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