Files
G0DM0D3/paper/references.bib
2026-03-25 10:44:35 -07:00

207 lines
8.5 KiB
BibTeX

@article{ackley1985learning,
title={A Learning Algorithm for {B}oltzmann Machines},
author={Ackley, David H and Hinton, Geoffrey E and Sejnowski, Terrence J},
journal={Cognitive Science},
volume={9},
number={1},
pages={147--169},
year={1985}
}
@article{bai2022constitutional,
title={Constitutional {AI}: Harmlessness from {AI} Feedback},
author={Bai, Yuntao and Kadavath, Saurav and Kundu, Sandipan and Askell, Amanda and Kernion, Jackson and Jones, Andy and Chen, Anna and Goldie, Anna and Mirhoseini, Azalia and McKinnon, Cameron and others},
journal={arXiv preprint arXiv:2212.08073},
year={2022}
}
@book{cohen1988statistical,
title={Statistical Power Analysis for the Behavioral Sciences},
author={Cohen, Jacob},
edition={2nd},
publisher={Lawrence Erlbaum Associates},
year={1988}
}
@article{chao2023jailbreaking,
title={Jailbreaking Black Box Large Language Models in Twenty Queries},
author={Chao, Patrick and Robey, Alexander and Dobriban, Edgar and Hassani, Hamed and Pappas, George J and Wong, Eric},
journal={arXiv preprint arXiv:2310.08419},
year={2023}
}
@article{chen2023frugalgpt,
title={{FrugalGPT}: How to Use Large Language Models While Reducing Cost and Improving Performance},
author={Chen, Lingjiao and Zaharia, Matei and Zou, James},
journal={arXiv preprint arXiv:2305.05176},
year={2023}
}
@inproceedings{dathathri2020plug,
title={Plug and Play Language Models: A Simple Approach to Controlled Text Generation},
author={Dathathri, Sumanth and Madotto, Andrea and Lan, Janice and Hung, Jane and Frank, Eric and Molino, Piero and Yosinski, Jason and Liu, Rosanne},
booktitle={International Conference on Learning Representations (ICLR)},
year={2020}
}
@inproceedings{fan2018hierarchical,
title={Hierarchical Neural Story Generation},
author={Fan, Angela and Lewis, Mike and Dauphin, Yann},
booktitle={Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL)},
year={2018}
}
@article{ganguli2022red,
title={Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned},
author={Ganguli, Deep and Lovitt, Liane and Kernion, Jackson and Askell, Amanda and Bai, Yuntao and Kadavath, Saurav and Mann, Ben and Perez, Ethan and Schiefer, Nicholas and Ndousse, Kamal and others},
journal={arXiv preprint arXiv:2209.07858},
year={2022}
}
@inproceedings{greshake2023not,
title={Not What You've Signed Up For: Compromising Real-World {LLM}-Integrated Applications with Indirect Prompt Injection},
author={Greshake, Kai and Abdelnabi, Sahar and Mishra, Shailesh and Endres, Christoph and Holz, Thorsten and Fritz, Mario},
booktitle={AISec},
year={2023}
}
@inproceedings{holtzman2020curious,
title={The Curious Case of Neural Text Degeneration},
author={Holtzman, Ari and Buys, Jan and Du, Li and Forbes, Maxwell and Choi, Yejin},
booktitle={International Conference on Learning Representations (ICLR)},
year={2020}
}
@inproceedings{jiang2023llmblender,
title={{LLM-Blender}: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion},
author={Jiang, Dongfu and Ren, Xiang and Lin, Bill Yuchen},
booktitle={Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL)},
year={2023}
}
@misc{li2023alpacaeval,
title={{AlpacaEval}: An Automatic Evaluator of Instruction-following Models},
author={Li, Xuechen and Zhang, Tianyi and Dubois, Yann and Taori, Rohan and Gulrajani, Ishaan and Guestrin, Carlos and Liang, Percy and Hashimoto, Tatsunori B},
year={2023},
howpublished={GitHub repository}
}
@article{liu2024jailbreaking,
title={Jailbreaking {ChatGPT} via Prompt Engineering: An Empirical Study},
author={Liu, Yi and Deng, Gelei and Xu, Zhengzi and Li, Yuekang and Zheng, Yaowen and Zhang, Ying and Zhao, Lida and Zhang, Tianwei and Wang, Kailong and Liu, Yang},
journal={arXiv preprint arXiv:2305.13860},
year={2024}
}
@article{mazeika2024harmbench,
title={{HarmBench}: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal},
author={Mazeika, Mantas and Phan, Long and Yin, Xuwang and Zou, Andy and Wang, Zifan and Mu, Norman and Sakhaee, Elham and Li, Nathaniel and Basart, Steven and Li, Bo and others},
