English
Related papers

Related papers: Knowledge Circuits in Pretrained Transformers

200 papers

Induction head mechanism is a part of the computational circuits for in-context learning (ICL) that enable large language models (LLMs) to adapt to new tasks without fine-tuning. Most existing work explains the training dynamics behind…

Computation and Language · Computer Science 2025-07-09 Shuo Wang , Issei Sato

What do large language models actually model? Do they tell us something about human capacities, or are they models of the corpus we've trained them on? I give a non-deflationary defence of the latter position. Cognitive science tells us…

Computation and Language · Computer Science 2025-08-27 Colin Klein

Large Language Models have rapidly advanced in their ability to interpret and generate natural language. In enterprise settings, they are frequently augmented with closed-source domain knowledge to deliver more contextually informed…

Computation and Language · Computer Science 2025-12-03 Tanmay Agrawal

Recent days have witnessed a diverse set of knowledge injection models for pre-trained language models (PTMs); however, most previous studies neglect the PTMs' own ability with quantities of implicit knowledge stored in parameters. A recent…

Computation and Language · Computer Science 2023-01-26 Yunzhi Yao , Shaohan Huang , Li Dong , Furu Wei , Huajun Chen , Ningyu Zhang

Understanding the mechanisms of information storage and transfer in Transformer-based models is important for driving model understanding progress. Recent work has studied these mechanisms for Large Language Models (LLMs), revealing…

Computer Vision and Pattern Recognition · Computer Science 2024-06-07 Samyadeep Basu , Martin Grayson , Cecily Morrison , Besmira Nushi , Soheil Feizi , Daniela Massiceti

Large-scale pretrained language models are surprisingly good at recalling factual knowledge presented in the training corpus. In this paper, we present preliminary studies on how factual knowledge is stored in pretrained Transformers by…

Computation and Language · Computer Science 2022-03-11 Damai Dai , Li Dong , Yaru Hao , Zhifang Sui , Baobao Chang , Furu Wei

To what extent can a neural network systematically reason over symbolic facts? Evidence suggests that large pre-trained language models (LMs) acquire some reasoning capacity, but this ability is difficult to control. Recently, it has been…

Computation and Language · Computer Science 2020-11-17 Alon Talmor , Oyvind Tafjord , Peter Clark , Yoav Goldberg , Jonathan Berant

Large language models (LLMs) have shown remarkable performances across a wide range of tasks. However, the mechanisms by which these models encode tasks of varying complexities remain poorly understood. In this paper, we explore the…

Computation and Language · Computer Science 2025-02-06 Mingyu Jin , Qinkai Yu , Jingyuan Huang , Qingcheng Zeng , Zhenting Wang , Wenyue Hua , Haiyan Zhao , Kai Mei , Yanda Meng , Kaize Ding , Fan Yang , Mengnan Du , Yongfeng Zhang

In many reasoning tasks, large language models (LLMs) rely on structured external knowledge, such as graphs and tables, which is typically linearized into sequential token representations. However, even when sufficient knowledge is…

Computation and Language · Computer Science 2026-05-27 Shanghao Li , Jinda Han , Yibo Wang , Yuanjie Zhu , Zihe Song , Langzhou He , Kenan Kamel A Alghythee , Philip S. Yu

Knowledge Editing (KE) enables the modification of outdated or incorrect information in large language models (LLMs). While existing KE methods can update isolated facts, they often fail to generalize these updates to multi-hop reasoning…

Computation and Language · Computer Science 2025-11-21 Yunzhi Yao , Jizhan Fang , Jia-Chen Gu , Ningyu Zhang , Shumin Deng , Huajun Chen , Nanyun Peng

Passage re-ranking is to obtain a permutation over the candidate passage set from retrieval stage. Re-rankers have been boomed by Pre-trained Language Models (PLMs) due to their overwhelming advantages in natural language understanding.…

Information Retrieval · Computer Science 2022-04-26 Qian Dong , Yiding Liu , Suqi Cheng , Shuaiqiang Wang , Zhicong Cheng , Shuzi Niu , Dawei Yin

Large language models may encounter factual knowledge during pre-training yet fail to reliably use that knowledge after fine-tuning. Despite growing empirical evidence that MLP layers store factual associations and fine-tuning affects…

Machine Learning · Computer Science 2026-05-19 Ruichen Xu , Kexin Chen

Despite significant achievements in improving the instruction-following capabilities of large language models (LLMs), the ability to process multiple potentially entangled or conflicting instructions remains a considerable challenge.…

Pre-trained language models learn informative word representations on a large-scale text corpus through self-supervised learning, which has achieved promising performance in fields of natural language processing (NLP) after fine-tuning.…

Computation and Language · Computer Science 2023-10-31 Jian Yang , Xinyu Hu , Gang Xiao , Yulong Shen

Human languages are full of metaphorical expressions. Metaphors help people understand the world by connecting new concepts and domains to more familiar ones. Large pre-trained language models (PLMs) are therefore assumed to encode…

Computation and Language · Computer Science 2022-03-29 Ehsan Aghazadeh , Mohsen Fayyaz , Yadollah Yaghoobzadeh

We present a systematic review of 337 articles evaluating the syntactic abilities of Transformer-based language models (TLMs), reporting on over 3,000 datapoints spanning a wide range of syntactic phenomena, languages, models, and methods.…

Computation and Language · Computer Science 2026-05-28 Nora Graichen , Iria de-Dios-Flores , Gemma Boleda

Large language models (LLMs) often benefit from intermediate steps of reasoning to generate answers to complex problems. When these intermediate steps of reasoning are used to monitor the activity of the model, it is essential that this…

Machine Learning · Computer Science 2023-11-02 Fabien Roger , Ryan Greenblatt

Large language models (LLMs) are increasingly deployed on complex reasoning tasks, yet little is known about their ability to internally evaluate problem difficulty, which is an essential capability for adaptive reasoning and efficient…

Computation and Language · Computer Science 2025-10-14 Sunbowen Lee , Qingyu Yin , Chak Tou Leong , Jialiang Zhang , Yicheng Gong , Shiwen Ni , Min Yang , Xiaoyu Shen

When large language models (LLMs) use in-context learning (ICL) to solve a new task, they must infer latent concepts from demonstration examples. This raises the question of whether and how transformers represent latent structures as part…

Machine Learning · Computer Science 2025-09-29 Guan Zhe Hong , Bhavya Vasudeva , Vatsal Sharan , Cyrus Rashtchian , Prabhakar Raghavan , Rina Panigrahy

Since the advent of ChatGPT, Large Language Models (LLMs) have excelled in various tasks but remain as black-box systems. Understanding the reasoning bottlenecks of LLMs has become a critical challenge, as these limitations are deeply tied…

Computation and Language · Computer Science 2024-12-24 Zifan Zheng , Yezhaohui Wang , Yuxin Huang , Shichao Song , Mingchuan Yang , Bo Tang , Feiyu Xiong , Zhiyu Li