Christopher J. Anders

RIKEN Center for Advanced Intelligence Project, Tokyo, Japan

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Interpretability & Mechanistic Interp (1)Natural Language Processing (1)

Frequent co-authors

Henrique Da Silva Gameiro (1)Mohammad Emtiyaz Khan (1)

Papers (1)

Jun 22, 2026

3w ago·also EPFL, TU Darmstadt

Quantifying the Agreement Between Data-Influence and Data-Similarity to Understand LLM Behavior

Data-similarity can reliably guide output tracing, but its accuracy skyrockets when refined with data-influence, revealing a powerful synergy between the two measures.

Christopher J. Anders, Henrique Da Silva Gameiro, Mohammad Emtiyaz Khan

Interpretability & Mechanistic Interp Natural Language Processing

Search

Christopher J. Anders

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)