8 papers
The Dual Mechanisms of Spatial Variable Binding in Vision-Language Models
Kelly Cui, Nikhil Prakash, Shoval Messica +4
Many multimodal tasks, such as image captioning and visual question answering, require vision-language models (VLMs) to bind objects with their properties and spatial relations. Ye…
Pitfalls in Evaluating Interpretability Agents
Tal Haklay, Nikhil Prakash, Sana Pandey +5
Automated interpretability systems aim to reduce the need for human labor and scale analysis to increasingly large models and diverse tasks. Recent efforts toward this goal leverag…
Language Models use Lookbacks to Track Beliefs
Nikhil Prakash, Natalie Shapira, Arnab Sen Sharma +5
How do language models (LMs) represent characters' beliefs, especially when those beliefs may differ from reality? This question lies at the heart of understanding the Theory of Mi…
Agents of Chaos
Natalie Shapira, Chris Wendler, Avery Yen +35
We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent memory, email accounts, Discord acc…
Constructive Circuit Amplification: Improving Math Reasoning in LLMs via Targeted Sub-Network Updates
Nikhil Prakash, Donghao Ren, Dominik Moritz +1
Prior studies investigating the internal workings of LLMs have uncovered sparse subnetworks, often referred to as circuits, that are responsible for performing specific tasks. Addi…
The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis
Aaron Mueller, Jannik Brinkmann, Millicent Li +10
Interpretability provides a toolset for understanding how and why neural networks behave in certain ways. However, there is little unity in the field: most studies employ ad-hoc ev…