English
Related papers

Related papers: Does Circuit Analysis Interpretability Scale? Evid…

200 papers

Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level…

Computation and Language · Computer Science 2026-03-12 Ajay Pravin Mahale

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 leverage large language models (LLMs) at increasing levels of…

Artificial Intelligence · Computer Science 2026-03-23 Tal Haklay , Nikhil Prakash , Sana Pandey , Antonio Torralba , Aaron Mueller , Jacob Andreas , Tamar Rott Shaham , Yonatan Belinkov

Mechanistic interpretability assumes that circuit analysis becomes harder as models scale. We challenge this assumption by showing that the attention architecture matters more than parameter count. Studying three circuit types across Pythia…

Computation and Language · Computer Science 2026-05-12 Sohan Venkatesh

A widely used strategy to discover and understand language model mechanisms is circuit analysis. A circuit is a minimal subgraph of a model's computation graph that executes a specific task. We identify a gap in existing circuit discovery…

Machine Learning · Computer Science 2025-02-10 Tal Haklay , Hadas Orgad , David Bau , Aaron Mueller , Yonatan Belinkov

The circuits framework in mechanistic interpretability aims to identify causally important sparse subgraphs of model components, typically evaluated by measuring necessity and sufficiency. We measure circuit reuse, the proportion of…

Computation and Language · Computer Science 2026-05-12 Michael Li , Nishant Subramani

Achieving human-level performance on some of the Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs). However, the internal mechanism of these artifacts remains…

Computation and Language · Computer Science 2024-10-29 Yiming Cui , Wei-Nan Zhang , Wanxiang Che , Ting Liu , Zhigang Chen , Shijin Wang

The debate around the interpretability of attention mechanisms is centered on whether attention scores can be used as a proxy for the relative amounts of signal carried by sub-components of data. We propose to study the interpretability of…

Machine Learning · Computer Science 2022-07-27 Jonathan Haab , Nicolas Deutschmann , Maria Rodríguez Martínez

Attention mechanisms have improved the performance of NLP tasks while allowing models to remain explainable. Self-attention is currently widely used, however interpretability is difficult due to the numerous attention distributions. Recent…

Computation and Language · Computer Science 2020-10-30 Khalil Mrini , Franck Dernoncourt , Quan Tran , Trung Bui , Walter Chang , Ndapa Nakashole

Due to the size and complexity of modern large language models (LLMs), it has proven challenging to uncover the underlying mechanisms that models use to solve reasoning problems. For instance, is their reasoning for a specific problem…

Machine Learning · Computer Science 2025-06-23 Guan Zhe Hong , Nishanth Dikkala , Enming Luo , Cyrus Rashtchian , Xin Wang , Rina Panigrahy

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 Interpretability Benchmark (MIB) and propose three key improvements to…

Computation and Language · Computer Science 2025-10-31 Yaniv Nikankin , Dana Arad , Itay Itzhak , Anja Reusch , Adi Simhi , Gal Kesten-Pomeranz , Yonatan Belinkov

Hoffman et al (2022)'s Chinchilla paper introduced the principle of compute-optimal scaling, laying a foundation for future scaling of language models. In the years since, however, valid concerns about Chinchilla have been raised: wide…

Machine Learning · Computer Science 2025-09-30 Rylan Schaeffer , Noam Levi , Andreas Kirsch , Theo Guenais , Brando Miranda , Elyas Obbad , Sanmi Koyejo

This paper introduces an efficient and robust method for discovering interpretable circuits in large language models using discrete sparse autoencoders. Our approach addresses key limitations of existing techniques, namely computational…

Computation and Language · Computer Science 2024-05-22 Charles O'Neill , Thang Bui

Multilingual language models achieve strong aggregate performance yet often behave unpredictably across languages, scripts, and cultures. We argue that mechanistic explanations for such models should satisfy a \emph{causal} standard: claims…

Computation and Language · Computer Science 2026-01-01 Yanan Long

Mechanistic interpretability research seeks to reveal the inner workings of large language models, yet most work focuses on classification or generative tasks rather than summarization. This paper presents an interpretability framework for…

Computation and Language · Computer Science 2025-05-26 Anurag Mishra

The role of Large Language Models (LLMs) has not been extensively explored in analog circuit design, which could benefit from a reasoning-based approach that transcends traditional optimization techniques. In particular, despite their…

Machine Learning · Computer Science 2025-02-13 Lejla Skelic , Yan Xu , Matthew Cox , Wenjie Lu , Tao Yu , Ruonan Han

CLIP is one of the most popular foundational models and is heavily used for many vision-language tasks. However, little is known about the inner workings of CLIP. To bridge this gap we propose a study to quantify the interpretability in…

Computer Vision and Pattern Recognition · Computer Science 2024-09-11 Avinash Madasu , Yossi Gandelsman , Vasudev Lal , Phillip Howard

Many proposed applications of neural networks in machine learning, cognitive/brain science, and society hinge on the feasibility of inner interpretability via circuit discovery. This calls for empirical and theoretical explorations of…

Artificial Intelligence · Computer Science 2025-04-02 Federico Adolfi , Martina G. Vilas , Todd Wareham

We present causal head gating (CHG), a scalable method for interpreting the functional roles of attention heads in transformer models. CHG learns soft gates over heads and assigns them a causal taxonomy - facilitating, interfering, or…

Artificial Intelligence · Computer Science 2025-10-27 Andrew Nam , Henry Conklin , Yukang Yang , Thomas Griffiths , Jonathan Cohen , Sarah-Jane Leslie

Large Language Models (LLMs) have shown impressive performance across a wide range of tasks. However, the size of LLMs is steadily increasing, hindering their application on computationally constrained environments. On the other hand,…

Machine Learning · Computer Science 2024-12-23 Jorge García-Carrasco , Alejandro Maté , Juan Trujillo

This paper tests whether large language models (LLMs) can support interpretative citation context analysis (CCA) by scaling in thick, text-grounded readings of a single hard case rather than scaling up typological labels. It foregrounds…

Computation and Language · Computer Science 2026-02-27 Arno Simons
‹ Prev 1 2 3 10 Next ›