Computer Science > Machine Learning
arXiv:2402.05110 (cs)
[Submitted on 7 Feb 2024]
Title:Opening the AI black box: program synthesis via mechanistic interpretability
Authors:Eric J. Michaud,Isaac Liao,Vedang Lad,Ziming Liu,Anish Mudide,Chloe Loughridge,Zifan Carl Guo,Tara Rezaei Kheirkhah,Mateja Vukelić,Max Tegmark
View a PDF of the paper titled Opening the AI black box: program synthesis via mechanistic interpretability, by Eric J. Michaud and 9 other authors
View PDFAbstract:We present MIPS, a novel method for program synthesis based on automated mechanistic interpretability of neural networks trained to perform the desired task, auto-distilling the learned algorithm into Python code. We test MIPS on a benchmark of 62 algorithmic tasks that can be learned by an RNN and find it highly complementary to GPT-4: MIPS solves 32 of them, including 13 that are not solved by GPT-4 (which also solves 30). MIPS uses an integer autoencoder to convert the RNN into a finite state machine, then applies Boolean or integer symbolic regression to capture the learned algorithm. As opposed to large language models, this program synthesis technique makes no use of (and is therefore not limited by) human training data such as algorithms and code from GitHub. We discuss opportunities and challenges for scaling up this approach to make machine-learned models more interpretable and trustworthy.
| Comments: | 24 pages |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2402.05110 [cs.LG] |
| (orarXiv:2402.05110v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2402.05110 arXiv-issued DOI via DataCite |
Full-text links:
Access Paper:
- View PDF
- TeX Source
- Other Formats
View a PDF of the paper titled Opening the AI black box: program synthesis via mechanistic interpretability, by Eric J. Michaud and 9 other authors
References & Citations
Bookmark
Bibliographic and Citation Tools
Bibliographic Explorer(What is the Explorer?)
Connected Papers(What is Connected Papers?)
Litmaps(What is Litmaps?)
scite Smart Citations(What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv(What is alphaXiv?)
CatalyzeX Code Finder for Papers(What is CatalyzeX?)
DagsHub(What is DagsHub?)
Gotit.pub(What is GotitPub?)
Hugging Face(What is Huggingface?)
Papers with Code(What is Papers with Code?)
ScienceCast(What is ScienceCast?)
Demos
Recommenders and Search Tools
Influence Flower(What are Influence Flowers?)
CORE Recommender(What is CORE?)
IArxiv Recommender(What is IArxiv?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community?Learn more about arXivLabs.