Papers by Michael Lan

3 papers
Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Recent work aims to reverse engineer transformer models into human-readable representations . transformers exhibit strong capabilities on linguistic tasks, but their complex architectures make them difficult to interpret.
Approach: They extend transformer models into human-readable representations that implement algorithmic functions by analyzing sequence continuation tasks.
Outcome: The proposed model can be reverse-engineered into human-readable representations that implement algorithmic functions.
Do Transformer Modifications Transfer Across Implementations and Applications? (2021.emnlp-main)

Copied to clipboard

Challenge: Currently, the Transformer is the de facto architecture of choice for processing sequential data.
Approach: They evaluate the Transformer architecture and its modifications in a shared experimental setting . they conjecture that performance improvements may strongly depend on implementation details .
Outcome: The proposed improvements do not significantly improve performance, the authors find . the proposed improvements are either developed in the same codebase or are minor changes .
Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing (2026.acl-long)

Copied to clipboard

Challenge: a recent paper found conflicting conclusions for the same behavior in a neural network . authors propose auditing MI itself is essential for its application in AI safety, industry, and governance .
Approach: They propose to develop a system that can audit experiments to ensure validity . authors propose to generalize good practices found on platform into expert-verified guidelines .
Outcome: a new review system could be developed that can be standardized and audited . authors argue that auditing MI is essential for its application in AI safety, industry, and governance .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations