Exploring the Robustness of Model-Graded Evaluations and Automated Interpretability

Concrete problems in ai safety

Original

Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., and Mané, D. (2016) · 2016

Earlier work this paper cites.

Constitutional ai: Harmlessness from ai feedback

Bai, Y., Kadavath, S., Kundu, S., Askell, A., Kernion, J., Jones, A., Chen, A., Goldie, A., Mirhoseini, A., McKinnon, C., Chen, C., Olsson, C., Olah, C., Hernandez, D., Drain, D., Ganguli, D., Li, D., Tran-Johnson, E., Perez, E., Kerr, J., Mueller, J., Ladish, J., Landau, J., Ndousse, K., Lukosuite, K., Lovitt, L., Sellitto, M., Elhage, N., Schiefer, N., Mercado, N., DasSarma, N., Lasenby, R., Larson, R., Ringer, S., Johnston, S., Kravec, S., Showk, S. E., Fort, S., Lanham, T., Telleen-Lawton, T., Conerly, T., Henighan, T., Hume, T., Bowman, S. R., Hatfield-Dodds, Z., Mann, B., Amodei, D., Joseph, N., McCandlish, S., Brown, T., and Kaplan, J. (2022) · 2022

Earlier work this paper cites.

Our approach to alignment research

Leike, J., Schulman, J., and Wu, J. (2022) · 2022

Earlier work this paper cites.

Truthfulqa: Measuring how models mimic human falsehoods

Lin, S., Hilton, J., and Evans, O. (2022) · 2022

Earlier work this paper cites.

Introducing superalignment

OpenAI (2022) · 2022

Cited alongside, same era.

You can use gpt-4 to create prompt injections against gpt-4

Anonymous (2023) · 2023

Cited alongside, same era.

Language models can explain neurons in language models

Bills, S., Cammarata, N., Mossing, D., Tillman, H., Gao, L., Goh, G., Sutskever, I., Leike, J., Wu, J., and Saunders, W. (2023) · 2023

Cited alongside, same era.

Do the rewards justify the means? measuring trade-offs between rewards and ethical behavior in the machiavelli benchmark

Original

Pan, A., Shern, C. J., Zou, A., Li, N., Basart, S., Woodside, T., Ng, J., Zhang, H., Emmons, S., and Hendrycks, D. (2023) · 2023

Cited alongside, same era.

Red teaming language models with language models

Perez, E., Huang, S., Song, F., Cai, T., Ring, R., Aslanides, J., Glaese, A., McAleese, N., and Irving, G. (2022a)

Cited in the paper.

Discovering language model behaviors with model-written evaluations

Language models don’t always say what they think: Unfaithful explanations in chain-of-thought prompting

Turpin, M., Michael, J., Perez, E., and Bowman, S. R. (2023) · 2023

Closest in time.

Evaluating shutdown avoidance of language models in textual scenarios

van der Weij, T., Lermen, S., and Lang, L. (2023) · 2023

Closest in time.

Exploring the mit mathematics and eecs curriculum using large language models

Original

Zhang, S. J., Florin, S., Lee, A. N., Niknafs, E., Marginean, A., Wang, A., Tyser, K., Chin, Z., Hicke, Y., Singh, N., Udell, M., Kim, Y., Buonassisi, T., Solar-Lezama, A., and Drori, I. (2023) · 2023

Closest in time.