collaborators

6 papers

cs.LG2026

Induction Meets Biology: Mechanisms of Repeat Detection in Protein Language Models

Gal Pomerants, Yaniv Nikankin, Anja Reusch +3

Protein sequences are abundant in repeating segments, both as exact copies and as approximate segments with mutations. These repeats are important for protein structure and functio…

cs.LG2026

Interpretability Can Be Actionable

Hadas Orgad, Fazl Barez, Tal Haklay +9

Interpretability aims to explain the behavior of deep neural networks. Despite rapid growth, there is mounting concern that much of this work has not translated into practical impa…

cs.CL2025

BlackboxNLP-2025 MIB Shared Task: Improving Circuit Faithfulness via Better Edge Selection

Yaniv Nikankin, Dana Arad, Itay Itzhak +4

One of the main challenges in mechanistic interpretability is circuit discovery, determining which parts of a model perform a given task. We build on the Mechanistic Interpretabili…

cs.LG2025

MIB: A Mechanistic Interpretability Benchmark

Aaron Mueller, Atticus Geiger, Sarah Wiegreffe +20

How can we know whether new mechanistic interpretability methods achieve real improvements? In pursuit of lasting evaluation standards, we propose MIB, a Mechanistic Interpretabili…

cs.CL2025

Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics

Yaniv Nikankin, Anja Reusch, Aaron Mueller +1

Do large language models (LLMs) solve reasoning tasks by learning robust generalizable algorithms, or do they memorize training data? To investigate this question, we use arithmeti…

cs.IR2025

Reverse-Engineering the Retrieval Process in GenIR Models

Anja Reusch, Yonatan Belinkov

Generative Information Retrieval (GenIR) is a novel paradigm in which a transformer encoder-decoder model predicts document rankings based on a query in an end-to-end fashion. Thes…