collaborators

6 papers

cs.CL2026

Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context

Yoav Gur-Arieh, Mor Geva, Atticus Geiger

A key component of in-context reasoning is the ability of language models (LMs) to bind entities for later retrieval. For example, an LM might represent "Ann loves pie" by binding…

cs.CL2026

Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth

Yoav Gur-Arieh, Ana Marasović, Mor Geva

Chains of thought (CoTs) have become central in interpreting and auditing behaviors of large language models. Yet growing evidence suggests that these traces often fail to faithful…

cs.CL2026

Disentangling MLP Neuron Weights in Vocabulary Space

Asaf Avrahamy, Yoav Gur-Arieh, Mor Geva

Interpreting the information encoded in language model weights remains a fundamental challenge in mechanistic interpretability. In this work, we introduce ROTATE (Rotation-Optimize…

cs.CL2025

Precise In-Parameter Concept Erasure in Large Language Models

Yoav Gur-Arieh, Clara Suslik, Yihuai Hong +2

Large language models (LLMs) often acquire knowledge during pretraining that is undesirable in downstream deployments, e.g., sensitive information or copyrighted content. Existing…

cs.CL2025

LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations

Daniela Gottesman, Alon Gilae-Dotan, Ido Cohen +4

Language models (LMs) increasingly drive real-world applications that require world knowledge. However, the internal processes through which models turn data into representations o…

cs.CL2025

Enhancing Automated Interpretability with Output-Centric Feature Descriptions

Yoav Gur-Arieh, Roy Mayan, Chen Agassy +2

Automated interpretability pipelines generate natural language descriptions for the concepts represented by features in large language models (LLMs), such as plants or the first wo…