English
Related papers

Related papers: Identifying a Circuit for Verb Conjugation in GPT-…

200 papers

Several algorithms implemented by language models have recently been successfully reversed-engineered. However, these findings have been concentrated on specific tasks and models, leaving it unclear how universal circuits are across…

Computation and Language · Computer Science 2024-10-10 Javier Ferrando , Marta R. Costa-jussà

Neural network models have achieved high performance on a wide variety of complex tasks, but the algorithms that they implement are notoriously difficult to interpret. It is often necessary to hypothesize intermediate variables involved in…

Computation and Language · Computer Science 2025-02-13 Michael A. Lepori , Thomas Serre , Ellie Pavlick

This case study investigates the extent to which a language model (GPT-2) is able to capture native speakers' intuitions about implicit causality in a sentence completion task. We first reproduce earlier results (showing lower surprisal…

Computation and Language · Computer Science 2022-12-09 Hien Huynh , Tomas O. Lentz , Emiel van Miltenburg

While transformer models exhibit strong capabilities on linguistic tasks, their complex architectures make them difficult to interpret. Recent work has aimed to reverse engineer transformer models into human-readable representations called…

Computation and Language · Computer Science 2024-10-08 Michael Lan , Philip Torr , Fazl Barez

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

A fundamental question in interpretability research is to what extent neural networks, particularly language models, implement reusable functions through subnetworks that can be composed to perform more complex tasks. Recent advances in…

Machine Learning · Computer Science 2025-06-24 Philipp Mondorf , Sondre Wold , Barbara Plank

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

Which components in transformer language models are responsible for discourse understanding? We hypothesize that sparse computational graphs, termed as discursive circuits, control how models process discourse relations. Unlike simpler…

Computation and Language · Computer Science 2025-10-14 Yisong Miao , Min-Yen Kan

Understanding the internal circuits that language models use to solve tasks remains a central challenge in mechanistic interpretability. A crucial part of finding circuits is understanding why each attention head attends where it does. To…

Machine Learning · Computer Science 2026-05-15 Gabriel Franco , Lucas M. Tassis , Azalea Rohr , Mark Crovella

Mechanistic interpretability aims to understand the inner workings of large neural networks by identifying circuits, or minimal subgraphs within the model that implement algorithms responsible for performing specific tasks. These circuits…

Machine Learning · Computer Science 2024-12-06 Jatin Nainani , Sankaran Vaidyanathan , AJ Yeung , Kartik Gupta , David Jensen

Language models often exhibit behaviors that improve performance on a pre-training objective but harm performance on downstream tasks. We propose a novel approach to removing undesirable behaviors by ablating a small number of causal…

Computation and Language · Computer Science 2024-01-31 Maximilian Li , Xander Davies , Max Nadeau

Verbs form the backbone of language, providing the structure and meaning to sentences. Yet, their intricate semantic nuances pose a longstanding challenge. Understanding verb relations through the concept of lexical entailment is crucial…

Computation and Language · Computer Science 2024-11-08 Candida M. Greco , Lucio La Cava , Andrea Tagarelli

GPT-3 can perform numerous tasks when provided a natural language prompt that contains a few training examples. We show that this type of few-shot learning can be unstable: the choice of prompt format, training examples, and even the order…

Computation and Language · Computer Science 2021-06-14 Tony Z. Zhao , Eric Wallace , Shi Feng , Dan Klein , Sameer Singh

Language models (LMs) exhibit and amplify many types of undesirable biases learned from the training data, including gender bias. However, we lack tools for effectively and efficiently changing this behavior without hurting general language…

Computation and Language · Computer Science 2023-10-20 Abhijith Chintam , Rahel Beloch , Willem Zuidema , Michael Hanna , Oskar van der Wal

Many papers have shown that attention heads work in conjunction with each other to perform complex tasks. It's frequently assumed that communication between attention heads is via the addition of specific features to token residuals. In…

Machine Learning · Computer Science 2024-10-30 Gabriel Franco , Mark Crovella

Explaining neural network models is important for increasing their trustworthiness in real-world applications. Most existing methods generate post-hoc explanations for neural network models by identifying individual feature attributions or…

Computation and Language · Computer Science 2021-04-14 Hanjie Chen , Song Feng , Jatin Ganhotra , Hui Wan , Chulaka Gunasekara , Sachindra Joshi , Yangfeng Ji

Recent advances in language model interpretability have identified circuits, critical subnetworks that replicate model behaviors, yet how knowledge is structured within these crucial subnetworks remains opaque. To gain an understanding…

Computation and Language · Computer Science 2025-07-17 Huaizhi Ge , Frank Rudzicz , Zining Zhu

Transformer-based language models have achieved significant success; however, their internal mechanisms remain largely opaque due to the complexity of non-linear interactions and high-dimensional operations. While previous studies have…

Artificial Intelligence · Computer Science 2025-02-17 Lin Zhang , Lijie Hu , Di Wang

Through considerable effort and intuition, several recent works have reverse-engineered nontrivial behaviors of transformer models. This paper systematizes the mechanistic interpretability process they followed. First, researchers choose a…

Machine Learning · Computer Science 2023-10-31 Arthur Conmy , Augustine N. Mavor-Parker , Aengus Lynch , Stefan Heimersheim , Adrià Garriga-Alonso

Circuit graph discovery has emerged as a fundamental approach to elucidating the skill mechanistic of language models. Despite the output faithfulness of circuit graphs, they suffer from atomic ablation, which causes the loss of causal…

Computation and Language · Computer Science 2025-11-11 Hang Chen , Jiaying Zhu , Xinyu Yang , Wenya Wang
‹ Prev 1 2 3 10 Next ›