English
Related papers

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

200 papers

Knowledge augmentation has significantly enhanced the performance of Large Language Models (LLMs) in knowledge-intensive tasks. However, existing methods typically operate on the simplistic premise that model performance equates with…

Computation and Language · Computer Science 2026-02-16 Hao Chen , Ye He , Yuchun Fan , Yukun Yan , Zhenghao Liu , Qingfu Zhu , Maosong Sun , Wanxiang Che

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

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

Large language models (LLMs) encode vast amounts of knowledge during pre-training (parametric knowledge, or PK) and can further be enhanced by incorporating contextual knowledge (CK). Can LLMs effectively integrate their internal PK with…

Computation and Language · Computer Science 2024-10-16 Sitao Cheng , Liangming Pan , Xunjian Yin , Xinyi Wang , William Yang Wang

The proliferation of large language models (LLMs) has significantly advanced intelligent systems. Unfortunately, LLMs often face knowledge conflicts between internal memory and retrieved external information, arising from misinformation,…

Computation and Language · Computer Science 2025-11-18 Jiatai Wang , Zhiwei Xu , Di Jin , Xuewen Yang , Tao Li

Large language models (LLMs) have had a huge impact on society due to their impressive capabilities and vast knowledge of the world. Various applications and tools have been created that allow users to interact with these models in a…

Artificial Intelligence · Computer Science 2023-09-25 Eric Nuertey Coleman , Julio Hurtado , Vincenzo Lomonaco

Large language models (LLMs) acquire knowledge across diverse domains such as science, history, and geography encountered during generative pre-training. However, due to their stochasticity, it is difficult to predict what LLMs have…

Computation and Language · Computer Science 2026-01-27 Kartik Sharma , Yiqiao Jin , Rakshit Trivedi , Srijan Kumar

Methods for knowledge editing and unlearning in large language models seek to edit or remove undesirable knowledge or capabilities without compromising general language modeling performance. This work investigates how mechanistic…

Machine Learning · Computer Science 2024-12-06 Phillip Guo , Aaquib Syed , Abhay Sheshadri , Aidan Ewart , Gintare Karolina Dziugaite

Previous works show that Pre-trained Language Models (PLMs) can capture factual knowledge. However, some analyses reveal that PLMs fail to perform it robustly, e.g., being sensitive to the changes of prompts when extracting factual…

Computation and Language · Computer Science 2022-10-21 Shaobo Li , Xiaoguang Li , Lifeng Shang , Chengjie Sun , Bingquan Liu , Zhenzhou Ji , Xin Jiang , Qun Liu

The behavior of Large Language Models (LLMs) when facing contextual information that conflicts with their internal parametric knowledge is inconsistent, with no generally accepted explanation for the expected outcome distribution. Recent…

Computation and Language · Computer Science 2025-09-18 Zineddine Tighidet , Andrea Mogini , Hedi Ben-younes , Jiali Mei , Patrick Gallinari , Benjamin Piwowarski

Large language models (LLMs) frequently encode factual and reasoning knowledge in their internal representations that is not faithfully reflected in their surface-level outputs -- a phenomenon known as \emph{latent knowledge}. Existing…

Computation and Language · Computer Science 2026-05-29 Ji-jun Park , Soo-joon Choi , Jiwon Jeong , Taeyang Yoon , Ju-Wan Lee

Large Language Models (LLMs) store an extensive amount of factual knowledge obtained from vast collections of text. To effectively utilize these models for downstream tasks, it is crucial to have reliable methods for measuring their…

Computation and Language · Computer Science 2023-06-13 Pouya Pezeshkpour

Large language models (LLMs) can store a vast amount of world knowledge, often extractable via question-answering (e.g., "What is Abraham Lincoln's birthday?"). However, do they answer such questions based on exposure to similar questions…

Computation and Language · Computer Science 2024-07-17 Zeyuan Allen-Zhu , Yuanzhi Li

Scaling large language models (LLMs) leads to an emergent capacity to learn in-context from example demonstrations. Despite progress, theoretical understanding of this phenomenon remains limited. We argue that in-context learning relies on…

Computation and Language · Computer Science 2023-03-15 Michael Hahn , Navin Goyal

In the context of knowledge-driven seq-to-seq generation tasks, such as document-based question answering and document summarization systems, two fundamental knowledge sources play crucial roles: the inherent knowledge embedded within model…

Computation and Language · Computer Science 2025-01-16 Han Cao , Zhaoyang Zhang , Xiangtian Li , Chufan Wu , Hansong Zhang , Wenqing Zhang

Large language models (LLMs) have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque. Mechanistic interpretability (i.e., the systematic study of how neural networks…

Computation and Language · Computer Science 2026-02-13 Usman Naseem

Knowledge conflicts commonly arise across diverse sources, and their prevalence has increased with the advent of LLMs. When dealing with conflicts between multiple contexts, also known as \emph{inter-context knowledge conflicts}, LLMs are…

Artificial Intelligence · Computer Science 2025-08-06 Xianda Zheng , Zijian Huang , Meng-Fen Chiang , Michael J. Witbrock , Kaiqi Zhao

Training Large Language Models (LLMs) with high multilingual coverage is becoming increasingly important -- especially when monolingual resources are scarce. Recent studies have found that LLMs process multilingual inputs in shared concept…

Computation and Language · Computer Science 2026-02-02 Felicia Körner , Max Müller-Eberstein , Anna Korhonen , Barbara Plank

Relational knowledge bases (KBs) are commonly used to represent world knowledge in machines. However, while advantageous for their high degree of precision and interpretability, KBs are usually organized according to manually-defined…

Computation and Language · Computer Science 2021-09-13 Tara Safavi , Danai Koutra

Despite exceptional capabilities in knowledge-intensive tasks, Large Language Models (LLMs) face a critical gap in understanding how they internalize new knowledge, particularly how to structurally embed acquired knowledge in their neural…

Machine Learning · Computer Science 2025-06-03 Yixin Ou , Yunzhi Yao , Ningyu Zhang , Hui Jin , Jiacheng Sun , Shumin Deng , Zhenguo Li , Huajun Chen