English
Related papers

Related papers: Adaptive Circuit Behavior and Generalization in Me…

200 papers

While Large Language Models (LLMs) excel at factual retrieval, they often struggle with the "curse of two-hop reasoning" in compositional tasks. Recent research suggests that parameter-sharing transformers can bridge this gap by forming a…

Computation and Language · Computer Science 2026-01-15 Kaiyu He , Zhang Mian , Peilin Wu , Xinya Du , Zhiyu Chen

Understanding AI systems' inner workings is critical for ensuring value alignment and safety. This review explores mechanistic interpretability: reverse engineering the computational mechanisms and representations learned by neural networks…

Artificial Intelligence · Computer Science 2024-08-27 Leonard Bereska , Efstratios Gavves

Mechanistic interpretability work attempts to reverse engineer the learned algorithms present inside neural networks. One focus of this work has been to discover 'circuits' -- subgraphs of the full model that explain behaviour on specific…

Machine Learning · Computer Science 2024-07-12 Joseph Miller , Bilal Chughtai , William Saunders

We introduce methods for discovering and applying sparse feature circuits. These are causally implicated subnetworks of human-interpretable features for explaining language model behaviors. Circuits identified in prior work consist of…

Machine Learning · Computer Science 2025-03-28 Samuel Marks , Can Rager , Eric J. Michaud , Yonatan Belinkov , David Bau , Aaron Mueller

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

Mechanistic interpretability aims to reverse engineer the computation performed by a neural network in terms of its internal components. Although there is a growing body of research on mechanistic interpretation of neural networks, the…

Machine Learning · Computer Science 2025-06-24 Nils Palumbo , Ravi Mangal , Zifan Wang , Saranya Vijayakumar , Corina S. Pasareanu , Somesh Jha

Research on Large Language Models (LLMs) increasingly focuses on identifying mechanistic explanations for their behaviors, yet the field lacks clear principles for determining when (and how) findings from one model instance generalize to…

Artificial Intelligence · Computer Science 2025-09-30 Sean Trott

Mechanistic interpretability has transformed the analysis of transformer circuits by decomposing model behavior into competing algorithms, identifying phase transitions during training, and deriving closed-form predictions for when and why…

Machine Learning · Computer Science 2026-03-19 Alma Lago

Large Language Models (LLMs) exhibit remarkable capabilities across a spectrum of tasks in financial services, including report generation, chatbots, sentiment analysis, regulatory compliance, investment advisory, financial knowledge…

Computational Engineering, Finance, and Science · Computer Science 2025-06-02 Hariom Tatsat , Ariye Shater

We study implicit reasoning, i.e. the ability to combine knowledge or rules within a single forward pass. While transformer-based large language models store substantial factual knowledge and rules, they often fail to compose this knowledge…

Computation and Language · Computer Science 2026-04-10 Harsh Kohli , Srinivasan Parthasarathy , Huan Sun , Yuekun Yao

In-context learning (ICL) refers to a remarkable capability of pretrained large language models, which can learn a new task given a few examples during inference. However, theoretical understanding of ICL is largely under-explored,…

Machine Learning · Computer Science 2024-09-27 Tong Yang , Yu Huang , Yingbin Liang , Yuejie Chi

Mechanistic interpretability has identified small sets of attention heads that implement specific behaviours in transformer language models, but recovering these circuits typically requires a bespoke analytical pipeline for each new task.…

Machine Learning · Computer Science 2026-05-27 Barsat Khadka

In-context learning (ICL) has emerged as a powerful paradigm for easily adapting Large Language Models (LLMs) to various tasks. However, our understanding of how ICL works remains limited. We explore a simple model of ICL in a controlled…

Machine Learning · Computer Science 2025-09-03 Omar Naim , Guilhem Fouilhé , Nicholas Asher

Soft prompts have been popularized as a cheap and easy way to improve task-specific LLM performance beyond few-shot prompts. Despite their origin as an automated prompting method, however, soft prompts and other trainable prompts remain a…

Machine Learning · Computer Science 2025-04-04 Oam Patel , Jason Wang , Nikhil Shivakumar Nayak , Suraj Srinivas , Himabindu Lakkaraju

Large natural language models (such as GPT-3 or T5) demonstrate impressive abilities across a range of general NLP tasks. Here, we show that the knowledge embedded in such models provides a useful inductive bias, not just on traditional NLP…

Computation and Language · Computer Science 2021-10-07 Christopher Michael Rytting , David Wingate

Large language models (LLMs) have achieved remarkable proficiency on solving diverse problems. However, their generalization ability is not always satisfying and the generalization problem is common for generative transformer models in…

Machine Learning · Computer Science 2024-08-20 Xingcheng Xu , Zihao Pan , Haipeng Zhang , Yanqing Yang

Inspired by recent strides in empirical efficacy of implicit learning in many robotics tasks, we seek to understand the theoretical benefits of implicit formulations in the face of nearly discontinuous functions, common characteristics for…

Robotics · Computer Science 2022-04-08 Bibit Bianchini , Mathew Halm , Nikolai Matni , Michael Posa

Recent advancements in cognitive science and multi-round reasoning techniques for Large Language Models (LLMs) suggest that iterative thinking processes improve problem-solving performance in complex tasks. Inspired by this, approaches like…

Artificial Intelligence · Computer Science 2025-03-06 Chenhui Xu , Dancheng Liu , Jiajie Li , Amir Nassereldine , Zhaohui Li , Jinjun Xiong

Universality is a key hypothesis in mechanistic interpretability -- that different models learn similar features and circuits when trained on similar tasks. In this work, we study the universality hypothesis by examining how small neural…

Machine Learning · Computer Science 2023-05-26 Bilal Chughtai , Lawrence Chan , Neel Nanda

Mechanistic interpretability (MI) is an emerging sub-field of interpretability that seeks to understand a neural network model by reverse-engineering its internal computations. Recently, MI has garnered significant attention for…

Artificial Intelligence · Computer Science 2025-10-14 Daking Rai , Yilun Zhou , Shi Feng , Abulhair Saparov , Ziyu Yao