English
Related papers

Related papers: How Quantization Shapes Bias in Large Language Mod…

200 papers

With the rapid increase in the size of neural networks, model compression has become an important area of research. Quantization is an effective technique at decreasing the model size, memory access, and compute load of large models.…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-26 David Qiu , David Rim , Shaojin Ding , Oleg Rybakov , Yanzhang He

Quantization has emerged as an essential technique for deploying deep neural networks (DNNs) on devices with limited resources. However, quantized models exhibit vulnerabilities when exposed to various noises in real-world applications.…

Machine Learning · Computer Science 2023-04-11 Yisong Xiao , Tianyuan Zhang , Shunchang Liu , Haotong Qin

Large Language Models (LLMs) have made substantial progress in the past several months, shattering state-of-the-art benchmarks in many domains. This paper investigates LLMs' behavior with respect to gender stereotypes, a known issue for…

Computation and Language · Computer Science 2023-08-30 Hadas Kotek , Rikker Dockum , David Q. Sun

Authorship attribution techniques are increasingly being used in online contexts such as sock puppet detection, malicious account linking, and cross-platform account linking. Yet, it is unknown whether these models perform equitably across…

Social and Information Networks · Computer Science 2025-10-23 Jasmin Wyss , Rebekah Overdorf

Large language models (LLMs) are widely applied across diverse domains, raising concerns about their limitations and potential risks. In this study, we investigate two types of bias that LLMs may display: stereotype bias and deviation bias.…

Computation and Language · Computer Science 2026-05-20 Daniel Wang , Eli Brignac , Minjia Mao , Xiao Fang

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,…

Tokenizers provide the fundamental basis through which text is represented and processed by language models (LMs). Despite the importance of tokenization, its role in LM performance and behavior is poorly understood due to the challenge of…

Computation and Language · Computer Science 2025-12-25 Gül Sena Altıntaş , Malikeh Ehghaghi , Brian Lester , Fengyuan Liu , Wanru Zhao , Marco Ciccone , Colin Raffel

With the ever-increasing cases of hate spread on social media platforms, it is critical to design abuse detection mechanisms to proactively avoid and control such incidents. While there exist methods for hate speech detection, they…

Computation and Language · Computer Science 2020-01-17 Pinkesh Badjatiya , Manish Gupta , Vasudeva Varma

Tokenization and transfer learning are two critical components in building state of the art time series foundation models for forecasting. In this work, we systematically study the effect of tokenizer design, specifically scaling and…

Machine Learning · Computer Science 2025-11-18 Alexis Roger , Gwen Legate , Kashif Rasul , Yuriy Nevmyvaka , Irina Rish

Large language models are increasingly used for creative writing and engagement content, raising safety concerns about the outputs. Therefore, casting humor generation as a testbed, this work evaluates how funniness optimization in modern…

Computation and Language · Computer Science 2025-10-22 Atharvan Dogra , Soumya Suvra Ghosal , Ameet Deshpande , Ashwin Kalyan , Dinesh Manocha

Transformer-based Large Language Models (LLMs) have revolutionized Natural Language Processing by demonstrating exceptional performance across diverse tasks. This study investigates the impact of the parameter initialization scale on the…

Computation and Language · Computer Science 2025-05-22 Junjie Yao , Zhongwang Zhang , Zhi-Qin John Xu

Pre-trained language models trained on large-scale data have learned serious levels of social biases. Consequently, various methods have been proposed to debias pre-trained models. Debiasing methods need to mitigate only discriminatory bias…

Computation and Language · Computer Science 2023-09-19 Masahiro Kaneko , Danushka Bollegala , Naoaki Okazaki

World models learn an internal representation of environment dynamics, enabling agents to simulate and reason about future states within a compact latent space for tasks such as planning, prediction, and inference. However, running world…

Machine Learning · Computer Science 2026-02-03 Zhongqian Fu , Tianyi Zhao , Kai Han , Hang Zhou , Xinghao Chen , Yunhe Wang

Language Models have ushered a new age of AI gaining traction within the NLP community as well as amongst the general population. AI's ability to make predictions, generations and its applications in sensitive decision-making scenarios,…

Computation and Language · Computer Science 2023-11-28 Ananya Malik

Recent generative large language models (LLMs) show remarkable performance in non-English languages, but when prompted in those languages they tend to express higher harmful social biases and toxicity levels. Prior work has shown that…

Computation and Language · Computer Science 2025-06-03 Vera Neplenbroek , Arianna Bisazza , Raquel Fernández

LLMs are increasingly powerful and widely used to assist users in a variety of tasks. This use risks the introduction of LLM biases to consequential decisions such as job hiring, human performance evaluation, and criminal sentencing. Bias…

Computation and Language · Computer Science 2024-06-21 Mahammed Kamruzzaman , Md. Minul Islam Shovon , Gene Louis Kim

Most machine learning methods are known to capture and exploit biases of the training data. While some biases are beneficial for learning, others are harmful. Specifically, image captioning models tend to exaggerate biases present in…

Computer Vision and Pattern Recognition · Computer Science 2019-03-15 Kaylee Burns , Lisa Anne Hendricks , Kate Saenko , Trevor Darrell , Anna Rohrbach

Large Language Models increasingly suppress biased outputs when demographic identity is stated explicitly, yet may still exhibit implicit biases when identity is conveyed indirectly. Existing benchmarks use name based proxies to detect…

Computation and Language · Computer Science 2026-04-03 Bhaskara Hanuma Vedula , Darshan Anghan , Ishita Goyal , Ponnurangam Kumaraguru , Abhijnan Chakraborty

Mitigating bias in training on biased datasets is an important open problem. Several techniques have been proposed, however the typical evaluation regime is very limited, considering very narrow data conditions. For instance, the effect of…

Machine Learning · Computer Science 2022-10-18 Xudong Han , Aili Shen , Trevor Cohn , Timothy Baldwin , Lea Frermann

This paper investigates contextual word representation models from the lens of similarity analysis. Given a collection of trained models, we measure the similarity of their internal representations and attention. Critically, these models…

Computation and Language · Computer Science 2020-05-05 John M. Wu , Yonatan Belinkov , Hassan Sajjad , Nadir Durrani , Fahim Dalvi , James Glass