The Disparate Impacts of Speculative Decoding

Fairness in large language models: A taxonomic survey

Zhibo Chu, Zichong Wang, and Wenbin Zhang · 1931

Earlier work this paper cites.

Nltk: The natural language toolkit, 2002

Edward Loper and Steven Bird · 2002

Earlier work this paper cites.

BLEU: a method for automatic evaluation of machine translation

Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu · 2002

Earlier work this paper cites.

Quantifying social biases in NLP: A generalization and empirical comparison of extrinsic fairness metrics

Paula Czarnowska, Yogarshi Vyas, and Kashif Shah · 2021

Earlier work this paper cites.

BOLD: dataset and metrics for measuring biases in open-ended language generation

Jwala Dhamala, Tony Sun, Varun Kumar, Satyapriya Krishna, Yada Pruksachatkun, Kai-Wei Chang, and Rahul Gupta · 2021

Earlier work this paper cites.

Measuring fairness with biased rulers: A comparative study on bias metrics for pre-trained language models

Pieter Delobelle, Ewoenam Kwaku Tokpo, Toon Calders, and Bettina Berendt · 2022

Earlier work this paper cites.

Upstream mitigation is not all you need: Testing the bias transfer hypothesis in pre-trained language models

Ryan Steed, Swetasudha Panda, Ari Kobren, and Michael L. Wick · 2022

Earlier work this paper cites.

Bias and fairness in large language models: A survey

Original

Isabel O. Gallegos, Ryan A. Rossi, Joe Barrow, Md. Mehrab Tanjim, Sungchul Kim, Franck Dernoncourt, Tong Yu, Ruiyi Zhang, and Nesreen K. Ahmed · 2023

Earlier work this paper cites.

Parameter-efficient modularised bias mitigation via adapterfusion

Deepak Kumar, Oleg Lesota, George Zerveas, Daniel Cohen, Carsten Eickhoff, Markus Schedl, and Navid Rekabsaz · 2023

Cited alongside, same era.

Fast inference from transformers via speculative decoding

Yaniv Leviathan, Matan Kalman, and Yossi Matias · 2023

Cited alongside, same era.

Social-group-agnostic bias mitigation via the stereotype content model

Ali Omrani, Alireza Salkhordeh Ziabari, Charles Yu, Preni Golazizian, Brendan Kennedy, Mohammad Atari, Heng Ji, and Morteza Dehghani · 2023

Cited alongside, same era.

Language model tokenizers introduce unfairness between languages

Aleksandar Petrov, Emanuele La Malfa, Philip H. S. Torr, and Adel Bibi · 2023

Cited alongside, same era.

Improving speculative decoding via knowledge distillation

Original

Yongchao Zhou, Kaifeng Lyu, Ankit Singh Rawat, Aditya Krishna Menon, Afshin Rostamizadeh, Sanjiv Kumar, Jean-François Kagy, and Rishabh Agarwal · 2023

Cited alongside, same era.

Critical phase transition in large language models, 2024

Original

Kai Nakaishi, Yoshihiko Nishikawa, and Koji Hukushima · 2024

Later among the works it cites.

Aya dataset: An open-access collection for multilingual instruction tuning

Shivalika Singh, Freddie Vargus, Daniel D-souza, Börje Karlsson, Abinaya Mahendiran, Wei-Yin Ko, Herumb Shandilya, Jay Patel, Deividas Mataciunas, Laura O-Mahony, Mike Zhang, Ramith Hettiarachchi, Joseph Wilson, Marina Machado, Luisa Souza Moura, Dominik Krzemiński, Hakimeh Fadaei, Irem Ergün, Ifeoma Okoh, Aisha Alaagib, Oshan Mudannayake, Zaid Alyafeai, Vu Chien, Sebastian Ruder, Surya Guthikonda, Emad Alghamdi, Sebastian Gehrmann, Niklas Muennighoff, Max Bartolo, Julia Kreutzer, Ahmet Üstün, Marzieh Fadaee, and Sara Hooker · 2024

Later among the works it cites.

Towards fast multilingual LLM inference: Speculative decoding and specialized drafters

Euiin Yi, Taehyeon Kim, Hongseok Jeung, Du-Seong Chang, and Se-Young Yun · 2024

Later among the works it cites.

Multilingual dolly-200 qa evaluation set

Ahmet Üstün, Shivalika Singh, Sara Hooker, and Cohere For AI Contributors · 2024

Later among the works it cites.

LLM Japanese Dataset: Wikinews Subset