English
Related papers

Related papers: Detoxifying Language Models with a Toxic Corpus

200 papers

Large language models (LLMs) are increasingly popular but are also prone to generating bias, toxic or harmful language, which can have detrimental effects on individuals and communities. Although most efforts is put to assess and mitigate…

Computation and Language · Computer Science 2024-06-26 Caroline Brun , Vassilina Nikoulina

With the recent proliferation of the use of text classifications, researchers have found that there are certain unintended biases in text classification datasets. For example, texts containing some demographic identity-terms (e.g., "gay",…

Computation and Language · Computer Science 2020-08-21 Guanhua Zhang , Bing Bai , Junqi Zhang , Kun Bai , Conghui Zhu , Tiejun Zhao

Current large-scale auto-regressive language models display impressive fluency and can generate convincing text. In this work we start by asking the question: Can the generations of these models be reliably distinguished from real text by…

Computation and Language · Computer Science 2020-12-22 Anton Bakhtin , Yuntian Deng , Sam Gross , Myle Ott , Marc'Aurelio Ranzato , Arthur Szlam

Modern toxic speech detectors are incompetent in recognizing disguised offensive language, such as adversarial attacks that deliberately avoid known toxic lexicons, or manifestations of implicit bias. Building a large annotated dataset for…

Computation and Language · Computer Science 2020-10-08 Xiaochuang Han , Yulia Tsvetkov

Discriminatory language and biases are often present in hate speech during conversations, which usually lead to negative impacts on targeted groups such as those based on race, gender, and religion. To tackle this issue, we propose an…

Computation and Language · Computer Science 2023-07-21 Shaina Raza , Chen Ding , Deval Pandya

Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversity, or demographic…

Computation and Language · Computer Science 2025-03-13 Liu Yu , Ludie Guo , Ping Kuang , Fan Zhou

Text detoxification is a textual style transfer (TST) task where a text is paraphrased from a toxic surface form, e.g. featuring rude words, to the neutral register. Recently, text detoxification methods found their applications in various…

Computation and Language · Computer Science 2024-04-03 Daryna Dementieva , Nikolay Babakov , Alexander Panchenko

Existing approaches for Large language model (LLM) detoxification generally rely on training on large-scale non-toxic or human-annotated preference data, designing prompts to instruct the LLM to generate safe content, or modifying the model…

Computation and Language · Computer Science 2025-06-03 Yuanhe Tian , Mingjie Deng , Guoqing Jin , Yan Song

Large Language Models (LLMs) have demonstrated a powerful ability for text generation. However, achieving optimal results with a given prompt or instruction can be challenging, especially for billion-sized models. Additionally, undesired…

Computation and Language · Computer Science 2024-10-07 Lifu Tu , Semih Yavuz , Jin Qu , Jiacheng Xu , Rui Meng , Caiming Xiong , Yingbo Zhou

The use of abusive language online has become an increasingly pervasive problem that damages both individuals and society, with effects ranging from psychological harm right through to escalation to real-life violence and even death.…

Computation and Language · Computer Science 2023-09-26 Mali Jin , Yida Mu , Diana Maynard , Kalina Bontcheva

Large language models (LLMs) aligned for safety often suffer from over-refusal, the tendency to reject seemingly toxic or benign prompts by misclassifying them as toxic. This behavior undermines models' helpfulness and restricts usability…

Computation and Language · Computer Science 2026-03-05 Yuxiao Lu , Lin Xu , Yang Sun , Wenjun Li , Jie Shi

Dehumanization is a mental process that enables the exclusion and ill treatment of a group of people. In this paper, we present two data sets of dehumanizing text, a large, automatically collected corpus and a smaller, manually annotated…

Computation and Language · Computer Science 2024-02-15 Paul Engelmann , Peter Brunsgaard Trolle , Christian Hardmeier

Recently, more and more research has focused on addressing bias in text classification models. However, existing research mainly focuses on the fairness of monolingual text classification models, and research on fairness for multilingual…

Computation and Language · Computer Science 2023-03-29 Nankai Lin , Junheng He , Zhenghang Tang , Dong Zhou , Aimin Yang

Legacy procedures for topic modelling have generally suffered problems of overfitting and a weakness towards reconstructing sparse topic structures. With motivation from a consumer-generated corpora, this paper proposes semiparametric topic…

Computation and Language · Computer Science 2025-03-05 Dominic B. Dayta , Erniel B. Barrios

Recently, high-performing code generation systems based on large language models have surfaced. They are trained on massive corpora containing much more natural text than actual executable computer code. This work shows that current code…

Artificial Intelligence · Computer Science 2023-05-10 Spyridon Mouselinos , Mateusz Malinowski , Henryk Michalewski

Deep-learning models for language generation tasks tend to produce repetitive output. Various methods have been proposed to encourage lexical diversity during decoding, but this often comes at a cost to the perceived fluency and adequacy of…

Computation and Language · Computer Science 2021-09-22 Giulio Zhou , Gerasimos Lampouras

Several recent studies have shown that strong natural language understanding (NLU) models are prone to relying on unwanted dataset biases without learning the underlying task, resulting in models that fail to generalize to out-of-domain…

Computation and Language · Computer Science 2020-04-27 Rabeeh Karimi Mahabadi , Yonatan Belinkov , James Henderson

Large language models (LLMs) are trained on huge amounts of textual data, and concerns have been raised that the limits of such data may soon be reached. A potential solution is to train on synthetic data sampled from LLMs. In this work, we…

Computation and Language · Computer Science 2025-10-10 Jannek Ulm , Kevin Du , Vésteinn Snæbjarnarson

It is well known that textual data on the internet and other digital platforms contain significant levels of bias and stereotypes. Although many such texts contain stereotypes and biases that inherently exist in natural language for reasons…

Computation and Language · Computer Science 2022-01-24 Ewoenam Kwaku Tokpo , Toon Calders

Topic modeling has emerged as a dominant method for exploring large document collections. Recent approaches to topic modeling use large contextualized language models and variational autoencoders. In this paper, we propose a negative…

Computation and Language · Computer Science 2023-03-28 Suman Adhya , Avishek Lahiri , Debarshi Kumar Sanyal , Partha Pratim Das
‹ Prev 1 4 5 6 7 8 10 Next ›