English
Related papers

Related papers: Parameter-Efficient Detoxification with Contrastiv…

200 papers

Large pre-trained language models are often trained on large volumes of internet data, some of which may contain toxic or abusive language. Consequently, language models encode toxic information, which makes the real-world usage of these…

Computation and Language · Computer Science 2021-12-16 Andrew Wang , Mohit Sudhakar , Yangfeng Ji

Existing text generation methods tend to produce repeated and "boring" expressions. To tackle this problem, we propose a new text generation model, called Diversity-Promoting Generative Adversarial Network (DP-GAN). The proposed model…

Computation and Language · Computer Science 2018-08-22 Jingjing Xu , Xuancheng Ren , Junyang Lin , Xu Sun

Due to language models' propensity to generate toxic or hateful responses, several techniques were developed to align model generations with users' preferences. Despite the effectiveness of such methods in improving the safety of model…

Computation and Language · Computer Science 2023-09-06 Daniel Scalena , Gabriele Sarti , Malvina Nissim , Elisabetta Fersini

Warning: this paper includes model outputs showing offensive content. Recent large-scale Visual-Language Generative Models (VLGMs) have achieved unprecedented improvement in multimodal image/text generation. However, these models might also…

Computation and Language · Computer Science 2023-12-20 Xinpeng Wang , Xiaoyuan Yi , Han Jiang , Shanlin Zhou , Zhihua Wei , Xing Xie

Controlled text generation is a very important task in the arena of natural language processing due to its promising applications. In order to achieve this task we mainly introduce the novel soft prompt tuning method of using soft prompts…

Computation and Language · Computer Science 2022-12-07 Damith Chamalke Senadeera , Julia Ive

Decoding from the output distributions of large language models to produce high-quality text is a complex challenge in language modeling. Various approaches, such as beam search, sampling with temperature, $k-$sampling, nucleus…

Computation and Language · Computer Science 2024-10-22 Esteban Garces Arias , Julian Rodemann , Meimingwei Li , Christian Heumann , Matthias Aßenmacher

While large language models (LLMs) have achieved impressive performance in generating fluent and realistic text, controlling the generated text so that it exhibits properties such as safety, factuality, and non-toxicity remains challenging.…

Computation and Language · Computer Science 2023-11-10 Meng Cao , Mehdi Fatemi , Jackie Chi Kit Cheung , Samira Shabanian

As large-scale language model pretraining pushes the state-of-the-art in text generation, recent work has turned to controlling attributes of the text such models generate. While modifying the pretrained models via fine-tuning remains the…

Computation and Language · Computer Science 2021-08-05 Sachin Kumar , Eric Malmi , Aliaksei Severyn , Yulia Tsvetkov

We propose a novel lightweight generative adversarial network for efficient image manipulation using natural language descriptions. To achieve this, a new word-level discriminator is proposed, which provides the generator with fine-grained…

Computer Vision and Pattern Recognition · Computer Science 2020-10-26 Bowen Li , Xiaojuan Qi , Philip H. S. Torr , Thomas Lukasiewicz

Recently, generative retrieval emerges as a promising alternative to traditional retrieval paradigms. It assigns each document a unique identifier, known as DocID, and employs a generative model to directly generate the relevant DocID for…

Information Retrieval · Computer Science 2024-04-16 Peitian Zhang , Zheng Liu , Yujia Zhou , Zhicheng Dou , Fangchao Liu , Zhao Cao

We present UniDetox, a universally applicable method designed to mitigate toxicity across various large language models (LLMs). Previous detoxification methods are typically model-specific, addressing only individual models or model…

Computation and Language · Computer Science 2025-04-30 Huimin Lu , Masaru Isonuma , Junichiro Mori , Ichiro Sakata

Accurately controlling object count in text-to-image generation remains a key challenge. Supervised methods often fail, as training data rarely covers all count variations. Methods that manipulate the denoising process to add or remove…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Oz Zafar , Yuval Cohen , Lior Wolf , Idan Schwartz

This study focused on efficient text generation using generative adversarial networks (GAN). Assuming that the goal is to generate a paragraph of a user-defined topic and sentimental tendency, conventionally the whole network has to be…

Computation and Language · Computer Science 2020-06-23 Chenhan Yuan , Yi-chin Huang , Cheng-Hung Tsai

Toxic content detection aims to identify content that can offend or harm its recipients. Automated classifiers of toxic content need to be robust against adversaries who deliberately try to bypass filters. We propose a method of generating…

Computation and Language · Computer Science 2019-12-17 Keita Kurita , Anna Belova , Antonios Anastasopoulos

We introduce a language generative model framework for generating a styled paragraph based on a context sentence and a style reference example. The framework consists of a style encoder and a texts decoder. The style encoder extracts a…

Computation and Language · Computer Science 2020-03-03 Kuo-Hao Zeng , Mohammad Shoeybi , Ming-Yu Liu

Prior works about text-to-image synthesis typically concatenated the sentence embedding with the noise vector, while the sentence embedding and the noise vector are two different factors, which control the different aspects of the…

Multimedia · Computer Science 2023-03-27 Jiguo Li , Xiaobin Liu , Lirong Zheng

We design, implement, and evaluate adversarial decoding, a new, generic text generation technique that produces readable documents for different adversarial objectives. Prior methods either produce easily detectable gibberish, or cannot…

Computation and Language · Computer Science 2025-03-07 Collin Zhang , Tingwei Zhang , Vitaly Shmatikov

With adversarial or otherwise normal prompts, existing large language models (LLM) can be pushed to generate toxic discourses. One way to reduce the risk of LLMs generating undesired discourses is to alter the training of the LLM. This can…

Computation and Language · Computer Science 2023-02-28 Meng Cao , Mehdi Fatemi , Jackie Chi Kit Cheung , Samira Shabanian

Text detoxification is a style transfer task of creating neutral versions of toxic texts. In this paper, we use the concept of text editing to build a two-step tagging-based detoxification model using a parallel corpus of Russian texts.…

Computation and Language · Computer Science 2022-06-10 Ilya Gusev

Detoxification in large language models (LLMs) remains a significant research challenge. Existing decoding detoxification methods are all based on external constraints, which require additional resource overhead and lose generation fluency.…

Computation and Language · Computer Science 2025-10-16 Ming Dong , Jinkui Zhang , Bolong Zheng , Xinhui Tu , Po Hu , Tingting He