x

AI ALIGNMENT FORUM
AF

Academic Papers — AI Alignment Forum

Academic Papers

Edited by Kaj_Sotala last updated 9th Jul 2020

Posts either linking to, or summarizing, formal papers published elsewhere.

Add Posts

Posts tagged Academic Papers

1

65Some AI research areas and their relevance to existential safety

5y

34

3

37Pretraining on Aligned AI Data Dramatically Reduces Misalignment—Even After Post-Training

1mo

0

3

19How to Control an LLM's Behavior (why my P(DOOM) went down)

2y

0

3

7The Best Way to Align an LLM: Is Inner Alignment Now a Solved Problem?

9mo

0

2

512021 AI Alignment Literature Review and Charity Comparison

4y

15

1

58Evidence of Learned Look-Ahead in a Chess-Playing Neural Network

2y

0

1

29A technical note on bilinear layers for interpretability

3y

0

1

19Formal Solution to the Inner Alignment Problem

5y

123

1

21Why is pseudo-alignment "worse" than other ways ML can fail to generalize?

nostalgebraist, evhub

6y

7

0

75Shallow review of technical AI safety, 2024

technicalities, Stag, Stephen McAleese, jordine, Dr. David Mathers

1y

1

1

53Shallow review of technical AI safety, 2025

technicalities, Tomáš Gavenčiak, Stephen McAleese, peligrietzer, Stag, jordine, ozziegooen, Violet Hour, ramennaut

2mo

0

1

28NeurIPS ML Safety Workshop 2022

4y

1

0

19Secret Collusion: Will We Know When to Unplug AI?

schroederdewitt, srm, MikhailB, Lewis Hammond, chansmi, Angira Sharma

1y

1

1

25How truthful is GPT-3? A benchmark for language models

4y

18

0

14New paper: Corrigibility with Utility Preservation

7y

9

Load More (15/24)

Add Posts