English
Related papers

Related papers: Leashing the Inner Demons: Self-Detoxification for…

200 papers

The increasing use of large language models (LLMs) trained by third parties raises significant security concerns. In particular, malicious actors can introduce backdoors through poisoning attacks to generate undesirable outputs. While such…

Cryptography and Security · Computer Science 2024-07-19 Shuli Jiang , Swanand Ravindra Kadhe , Yi Zhou , Farhan Ahmed , Ling Cai , Nathalie Baracaldo

Large language models (LLMs) are becoming increasingly capable, but the mechanisms of their thinking and decision-making processes remain unclear. Chain-of-thoughts (CoTs) have been commonly utilized to externalize LLMs' thinking, but this…

Computation and Language · Computer Science 2026-05-28 Guanxu Chen , Jing Shao , Tao Luo , Lijie Hu , Qihao Lin , Dongrui Liu

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

Recent advancements in Large Language Models (LLMs) have significantly enhanced their code generation capabilities. However, their robustness against adversarial misuse, particularly through multi-turn malicious coding prompts, remains…

Computation and Language · Computer Science 2025-07-29 Muntasir Wahed , Xiaona Zhou , Kiet A. Nguyen , Tianjiao Yu , Nirav Diwan , Gang Wang , Dilek Hakkani-Tür , Ismini Lourentzou

Benchmark-based evaluation is the de facto standard for comparing large language models (LLMs). However, its reliability is increasingly threatened by test set contamination, where test samples or their close variants leak into training…

Computation and Language · Computer Science 2026-01-28 Jianzhe Chai , Yu Zhe , Jun Sakuma

Fine-tuning-based unlearning methods prevail for preventing targeted harmful, sensitive, or copyrighted information within large language models while preserving overall capabilities. However, the true effectiveness of these methods is…

Computation and Language · Computer Science 2024-10-16 Yihuai Hong , Yuelin Zou , Lijie Hu , Ziqian Zeng , Di Wang , Haiqin Yang

This paper investigates the propagation of harmful information in multilingual large language models (LLMs) and evaluates the efficacy of various unlearning methods. We demonstrate that fake information, regardless of the language it is in,…

Computation and Language · Computer Science 2025-09-04 Taiming Lu , Philipp Koehn

In large language model (LLM) pretraining, data quality is believed to determine model quality. In this paper, we re-examine the notion of "quality" from the perspective of pre- and post-training co-design. Specifically, we explore the…

Machine Learning · Computer Science 2025-05-09 Kenneth Li , Yida Chen , Fernanda Viégas , Martin Wattenberg

We explore the ability of large language models (LLMs) to engage in subtle deception through strategically phrasing and intentionally manipulating information. This harmful behavior can be hard to detect, unlike blatant lying or…

Computation and Language · Computer Science 2025-10-02 Atharvan Dogra , Krishna Pillutla , Ameet Deshpande , Ananya B Sai , John Nay , Tanmay Rajpurohit , Ashwin Kalyan , Balaraman Ravindran

Large language models (LLMs) have achieved remarkable advancements in natural language processing. However, the massive scale and computational demands of these models present formidable challenges when considering their practical…

Computation and Language · Computer Science 2024-04-09 Weize Liu , Guocong Li , Kai Zhang , Bang Du , Qiyuan Chen , Xuming Hu , Hongxia Xu , Jintai Chen , Jian Wu

The wave of pre-training language models has been continuously improving the quality of the machine-generated conversations, however, some of the generated responses still suffer from excessive repetition, sometimes repeating words from…

Computation and Language · Computer Science 2021-12-17 Yadong Xi , Jiashu Pu , Xiaoxi Mao

Transformer-based Large Language Models (LLMs) have shown exceptional language generation capabilities in response to text-based prompts. However, controlling the direction of generation via textual prompts has been challenging, especially…

Computation and Language · Computer Science 2024-04-09 Rohan Deepak Ajwani , Zining Zhu , Jonathan Rose , Frank Rudzicz

Many social science questions ask how linguistic properties causally affect an audience's attitudes and behaviors. Because text properties are often interlinked (e.g., angry reviews use profane language), we must control for possible latent…

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

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…

Computation and Language · Computer Science 2023-11-27 Daryna Dementieva , Daniil Moskovskiy , David Dale , Alexander Panchenko

Large Language Models (LLMs) are capable of producing content that perpetuates stereotypes, discrimination, and toxicity. The recently proposed moral self-correction is a computationally efficient method for reducing harmful content in the…

Computation and Language · Computer Science 2024-10-10 Guangliang Liu , Haitao Mao , Jiliang Tang , Kristen Marie Johnson

Denoising language models (DLMs) have been proposed as a powerful alternative to traditional language models (LMs) for automatic speech recognition (ASR), motivated by their ability to use bidirectional context and adapt to a specific ASR…

Neural and Evolutionary Computing · Computer Science 2025-12-16 Dorian Koch , Albert Zeyer , Nick Rossenbach , Ralf Schlüter , Hermann Ney

Language models (LMs) have introduced a major paradigm shift in Natural Language Processing (NLP) modeling where large pre-trained LMs became integral to most of the NLP tasks. The LMs are intelligent enough to find useful and relevant…

Computation and Language · Computer Science 2023-05-09 Abbas Raza Ali , Muhammad Ajmal Siddiqui , Rema Algunaibet , Hasan Raza Ali

Hate speech is a harmful form of online expression, often manifesting as derogatory posts. It is a significant risk in digital environments. With the rise of Large Language Models (LLMs), there is concern about their potential to replicate…

Computation and Language · Computer Science 2025-06-10 Paloma Piot , Javier Parapar

Large Language Models (LLMs) are being enhanced with the ability to use tools and to process multiple modalities. These new capabilities bring new benefits and also new security risks. In this work, we show that an attacker can use visual…

Cryptography and Security · Computer Science 2023-10-06 Xiaohan Fu , Zihan Wang , Shuheng Li , Rajesh K. Gupta , Niloofar Mireshghallah , Taylor Berg-Kirkpatrick , Earlence Fernandes