activity
20242026
collaborators

6 papers

cs.CL2026

Latent Planning Emerges with Scale

Michael Hanna, Emmanuel Ameisen

LLMs can perform seemingly planning-intensive tasks, like writing coherent stories or functioning code, without explicitly verbalizing a plan; however, the extent to which they imp…

cs.CL2025

Are formal and functional linguistic mechanisms dissociated in language models?

Michael Hanna, Yonatan Belinkov, Sandro Pezzelle

Although large language models (LLMs) are increasingly capable, these capabilities are unevenly distributed: they excel at formal linguistic tasks, such as producing fluent, gramma…

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

LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks

Anna Bavaresco, Raffaella Bernardi, Leonardo Bertolazzi +17

There is an increasing trend towards evaluating NLP models with LLMs instead of human judgments, raising questions about the validity of these evaluations, as well as their reprodu…

cs.CL2024

Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Models

Michael Hanna, Aaron Mueller

Autoregressive transformer language models (LMs) possess strong syntactic abilities, often successfully handling phenomena from agreement to NPI licensing. However, the features th…

cs.LG2024

LLM Circuit Analyses Are Consistent Across Training and Scale

Curt Tigges, Michael Hanna, Qinan Yu +1

Most currently deployed large language models (LLMs) undergo continuous training or additional finetuning. By contrast, most research into LLMs' internal mechanisms focuses on mode…