English
Related papers

Related papers: Can Small-Scale Data Poisoning Exacerbate Dialect-…

200 papers

Style features such as friendly, helpful, or concise are widely used in prompts to steer the behavior of Large Language Model (LLM) conversational agents, yet their unintended side effects remain poorly understood. In this work, we present…

Computation and Language · Computer Science 2026-01-19 Young-Min Cho , Yuan Yuan , Sharath Chandra Guntuku , Lyle Ungar

Uses of pejorative expressions can be benign or actively empowering. When models for abuse detection misclassify these expressions as derogatory, they inadvertently censor productive conversations held by marginalized groups. One way to…

Computation and Language · Computer Science 2022-06-20 Jana Kurrek , Haji Mohammad Saleem , Derek Ruths

Large language models (LLMs) have been recently leveraged as training data generators for various natural language processing (NLP) tasks. While previous research has explored different approaches to training models using generated data,…

Computation and Language · Computer Science 2023-10-19 Yue Yu , Yuchen Zhuang , Jieyu Zhang , Yu Meng , Alexander Ratner , Ranjay Krishna , Jiaming Shen , Chao Zhang

Large language models (LLMs) have become integral to our professional workflows and daily lives. Nevertheless, these machine companions of ours have a critical flaw: the huge amount of data which endows them with vast and diverse knowledge,…

Computation and Language · Computer Science 2024-05-21 Tinh Son Luong , Thanh-Thien Le , Linh Ngo Van , Thien Huu Nguyen

Data contamination -- the accidental consumption of evaluation examples within the pre-training data -- can undermine the validity of evaluation benchmarks. In this paper, we present a rigorous analysis of the effects of contamination on…

Computation and Language · Computer Science 2025-02-03 Muhammed Yusuf Kocyigit , Eleftheria Briakou , Daniel Deutsch , Jiaming Luo , Colin Cherry , Markus Freitag

With the widespread availability of pretrained Large Language Models (LLMs) and their training datasets, concerns about the security risks associated with their usage has increased significantly. One of these security risks is the threat of…

Cryptography and Security · Computer Science 2025-06-10 Neil Fendley , Edward W. Staley , Joshua Carney , William Redman , Marie Chau , Nathan Drenkow

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

Large language models produce human-like text that drive a growing number of applications. However, recent literature and, increasingly, real world observations, have demonstrated that these models can generate language that is toxic,…

In-context learning, a paradigm bridging the gap between pre-training and fine-tuning, has demonstrated high efficacy in several NLP tasks, especially in few-shot settings. Despite being widely applied, in-context learning is vulnerable to…

Computation and Language · Computer Science 2024-10-10 Shuai Zhao , Meihuizi Jia , Luu Anh Tuan , Fengjun Pan , Jinming Wen

Recently efforts have been made by social media platforms as well as researchers to detect hateful or toxic language using large language models. However, none of these works aim to use explanation, additional context and victim community…

Computation and Language · Computer Science 2023-10-31 Sarthak Roy , Ashish Harshavardhan , Animesh Mukherjee , Punyajoy Saha

It's been said that "Language Models are Unsupervised Multitask Learners." Indeed, self-supervised language models trained on "positive" examples of English text generalize in desirable ways to many natural language tasks. But if such…

Computation and Language · Computer Science 2020-10-23 Michael L. Wick , Kate Silverstein , Jean-Baptiste Tristan , Adam Pocock , Mark Johnson

Multilingual studies of social bias in open-ended LLM generation remain limited: most existing benchmarks are English-centric, template-based, or restricted to recognizing pre-specified stereotypes. We introduce StereoTales, a multilingual…

Computers and Society · Computer Science 2026-05-13 Pierre Le Jeune , Étienne Duchesne , Weixuan Xiao , Stefano Palminteri , Bazire Houssin , Benoît Malézieux , Matteo Dora

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

Despite the remarkable performance of foundation vision-language models, the shared representation space for text and vision can also encode harmful label associations detrimental to fairness. While prior work has uncovered bias in…

Computer Vision and Pattern Recognition · Computer Science 2024-04-17 Caner Hazirbas , Alicia Sun , Yonathan Efroni , Mark Ibrahim

Detecting social bias in text is challenging due to nuance, subjectivity, and difficulty in obtaining good quality labeled datasets at scale, especially given the evolving nature of social biases and society. To address these challenges, we…

Computation and Language · Computer Science 2022-04-19 Shrimai Prabhumoye , Rafal Kocielnik , Mohammad Shoeybi , Anima Anandkumar , Bryan Catanzaro

Language models (LMs) must be both safe and equitable to be responsibly deployed in practice. With safety in mind, numerous detoxification techniques (e.g., Dathathri et al. 2020; Krause et al. 2020) have been proposed to mitigate toxic LM…

Computation and Language · Computer Science 2021-04-14 Albert Xu , Eshaan Pathak , Eric Wallace , Suchin Gururangan , Maarten Sap , Dan Klein

Modern language models remain vulnerable to backdoor attacks via poisoned data, where training inputs containing a trigger are paired with a target output, causing the model to reproduce that behavior whenever the trigger appears at…

Cryptography and Security · Computer Science 2026-01-06 Eric Xue , Ruiyi Zhang , Pengtao Xie

Neural approaches to ranking based on pre-trained language models are highly effective in ad-hoc search. However, the computational expense of these models can limit their application. As such, a process known as knowledge distillation is…

Information Retrieval · Computer Science 2024-11-05 Vishakha Suresh Kalal , Andrew Parry , Sean MacAvaney

Training-data poisoning attacks can induce targeted, undetectable failure in deep neural networks by corrupting a vanishingly small fraction of training labels. We demonstrate this on acoustic vehicle classification using the MELAUDIS urban…

Cryptography and Security · Computer Science 2026-02-27 Harrison Dahme

Causal learning is the cognitive process of developing the capability of making causal inferences based on available information, often guided by normative principles. This process is prone to errors and biases, such as the illusion of…