← Search

Andrew Joohun Nam

2 accepted papers

2025

Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers

NeurIPS 2025poster

We present causal head gating (CHG), a scalable method for interpreting the functional roles of attention heads in transformer models. CHG learns soft gates over heads and assigns them a causal taxonomy—facilitating, interfering, or irrelevant—based on their impact on task performance. Unlike prior…

Cited by 0SourceScholar
2023

Passive learning of active causal strategies in agents and language models

NeurIPS 2023poster

What can be learned about causality and experimentation from passive data? This question is salient given recent successes of passively-trained language models in interactive domains such as tool use. Passive learning is inherently limited. However, we show that purely passive learning can in fact a…

Cited by 23SourcePDFScholar