|
| 1 | +@article{ouyang2022training, |
| 2 | + title={Training language models to follow instructions with human feedback}, |
| 3 | + author={Ouyang, Long and Wu, Jeffrey and Jiang, Xu and Almeida, Diogo and Wainwright, Carroll and Mishkin, Pamela and Zhang, Chong and Agarwal, Sandhini and Slama, Katarina and Ray, Alex and others}, |
| 4 | + journal={Advances in Neural Information Processing Systems}, |
| 5 | + volume={35}, |
| 6 | + pages={27730--27744}, |
| 7 | + year={2022} |
| 8 | +} |
| 9 | + |
| 10 | +@article{bai2022constitutional, |
| 11 | + title={Constitutional {AI}: Harmlessness from {AI} Feedback}, |
| 12 | + 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}, |
| 13 | + journal={arXiv preprint arXiv:2212.08073}, |
| 14 | + year={2022} |
| 15 | +} |
| 16 | + |
| 17 | +@article{rafailov2023direct, |
| 18 | + title={Direct Preference Optimization: Your Language Model is Secretly a Reward Model}, |
| 19 | + author={Rafailov, Rafael and Sharma, Archit and Mitchell, Eric and Ermon, Stefano and Manning, Christopher D and Finn, Chelsea}, |
| 20 | + journal={Advances in Neural Information Processing Systems}, |
| 21 | + volume={36}, |
| 22 | + pages={53728--53741}, |
| 23 | + year={2023} |
| 24 | +} |
| 25 | + |
| 26 | +@inproceedings{rebedea2023nemo, |
| 27 | + title={{NeMo Guardrails}: A Toolkit for Controllable and Safe {LLM} Applications with Programmable Rails}, |
| 28 | + author={Rebedea, Traian and Dinu, Razvan and Sreedhar, Makesh Narsimhan and Parisien, Christopher and Cohen, Jonathan}, |
| 29 | + booktitle={Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations}, |
| 30 | + pages={431--445}, |
| 31 | + year={2023} |
| 32 | +} |
| 33 | + |
| 34 | +@article{perez2023discovering, |
| 35 | + title={Discovering Language Model Behaviors with Model-Written Evaluations}, |
| 36 | + author={Perez, Ethan and Ringer, Sam and Luko{\v{s}}i{\=u}t{\.e}, Kamil{\.e} and Nguyen, Karina and Chen, Edwin and Heiner, Scott and Pettit, Craig and Olsson, Catherine and Kundu, Sandipan and Kadavath, Saurav and others}, |
| 37 | + journal={Findings of the Association for Computational Linguistics: ACL 2023}, |
| 38 | + pages={13387--13434}, |
| 39 | + year={2023} |
| 40 | +} |
| 41 | + |
| 42 | +@article{sharma2023towards, |
| 43 | + title={Towards Understanding Sycophancy in Language Models}, |
| 44 | + author={Sharma, Mrinank and Tong, Meg and Korbak, Tomasz and Duvenaud, David and Askell, Amanda and Bowman, Samuel R and Cheng, Newton and Durmus, Esin and Hatfield-Dodds, Zac and Johnston, Scott R and others}, |
| 45 | + journal={arXiv preprint arXiv:2310.13548}, |
| 46 | + year={2023} |
| 47 | +} |
| 48 | + |
| 49 | +@article{costa1992revised, |
| 50 | + title={Revised {NEO} Personality Inventory ({NEO-PI-R}) and {NEO} Five-Factor Inventory ({NEO-FFI}) Professional Manual}, |
| 51 | + author={Costa, Paul T and McCrae, Robert R}, |
| 52 | + journal={Psychological Assessment Resources}, |
| 53 | + year={1992}, |
| 54 | + address={Odessa, FL} |
| 55 | +} |
| 56 | + |
| 57 | +@article{safdari2023personality, |
| 58 | + title={Personality Traits in Large Language Models}, |
| 59 | + author={Safdari, Mustafa and Serapio-Garc{\'i}a, Greg and Crepy, Cl{\'e}ment and Fitz, Stephen and Romero, Peter and Sun, Luning and Abdulhai, Marwa and Faust, Aleksandra and Matari{\'c}, Maja}, |
| 60 | + journal={arXiv preprint arXiv:2307.00184}, |
| 61 | + year={2023} |
| 62 | +} |
| 63 | + |
| 64 | +@article{shao2023character, |
| 65 | + title={Character-{LLM}: A Trainable Agent for Role-Playing}, |
| 66 | + author={Shao, Yunfan and Li, Linyang and Dai, Junqi and Qiu, Xipeng}, |
| 67 | + journal={Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing}, |
| 68 | + pages={13153--13187}, |
| 69 | + year={2023} |
| 70 | +} |
| 71 | + |
| 72 | +@article{zhang2018personalizing, |
| 73 | + title={Personalizing Dialogue Agents: {I} have a dog, do you have pets too?}, |
| 74 | + author={Zhang, Saizheng and Dinan, Emily and Urbanek, Jack and Szlam, Arthur and Kiela, Douwe and Weston, Jason}, |
| 75 | + journal={Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics}, |
| 76 | + pages={2204--2213}, |
| 77 | + year={2018} |
| 78 | +} |
| 79 | + |
| 80 | +@article{lin2022truthfulqa, |
| 81 | + title={{TruthfulQA}: Measuring How Models Mimic Human Falsehoods}, |
| 82 | + author={Lin, Stephanie and Hilton, Jacob and Evans, Owain}, |
| 83 | + journal={Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics}, |
| 84 | + pages={3214--3252}, |
| 85 | + year={2022} |
| 86 | +} |
| 87 | + |
| 88 | +@article{li2023halueval, |
| 89 | + title={{HaluEval}: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models}, |
| 90 | + author={Li, Junyi and Cheng, Xiaoxue and Zhao, Wayne Xin and Nie, Jian-Yun and Wen, Ji-Rong}, |
| 91 | + journal={Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing}, |
| 92 | + pages={6449--6464}, |
| 93 | + year={2023} |
| 94 | +} |
| 95 | + |
| 96 | +@article{jiang2023evaluating, |
| 97 | + title={Evaluating and Inducing Personality in Pre-trained Language Models}, |
| 98 | + author={Jiang, Guangyuan and Xu, Manjie and Zhu, Song-Chun and Han, Wenjuan and Zhang, Chi and Zhu, Yixin}, |
| 99 | + journal={Advances in Neural Information Processing Systems}, |
| 100 | + volume={36}, |
| 101 | + pages={10622--10643}, |
| 102 | + year={2023} |
| 103 | +} |
| 104 | + |
| 105 | +@article{burns2023weaktostrong, |
| 106 | + title={Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision}, |
| 107 | + author={Burns, Collin and Ye, Haotian and Klein, Dan and Steinhardt, Jacob}, |
| 108 | + journal={arXiv preprint arXiv:2312.09390}, |
| 109 | + year={2023} |
| 110 | +} |
| 111 | + |
| 112 | +@article{madaan2023selfrefine, |
| 113 | + title={Self-Refine: Iterative Refinement with Self-Feedback}, |
| 114 | + author={Madaan, Aman and Tandon, Niket and Gupta, Prakhar and Hallinan, Skyler and Gao, Luyu and Wiegreffe, Sarah and Alon, Uri and Dziri, Nouha and Prabhumoye, Shrimai and Yang, Yiming and others}, |
| 115 | + journal={Advances in Neural Information Processing Systems}, |
| 116 | + volume={36}, |
| 117 | + pages={46534--46594}, |
| 118 | + year={2023} |
| 119 | +} |
| 120 | + |
| 121 | +@article{irving2018ai, |
| 122 | + title={{AI} Safety via Debate}, |
| 123 | + author={Irving, Geoffrey and Christiano, Paul and Amodei, Dario}, |
| 124 | + journal={arXiv preprint arXiv:1805.00899}, |
| 125 | + year={2018} |
| 126 | +} |
0 commit comments