journal={arXiv preprint arXiv:2402.04249},
year={2024}
}
@article{ong2024routellm,
title={{RouteLLM}: Learning to Route {LLM}s with Preference Data},
author={Ong, Isaac and Almahairi, Amjad and Wu, Vincent and Chiang, Wei-Lin and Stoica, Ion},
journal={arXiv preprint arXiv:2406.18665},
year={2024}
}
@inproceedings{ouyang2022training,
title={Training language models to follow instructions with human feedback},
author={Ouyang, Long and Wu, Jeffrey and Jiang, Xu and others},
booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
year={2022}
}
@inproceedings{perez2022red,
title={Red Teaming Language Models with Language Models},
author={Perez, Ethan and Huang, Saffron and Song, Francis and Cai, Trevor and Ring, Roman and Aslanides, John and Glaese, Amelia and McAleese, Nat and Irving, Geoffrey},
booktitle={Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
year={2022}
}
@article{qi2024finetuning,
title={Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To},
author={Qi, Xiangyu and Zeng, Yi and Xie, Tinghao and Chen, Pin-Yu and Jia, Ruoxi and Mittal, Prateek and Henderson, Peter},
journal={arXiv preprint arXiv:2310.03693},
year={2024}
}
@inproceedings{rafailov2023direct,
title={Direct Preference Optimization: Your Language Model is Secretly a Reward Model},
author={Rafailov, Rafael and Sharma, Archit and Mitchell, Eric and Ermon, Stefano and Manning, Christopher D and Finn, Chelsea},
booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
year={2023}
}
@article{shen2024anything,
title={``Do Anything Now'': Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models},
author={Shen, Xinyue and Chen, Zeyuan and Backes, Michael and Shen, Yun and Zhang, Yang},
journal={arXiv preprint arXiv:2308.03825},
year={2024}
}
@inproceedings{stiennon2020learning,
title={Learning to summarize with human feedback},
author={Stiennon, Nisan and Ouyang, Long and Wu, Jeffrey and Ziegler, Daniel and Lowe, Ryan and Voss, Chelsea and Radford, Alec and Amodei, Dario and Christiano, Paul},
booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
year={2020}
}
@article{wang2024mixture,
title={Mixture-of-Agents Enhances Large Language Model Capabilities},
author={Wang, Junlin and others},
journal={arXiv preprint arXiv:2406.04692},
year={2024}
}
@inproceedings{wei2023jailbroken,
title={Jailbroken: How Does {LLM} Safety Training Fail?},
author={Wei, Alexander and Haghtalab, Nika and Steinhardt, Jacob},
booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
year={2023}
}
@inproceedings{yang2021fudge,
title={{FUDGE}: Controlled Text Generation With Future Discriminators},
author={Yang, Kevin and Klein, Dan},
booktitle={Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)},
year={2021}
}
@inproceedings{zheng2024judging,
title={Judging {LLM}-as-a-Judge with {MT-Bench} and {Chatbot Arena}},
author={Zheng, Lianmin and Chiang, Wei-Lin and Sheng, Ying and Zhuang, Siyuan and Wu, Zhanghao and Zhuang, Yonghao and Lin, Zi and Li, Zhuohan and Li, Dacheng and Xing, Eric P and Zhang, Hao and Gonzalez, Joseph E and Stoica, Ion},
booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
year={2024}
}
@article{zou2023universal,
title={Universal and Transferable Adversarial Attacks on Aligned Language Models},
author={Zou, Andy and Wang, Zifan and Kolter, J Zico and Fredrikson, Matt},
journal={arXiv preprint arXiv:2307.15043},
year={2023}
}
@misc{plinius2024autotemp,
title={{AutoTemp}: Automated Temperature Sampling for LLMs},
author={Plinius},
year={2024},
howpublished={Open-source project}
}
@article{amodei2016concrete,
title={Concrete Problems in {AI} Safety},
author={Amodei, Dario and Olah, Chris and Steinhardt, Jacob and Christiano, Paul and Schulman, John and Man{\'e}, Dan},
journal={arXiv preprint arXiv:1606.06565},
year={2016}
}
@article{hendrycks2021unsolved,
title={Unsolved Problems in {ML} Safety},
author={Hendrycks, Dan and Carlini, Nicholas and Mazeika, Mantas and others},
journal={arXiv preprint arXiv:2109.13916},
year={2021}
}