English
Related papers

Related papers: Challenges in Detoxifying Language Models

200 papers

Transformer-based Language Models (LMs) have achieved impressive results on natural language understanding tasks, but they can also generate toxic text such as insults, threats, and profanity, limiting their real-world applications. To…

Computation and Language · Computer Science 2023-07-06 Jin Myung Kwak , Minseon Kim , Sung Ju Hwang

Recent advancements in Large Language Models (LLMs), such as ChatGPT and LLaMA, have significantly transformed Natural Language Processing (NLP) with their outstanding abilities in text generation, summarization, and classification.…

Computation and Language · Computer Science 2024-08-12 Md Nazmus Sakib , Md Athikul Islam , Royal Pathak , Md Mashrur Arifin

Automatic evaluation is an integral aspect of dialogue system research. The traditional reference-based NLG metrics are generally found to be unsuitable for dialogue assessment. Consequently, recent studies have suggested various unique,…

Computation and Language · Computer Science 2024-01-23 Chen Zhang , Luis Fernando D'Haro , Yiming Chen , Malu Zhang , Haizhou Li

Large Language Models (LLMs) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using human feedback. While alignment has become an essential training…

Computation and Language · Computer Science 2024-09-04 Bocheng Chen , Hanqing Guo , Guangjing Wang , Yuanda Wang , Qiben Yan

In this position paper, we argue that the classical evaluation on Natural Language Processing (NLP) tasks using annotated benchmarks is in trouble. The worst kind of data contamination happens when a Large Language Model (LLM) is trained on…

Computation and Language · Computer Science 2023-10-30 Oscar Sainz , Jon Ander Campos , Iker García-Ferrero , Julen Etxaniz , Oier Lopez de Lacalle , Eneko Agirre

Evidence-enhanced detectors present remarkable abilities in identifying malicious social text. However, the rise of large language models (LLMs) brings potential risks of evidence pollution to confuse detectors. This paper explores…

Computation and Language · Computer Science 2025-05-30 Herun Wan , Minnan Luo , Zhixiong Su , Guang Dai , Xiang Zhao

Large language models (LLM) have revolutionized the processing of natural language. Although first benchmarks of the process modeling abilities of LLM are promising, it is currently under debate to what extent an LLM can generate good…

Computation and Language · Computer Science 2025-03-19 Peter Fettke , Constantin Houy

Machine learning models for text classification are trained to predict a class for a given text. To do this, training and validation samples must be prepared: a set of texts is collected, and each text is assigned a class. These classes are…

Computation and Language · Computer Science 2025-08-26 Aleksandr Tsymbalov , Mikhail Khovrichev

The exponential growth of text-based data in domains such as healthcare, education, and social sciences has outpaced the capacity of traditional qualitative analysis methods, which are time-intensive and prone to subjectivity. Large…

Large Language Models have demonstrated impressive fluency across diverse tasks, yet their tendency to produce toxic content remains a critical challenge for AI safety and public trust. Existing toxicity mitigation approaches primarily…

Computation and Language · Computer Science 2025-09-23 Zuhair Hasan Shaik , Abdullah Mazhar , Aseem Srivastava , Md Shad Akhtar

Large language models (LLMs) excel across diverse natural language processing tasks but face resource demands and limited context windows. Although techniques like pruning, quantization, and token dropping can mitigate these issues, their…

Computation and Language · Computer Science 2025-08-04 Ammar Ahmed , Sheng Di , Franck Cappello , Zirui Liu , Jingoo Han , Ali Anwar

Recent research has highlighted that assigning specific personas to large language models (LLMs) can significantly increase harmful content generation. However, limited attention has been given to persona-driven toxicity in non-Western…

Computers and Society · Computer Science 2026-05-28 Geng Liu , Li Feng , Carlo Alberto Bono , Songbo Yang , Mengxiao Zhu , Francesco Pierri

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

Reducing the likelihood of generating harmful and toxic output is an essential task when aligning large language models (LLMs). Existing methods mainly rely on training an external reward model (i.e., another language model) or fine-tuning…

While large language models (LLMs) present significant potential for supporting numerous real-world applications and delivering positive social impacts, they still face significant challenges in terms of the inherent risk of privacy…

Artificial Intelligence · Computer Science 2025-01-17 Huandong Wang , Wenjie Fu , Yingzhou Tang , Zhilong Chen , Yuxi Huang , Jinghua Piao , Chen Gao , Fengli Xu , Tao Jiang , Yong Li

Large language models (LLMs) are beginning to reshape how chemists plan and run reactions in organic synthesis. Trained on millions of reported transformations, these text-based models can propose synthetic routes, forecast reaction…

Artificial Intelligence · Computer Science 2025-08-08 Kartar Kumar Lohana Tharwani , Rajesh Kumar , Sumita , Numan Ahmed , Yong Tang

Growing applications of large language models (LLMs) trained by a third party raise serious concerns on the security vulnerability of LLMs.It has been demonstrated that malicious actors can covertly exploit these vulnerabilities in LLMs…

Cryptography and Security · Computer Science 2023-12-11 Shuli Jiang , Swanand Ravindra Kadhe , Yi Zhou , Ling Cai , Nathalie Baracaldo

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…

Machine Learning · Computer Science 2025-07-08 Jing Yu , Yibo Zhao , Jiapeng Zhu , Wenming Shao , Bo Pang , Zhao Zhang , Xiang Li

Large Language Models (LLMs) can generate content that is as persuasive as human-written text and appear capable of selectively producing deceptive outputs. These capabilities raise concerns about potential misuse and unintended…

Computation and Language · Computer Science 2024-12-24 Cameron R. Jones , Benjamin K. Bergen

Large language models pretrained on extensive web corpora demonstrate remarkable performance across a wide range of downstream tasks. However, a growing concern is data contamination, where evaluation datasets may be contained in the…

Computation and Language · Computer Science 2024-07-12 Medha Palavalli , Amanda Bertsch , Matthew R. Gormley