English
Related papers

Related papers: Knowledge Circuits in Pretrained Transformers

200 papers

This paper examines the capacity of LLMs to reason with knowledge graphs using their internal knowledge graph, i.e., the knowledge graph they learned during pre-training. Two research questions are formulated to investigate the accuracy of…

Computation and Language · Computer Science 2023-12-04 Pei-Chi Lo , Yi-Hang Tsai , Ee-Peng Lim , San-Yih Hwang

Knowledge plays a critical role in artificial intelligence. Recently, the extensive success of pre-trained language models (PLMs) has raised significant attention about how knowledge can be acquired, maintained, updated and used by language…

Computation and Language · Computer Science 2024-04-04 Boxi Cao , Hongyu Lin , Xianpei Han , Le Sun

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

Recent studies on reasoning in language models (LMs) have sparked a debate on whether they can learn systematic inferential principles or merely exploit superficial patterns in the training data. To understand and uncover the mechanisms…

Computation and Language · Computer Science 2025-06-24 Geonhee Kim , Marco Valentino , André Freitas

Recent advances in interpretability suggest we can project weights and hidden states of transformer-based language models (LMs) to their vocabulary, a transformation that makes them more human interpretable. In this paper, we investigate LM…

Computation and Language · Computer Science 2023-11-27 Shahar Katz , Yonatan Belinkov

Large Language Models (LLMs) inherently encode a wealth of knowledge within their parameters through pre-training on extensive corpora. While prior research has delved into operations on these parameters to manipulate the underlying…

Computation and Language · Computer Science 2024-05-09 Ming Zhong , Chenxin An , Weizhu Chen , Jiawei Han , Pengcheng He

Concepts play a pivotal role in various human cognitive functions, including learning, reasoning and communication. However, there is very little work on endowing machines with the ability to form and reason with concepts. In particular,…

Computation and Language · Computer Science 2023-11-06 Chen Shani , Jilles Vreeken , Dafna Shahaf

We propose a novel framework ConceptX, to analyze how latent concepts are encoded in representations learned within pre-trained language models. It uses clustering to discover the encoded concepts and explains them by aligning with a large…

Computation and Language · Computer Science 2022-06-28 Hassan Sajjad , Nadir Durrani , Fahim Dalvi , Firoj Alam , Abdul Rafae Khan , Jia Xu

Pre-trained language models (PLMs) contain vast amounts of factual knowledge, but how the knowledge is stored in the parameters remains unclear. This paper delves into the complex task of understanding how factual knowledge is stored in…

Computation and Language · Computer Science 2023-12-21 Yuheng Chen , Pengfei Cao , Yubo Chen , Kang Liu , Jun Zhao

Although large language models (LLMs) have demonstrated remarkable performance, the lack of transparency in their inference logic raises concerns about their trustworthiness. To gain a better understanding of LLMs, we conduct a detailed…

Computation and Language · Computer Science 2024-07-26 Jie Ren , Qipeng Guo , Hang Yan , Dongrui Liu , Quanshi Zhang , Xipeng Qiu , Dahua Lin

Transformer-based language models exhibit complex and distributed behavior, yet their internal computations remain poorly understood. Existing mechanistic interpretability methods typically treat attention heads and multilayer perceptron…

Machine Learning · Computer Science 2025-11-26 Areeb Ahmad , Abhinav Joshi , Ashutosh Modi

Pretraining on large, semantically rich datasets is key for developing language models. Surprisingly, recent studies have shown that even synthetic data, generated procedurally through simple semantic-free algorithms, can yield some of the…

Machine Learning · Computer Science 2025-05-29 Zachary Shinnick , Liangze Jiang , Hemanth Saratchandran , Anton van den Hengel , Damien Teney

In recent years, transformer-based language models have achieved state of the art performance in various NLP benchmarks. These models are able to extract mostly distributional information with some semantics from unstructured text, however…

Computation and Language · Computer Science 2021-02-08 Pedro Colon-Hernandez , Catherine Havasi , Jason Alonso , Matthew Huggins , Cynthia Breazeal

How much knowledge do pretrained language models hold? Recent research observed that pretrained transformers are adept at modeling semantics but it is unclear to what degree they grasp human knowledge, or how to ensure they do so. In this…

Computation and Language · Computer Science 2021-02-05 Corby Rosset , Chenyan Xiong , Minh Phan , Xia Song , Paul Bennett , Saurabh Tiwary

Large Vision-Language Models (LVLMs) represent a significant leap towards empathetic agents, demonstrating remarkable capabilities in emotion understanding. However, the internal mechanisms governing how LVLMs translate abstract visual…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Chengsheng Zhang , Chenghao Sun , Zhining Xie , Xinmei Tian

Vision-language models (VLMs) are powerful but remain opaque black boxes. We introduce the first framework for transparent circuit tracing in VLMs to systematically analyze multimodal reasoning. By utilizing transcoders, attribution graphs,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Jingcheng Yang , Tianhu Xiong , Shengyi Qian , Klara Nahrstedt , Mingyuan Wu

Understanding the internal mechanisms by which multi-modal large language models (LLMs) interpret different modalities and integrate cross-modal representations is becoming increasingly critical for continuous improvements in both academia…

Computation and Language · Computer Science 2024-06-12 Haowen Pan , Yixin Cao , Xiaozhi Wang , Xun Yang , Meng Wang

Although it is known that transformer language models (LMs) pass features from early layers to later layers, it is not well understood how this information is represented and routed by the model. We analyze a mechanism used in two LMs to…

Computation and Language · Computer Science 2025-05-12 Jack Merullo , Carsten Eickhoff , Ellie Pavlick

Fine-tuning pre-trained large language models (LLMs) on a diverse array of tasks has become a common approach for building models that can solve various natural language processing (NLP) tasks. However, where and to what extent these models…

Computation and Language · Computer Science 2024-10-29 Zheng Zhao , Yftah Ziser , Shay B. Cohen

Large language models (LLMs) have shown remarkable capabilities across various tasks, that are learned from massive amounts of text-based data. Although LLMs can control output sequence length, particularly in instruction-based settings,…

Computation and Language · Computer Science 2025-08-22 Sangjun Moon , Dasom Choi , Jingun Kwon , Hidetaka Kamigaito , Manabu Okumura