English
Related papers

Related papers: Where Knowledge Collides: A Mechanistic Study of I…

200 papers

Large Language Models (LLMs) trained on web-scale text corpora have been shown to capture world knowledge in their parameters. However, the mechanism by which language models store different types of knowledge is poorly understood. In this…

Computation and Language · Computer Science 2024-11-08 Jared Fernandez , Yonatan Bisk , Emma Strubell

Previous works show the great potential of pre-trained language models (PLMs) for storing a large amount of factual knowledge. However, to figure out whether PLMs can be reliable knowledge sources and used as alternative knowledge bases…

Computation and Language · Computer Science 2022-03-01 Daniel Gao , Yantao Jia , Lei Li , Chengzhen Fu , Zhicheng Dou , Hao Jiang , Xinyu Zhang , Lei Chen , Zhao Cao

Language Models (LMs) often encounter knowledge conflicts when parametric memory contradicts contextual knowledge. Previous works attribute this conflict to the interplay between "memory heads" and "context heads", attention heads assumed…

Computation and Language · Computer Science 2025-06-09 Gaotang Li , Yuzhong Chen , Hanghang Tong

Pre-trained language models (LMs) are used for knowledge intensive tasks like question answering, but their knowledge gets continuously outdated as the world changes. Prior work has studied targeted updates to LMs, injecting individual…

Computation and Language · Computer Science 2023-05-03 Yasumasa Onoe , Michael J. Q. Zhang , Shankar Padmanabhan , Greg Durrett , Eunsol Choi

The recent advancements in auto-regressive multimodal large language models (MLLMs) have demonstrated promising progress for vision-language tasks. While there exists a variety of studies investigating the processing of linguistic…

Artificial Intelligence · Computer Science 2025-03-28 Zhi Zhang , Srishti Yadav , Fengze Han , Ekaterina Shutova

Large Language Models (LLMs) struggle with dynamic knowledge updates, especially when new information conflicts with deeply embedded facts. Such conflicting factual edits often lead to two critical issues: resistance to adopting the new…

Machine Learning · Computer Science 2025-08-12 Stanley Ngugi

Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in multimodal tasks, but their performance is often constrained by the lack of external knowledge integration, limiting their ability to handle…

Computation and Language · Computer Science 2025-01-16 Julian Perry , Surasakdi Siripong , Thanakorn Phonchai

Fine-tuned Large Language Models (LLMs) often demonstrate poor calibration, with their confidence scores misaligned with actual performance. While calibration has been extensively studied in models trained from scratch, the impact of LLMs'…

Computation and Language · Computer Science 2025-05-28 Ziming Wang , Zeyu Shi , Haoyi Zhou , Shiqi Gao , Qingyun Sun , Jianxin Li

Recent research demonstrates that external knowledge injection can advance pre-trained language models (PLMs) in a variety of downstream NLP tasks. However, existing knowledge injection methods are either applicable to structured knowledge…

Computation and Language · Computer Science 2023-05-08 Deming Ye , Yankai Lin , Zhengyan Zhang , Maosong Sun

For Large Language Models (LLMs) to be reliable, they must learn robust knowledge that can be generally applied in diverse settings -- often unlike those seen during training. Yet, extensive research has shown that LLM performance can be…

Computation and Language · Computer Science 2025-10-15 Patrick Haller , Mark Ibrahim , Polina Kirichenko , Levent Sagun , Samuel J. Bell

It is widely acknowledged that large language models (LLMs) encode a vast reservoir of knowledge after being trained on mass data. Recent studies disclose knowledge conflicts in LLM generation, wherein outdated or incorrect parametric…

Computation and Language · Computer Science 2024-11-15 Dan Shi , Renren Jin , Tianhao Shen , Weilong Dong , Xinwei Wu , Deyi Xiong

Large language models (LLMs) acquire a large amount of knowledge through pre-training on vast and diverse corpora. While this endows LLMs with strong capabilities in generation and reasoning, it amplifies risks associated with sensitive,…

Cryptography and Security · Computer Science 2026-02-25 Ce Fang , Zhikun Zhang , Min Chen , Qing Liu , Lu Zhou , Zhe Liu , Yunjun Gao

Large language models (LLMs) store vast amounts of knowledge, which often requires updates to correct factual errors, incorporate newly acquired information, or adapt model behavior. Model editing methods have emerged as efficient solutions…

Computation and Language · Computer Science 2025-10-27 Fufang Wen , Shichang Zhang

Large language models (LMs) such as GPT-3 have the surprising ability to do in-context learning, where the model learns to do a downstream task simply by conditioning on a prompt consisting of input-output examples. The LM learns from these…

Computation and Language · Computer Science 2022-07-22 Sang Michael Xie , Aditi Raghunathan , Percy Liang , Tengyu Ma

Language models retain a significant amount of world knowledge from their pre-training stage. This allows knowledgeable models to be applied to knowledge-intensive tasks prevalent in information retrieval, such as ranking or question…

Computation and Language · Computer Science 2023-06-13 Jonas Wallat , Tianyi Zhang , Avishek Anand

Despite the recent observation that large language models (LLMs) can store substantial factual knowledge, there is a limited understanding of the mechanisms of how they acquire factual knowledge through pretraining. This work addresses this…

Computation and Language · Computer Science 2024-11-13 Hoyeon Chang , Jinho Park , Seonghyeon Ye , Sohee Yang , Youngkyung Seo , Du-Seong Chang , Minjoon Seo

As large language models (LLMs) are applied across diverse domains, the ability to selectively unlearn specific information is becoming increasingly essential. For instance, LLMs are expected to selectively provide confidential information…

Computation and Language · Computer Science 2025-06-04 Shota Takashiro , Takeshi Kojima , Andrew Gambardella , Qi Cao , Yusuke Iwasawa , Yutaka Matsuo

The remarkable capabilities of modern large language models are rooted in their vast repositories of knowledge encoded within their parameters, enabling them to perceive the world and engage in reasoning. The inner workings of how these…

Computation and Language · Computer Science 2025-01-06 Yunzhi Yao , Ningyu Zhang , Zekun Xi , Mengru Wang , Ziwen Xu , Shumin Deng , Huajun Chen

Large Language Models (LLMs), characterized by being trained on broad amounts of data in a self-supervised manner, have shown impressive performance across a wide range of tasks. Indeed, their generative abilities have aroused interest on…

Machine Learning · Computer Science 2024-07-30 Jorge García-Carrasco , Alejandro Maté , Juan Trujillo

Post-training is essential for the success of large language models (LLMs), transforming pre-trained base models into more useful and aligned post-trained models. While plenty of works have studied post-training algorithms and evaluated…

Computation and Language · Computer Science 2025-11-11 Hongzhe Du , Weikai Li , Min Cai , Karim Saraipour , Zimin Zhang , Himabindu Lakkaraju , Yizhou Sun , Shichang Zhang