"Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models

Www’18 open challenge: Financial opinion mining and question answering

Macedo Maia, Siegfried Handschuh, André Freitas, Brian Davis, Ross McDermott, Manel Zarrouk, and Alexandra Balahur. 2018 · 1942

Earlier work this paper cites.

Convergence of alternating optimization

James C Bezdek and Richard J Hathaway. 2003 · 2003

Earlier work this paper cites.

Generalized gumbel-softmax gradient estimator for various discrete random variables

Original

Weonyoung Joo, Dongjun Kim, Seungjae Shin, and Il-Chul Moon. 2020 · 2003

Earlier work this paper cites.

One word at a time: adversarial attacks on retrieval models

Original

Nisarg Raval and Manisha Verma. 2020 · 2008

Earlier work this paper cites.

Adversarial semantic collisions

Original

Congzheng Song, Alexander M Rush, and Vitaly Shmatikov. 2020 · 2011

Earlier work this paper cites.

Categorical reparameterization with gumbel-softmax

Original

Eric Jang, Shixiang Gu, and Ben Poole. 2016 · 2016

Earlier work this paper cites.

MS MARCO: A human generated machine reading comprehension dataset

Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016 · 2016

Earlier work this paper cites.

Hotflip: White-box adversarial examples for text classification

Original

Javid Ebrahimi, Anyi Rao, Daniel Lowd, and Dejing Dou. 2017 · 2017

Earlier work this paper cites.

Model-agnostic meta-learning for fast adaptation of deep networks

Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017 · 2017

Earlier work this paper cites.

Hotpotqa: A dataset for diverse, explainable multi-hop question answering

Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W. Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018 · 2018

Earlier work this paper cites.

Natural questions: a benchmark for question answering research

Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur P. Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M. Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019 · 2019

Earlier work this paper cites.

Language models are few-shot learners

Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020 · 2020

Earlier work this paper cites.

Retrieval-augmented generation for knowledge-intensive nlp tasks

Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020 · 2020

Earlier work this paper cites.

Gradient-based adversarial attacks against text transformers

Original

Chuan Guo, Alexandre Sablayrolles, Hervé Jégou, and Douwe Kiela. 2021 · 2021

Earlier work this paper cites.

Unsupervised dense information retrieval with contrastive learning

Original

Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2021 · 2021

Earlier work this paper cites.

Internet-augmented dialogue generation

Original

Mojtaba Komeili, Kurt Shuster, and Jason Weston. 2021 · 2021

Earlier work this paper cites.

Investigating bi-level optimization for learning and vision from a unified perspective: A survey and beyond

Risheng Liu, Jiaxin Gao, Jin Zhang, Deyu Meng, and Zhouchen Lin. 2021 · 2021

Earlier work this paper cites.

BEIR: A heterogeneous benchmark for zero-shot evaluation of information retrieval models

Nandan Thakur, Nils Reimers, Andreas Rücklé, Abhishek Srivastava, and Iryna Gurevych. 2021a · 2021

Earlier work this paper cites.

Approximate nearest neighbor negative contrastive learning for dense text retrieval

Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul N. Bennett, Junaid Ahmed, and Arnold Overwijk. 2021 · 2021

Cited alongside, same era.

Poisonedrag: Knowledge poisoning attacks to retrieval-augmented generation of large language models

Original

Wei Zou, Runpeng Geng, Binghui Wang, and Jinyuan Jia. 2024 · 2021

Cited alongside, same era.

Constitutional ai: Harmlessness from ai feedback

Original

Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen, Anna Goldie, Azalia Mirhoseini, Cameron McKinnon, et al. 2022 · 2022

Cited alongside, same era.

Beyond bounding box: Multimodal knowledge learning for object detection

Original

Weixin Feng, Xingyuan Bu, Chenchen Zhang, and Xubin Li. 2022 · 2022

Cited alongside, same era.

Unsupervised dense information retrieval with contrastive learning

Is my data in your retrieval database? membership inference attacks against retrieval augmented generation

Original

Maya Anderson, Guy Amit, and Abigail Goldsteen. 2024 · 2024

Closest in time.

The claude 3 model family: Opus, sonnet, haiku

AI Anthropic. 2024 · 2024

Closest in time.

Benchmarking large language models in retrieval-augmented generation

Jiawei Chen, Hongyu Lin, Xianpei Han, and Le Sun. 2024 · 2024

Closest in time.

Trojanrag: Retrieval-augmented generation can be backdoor driver in large language models

Original

Pengzhou Cheng, Yidong Ding, Tianjie Ju, Zongru Wu, Wei Du, Ping Yi, Zhuosheng Zhang, and Gongshen Liu. 2024 · 2024

Closest in time.

Typos that broke the rag’s back: Genetic attack on rag pipeline by simulating documents in the wild via low-level perturbations

Original

Sukmin Cho, Soyeong Jeong, Jeongyeon Seo, Taeho Hwang, and Jong C Park. 2024 · 2024