Model Merging and Safety Alignment: One Bad Model Spoils the Bunch

Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (cma-es)

Nikolaus Hansen, Sibylle D Müller, and Petros Koumoutsakos. 2003 · 2003

Earlier work this paper cites.

Sampling generative networks

Original

Tom White. 2016 · 2016

Earlier work this paper cites.

Think you have solved question answering? try ARC, the AI2 Reasoning Challenge

Original

Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal, Carissa Schoenick, and Oyvind Tafjord. 2018 · 2018

Earlier work this paper cites.

Pubmedqa: A dataset for biomedical research question answering

Qiao Jin, Bhuwan Dhingra, Zhengping Liu, William Cohen, and Xinghua Lu. 2019 · 2019

Earlier work this paper cites.

Aligning ai with shared human values

Dan Hendrycks, Collin Burns, Steven Basart, Andrew Critch, Jerry Li, Dawn Song, and Jacob Steinhardt. 2020 · 2020

Earlier work this paper cites.

Measuring massive multitask language understanding

Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021 · 2021

Earlier work this paper cites.

What disease does this patient have? a large-scale open domain question answering dataset from medical exams

Di Jin, Eileen Pan, Nassim Oufattole, Wei-Hung Weng, Hanyi Fang, and Peter Szolovits. 2021 · 2021

Earlier work this paper cites.

Winogrande: An adversarial winograd schema challenge at scale

Keisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, and Yejin Choi. 2021 · 2021

Earlier work this paper cites.

Merging models with fisher-weighted averaging

Michael S Matena and Colin A Raffel. 2022 · 2022

Earlier work this paper cites.

Training language models to follow instructions with human feedback

Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022 · 2022

Earlier work this paper cites.

Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering

Ankit Pal, Logesh Kumar Umapathi, and Malaikannan Sankarasubbu. 2022 · 2022

Earlier work this paper cites.

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Mitchell Wortsman, Gabriel Ilharco, Samir Ya Gadre, Rebecca Roelofs, Raphael Gontijo-Lopes, Ari S Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, et al. 2022 · 2022

Earlier work this paper cites.

Llemma: An open language model for mathematics

Zhangir Azerbayev, Hailey Schoelkopf, Keiran Paster, Marco Dos Santos, Stephen Marcus McAleer, Albert Q Jiang, Jia Deng, Stella Biderman, and Sean Welleck. 2023 · 2023

Earlier work this paper cites.

Sparks of artificial general intelligence: Early experiments with gpt-4

Original

Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, et al. 2023 · 2023

Earlier work this paper cites.

Model breadcrumbs: Scaling multi-task model merging with sparse masks

Original

MohammadReza Davari and Eugene Belilovsky. 2023 · 2023

Earlier work this paper cites.

A framework for few-shot language model evaluation

Leo Gao, Jonathan Tow, Baber Abbasi, Stella Biderman, Sid Black, Anthony DiPofi, Charles Foster, Laurence Golding, Jeffrey Hsu, Alain Le Noac’h, Haonan Li, Kyle McDonell, Niklas Muennighoff, Chris Ociepa, Jason Phang, Laria Reynolds, Hailey Schoelkopf, Aviya Skowron, Lintang Sutawika, Eric Tang, Anish Thite, Ben Wang, Kevin Wang, and Andy Zou. 2023 · 2023

Earlier work this paper cites.

Trustgpt: A benchmark for trustworthy and responsible large language models

Original

Yue Huang, Qihui Zhang, Lichao Sun, et al. 2023 · 2023

Earlier work this paper cites.

Editing models with task arithmetic

Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, Suchin Gururangan, Ludwig Schmidt, Hannaneh Hajishirzi, and Ali Farhadi. 2023 · 2023

Cited alongside, same era.

Llama guard: Llm-based input-output safeguard for human-ai conversations

Original

Hakan Inan, Kartikeya Upasani, Jianfeng Chi, Rashi Rungta, Krithika Iyer, Yuning Mao, Michael Tontchev, Qing Hu, Brian Fuller, Davide Testuggine, et al. 2023 · 2023

Cited alongside, same era.

Mistral 7b

Original

Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023 · 2023

Cited alongside, same era.

Dataless knowledge fusion by merging weights of language models

Xisen Jin, Xiang Ren, Daniel Preotiuc-Pietro, and Pengxiang Cheng. 2023 · 2023

Cited alongside, same era.

Wizardmath: Empowering mathematical reasoning for large language models via reinforced evol-instruct

Beyond imitation: Leveraging fine-grained quality signals for alignment

Geyang Guo, Ranchi Zhao, Tianyi Tang, Xin Zhao, and Ji-Rong Wen. 2024 · 2024

Closest in time.

Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks

Samyak Jain, Robert Kirk, Ekdeep Singh Lubana, Robert P. Dick, Hidenori Tanaka, Tim Rocktäschel, Edward Grefenstette, and David Krueger. 2024 · 2024

Closest in time.

Beavertails: Towards improved safety alignment of llm via a human-preference dataset

Jiaming Ji, Mickel Liu, Josef Dai, Xuehai Pan, Chi Zhang, Ce Bian, Boyuan Chen, Ruiyang Sun, Yizhou Wang, and Yaodong Yang. 2024 · 2024

Closest in time.

ARGS: Alignment as reward-guided search

Maxim Khanov, Jirayu Burapacheep, and Yixuan Li. 2024 · 2024

Closest in time.

Llama guard 2

Meta. 2024 · 2024

Closest in time.

Fine-tuning aligned language models compromises safety, even when users do not intend to!