leave, and hinder newcomers' (especially from underrepresented communities) participation in Open Source Software (OSS) projects. Thus, detection of toxic language plays a…

Lexical gaps are words that do not exist in certain languages. They pose challenges for building multilingual lexical resources, for machine translation, and for cross-lingual transfer. Existing lexical gap detection relies on human…

The application of large language models (LLMs) to chemistry is frequently hampered by a "tokenization bottleneck", where tokenizers tuned on general-domain text tend to fragment chemical representations such as SMILES into semantically…

Automatic detection of toxic language plays an essential role in protecting social media users, especially minority groups, from verbal abuse. However, biases toward some attributes, including gender, race, and dialect, exist in most…

Language Model pre-training uses broad data mixtures to enhance performance across domains and languages. However, training on such heterogeneous text corpora requires extensive and expensive efforts. Since these data sources vary…

Urdu toxic span detection remains limited because most existing systems rely on sentence-level classification and fail to identify the specific toxic spans within those text. It is further exacerbated by the multiple factors i.e. lack of…

In this work, we introduce our solution for the Multilingual Text Detoxification Task in the PAN-2025 competition for the ylmmcl team: a robust multilingual text detoxification pipeline that integrates lexicon-guided tagging, a fine-tuned…

Data cleaning is a crucial yet challenging task in data analysis, often requiring significant manual effort. To automate data cleaning, previous systems have relied on statistical rules derived from erroneous data, resulting in low accuracy…

Chatbots are robots that can communicate with humans using text or voice signals. Legal chatbots improve access to justice, since legal representation and legal advice by lawyers come with a high cost that excludes disadvantaged and…

The driving factors behind the development of large language models (LLMs) with impressive learning capabilities are their colossal model sizes and extensive training datasets. Along with the progress in natural language processing, LLMs…

Recently, large language models (LLMs) have shown strong potential in code generation tasks. However, there are still gaps before they can be fully applied in actual software development processes. Accurately assessing the code generation…

This paper investigates the underlying mechanisms of toxicity generation in Large Language Models (LLMs) and proposes an effective detoxification approach. Prior work typically considers the Feed-Forward Network (FFN) as the main source of…