Add research paper: paper/references.bib

paper/references.bib

@@ -0,0 +1,65 @@
+@article{arditi2024refusal,
+  title={Refusal in Language Models Is Mediated by a Single Direction},
+  author={Arditi, Andy and Obeso, Oscar and Syed, Aaquib and Paleka, Daniel and Rimsky, Nina and Neel, Wes and Sharkey, Lee},
+  journal={arXiv preprint arXiv:2406.11717},
+  year={2024}
+}
+
+@misc{sumandora2024,
+  title={remove-refusals-with-transformers},
+  author={Sumandora},
+  year={2024},
+  howpublished={\url{https://github.com/Sumandora/remove-refusals-with-transformers}}
+}
+
+@misc{hamsaomar2025,
+  title={Kimi-K2.5 Abliteration Research},
+  author={hamsaOmar},
+  year={2025},
+  howpublished={\url{https://huggingface.co/hamsaOmar/Kimi-K2.5-abliterated}}
+}
+
+@article{hu2022lora,
+  title={LoRA: Low-Rank Adaptation of Large Language Models},
+  author={Hu, Edward J. and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Wang, Lu and Chen, Weizhu},
+  journal={arXiv preprint arXiv:2106.09685},
+  year={2022}
+}
+
+@article{dettmers2023qlora,
+  title={QLoRA: Efficient Finetuning of Quantized Language Models},
+  author={Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke},
+  journal={Advances in Neural Information Processing Systems},
+  year={2023}
+}
+
+@article{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},
+  journal={Advances in Neural Information Processing Systems},
+  year={2023}
+}
+
+@article{liu2024bitdelta,
+  title={BitDelta: Your Fine-Tune May Only Be Worth One Bit},
+  author={Liu, James and Zhong, Guangxuan and Li, Yifan and Kolter, J. Zico and Sabharwal, Ashish},
+  journal={arXiv preprint arXiv:2402.10193},
+  year={2024}
+}
+
+@article{shazeer2017outrageously,
+  title={Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer},
+  author={Shazeer, Noam and Mirhoseini, Azalia and Maziarz, Krzysztof and Davis, Andy and Le, Quoc and Hinton, Geoffrey and Dean, Jeff},
+  journal={arXiv preprint arXiv:1701.06538},
+  year={2017}
+}
+
+@article{fedus2022switch,
+  title={Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity},
+  author={Fedus, William and Zoph, Barret and Shazeer, Noam},
+  journal={Journal of Machine Learning Research},
+  volume={23},
+  number={120},
+  pages={1--39},
+  year={2022}
+}