相关论文: Vector Arithmetic in Concept and Token Subspaces

Large Language Models (LLMs) often generate incorrect or unsupported content, known as hallucinations. Existing detection methods rely on heuristics or simple models over isolated computational traces such as activations, or attention maps.…

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Language models (LMs) struggle to perform such reasoning consistently. We propose an approach to pinpoint and rectify multi-hop…

Using Large Language Models (LLMs) to process graph-structured data is an active research area, yet current state-of-the-art approaches typically rely on multi-step pipelines with Graph Neural Network (GNN) encoders that compress rich…

Practitioners have consistently observed three puzzling phenomena in transformer-based large language models (LLMs): attention sinks, value-state drains, and residual-state peaks, collectively referred to as extreme-token phenomena. These…

Large Vision Language Models (LVLMs) have recently emerged as powerful architectures capable of understanding and reasoning over both visual and textual information. These models typically rely on two key components: a Vision Transformer…

Existing Large Vision-Language Models (LVLMs) exhibit insufficient visual attention, leading to hallucinations. To alleviate this problem, some previous studies adjust and amplify visual attention. These methods present a limitation that…

Large language models often reason beyond surface tokens, but the internal stage at which token-level information becomes abstract relational structure remains unclear. We investigate this question by analyzing how attention heads and…

Large vision-language models (LVLMs) achieve strong performance on visual reasoning tasks but remain highly susceptible to hallucination. Existing detection methods predominantly rely on coarse, whole-image measures of how an object token…

Vision-language models (VLMs) are commonly trained by directly inserting image tokens from a pretrained vision encoder into the text stream of a language model. This allows text and image information to fully attend to one another within…

This document provides a brief introduction to the attention mechanism used in modern language models based on the Transformer architecture. We first illustrate how text is encoded as vectors and how the attention mechanism processes these…

Vision-Language Models (VLMs) have demonstrated remarkable performance across a variety of real-world tasks. However, existing VLMs typically process visual information by serializing images, a method that diverges significantly from the…

LLMs process text as sequences of tokens that roughly correspond to words, where less common words are represented by multiple tokens. However, individual tokens are often semantically unrelated to the meanings of the words/concepts they…

The next-token prediction (NTP) objective has been foundational in the development of modern large language models (LLMs), driving advances in fluency and generalization. However, NTP operates at the \textit{token} level, treating…

Efficient parallelization of Large Language Models (LLMs) with long sequences is essential but challenging due to their significant computational and memory demands, particularly stemming from communication bottlenecks in attention…

Vision Large Language Models (VLLMs) usually take input as a concatenation of image token embeddings and text token embeddings and conduct causal modeling. However, their internal behaviors remain underexplored, raising the question of…

Locating and editing knowledge in large language models (LLMs) is crucial for enhancing their accuracy, safety, and inference rationale. We introduce ``concept editing'', an innovative variation of knowledge editing that uncovers…

The self-attention mechanism has significantly advanced the field of natural language processing, facilitating the development of advanced language-learning machines. Although its utility is widely acknowledged, the precise mechanisms of…

Cross-lingual transfer learning is an important property of multilingual large language models (LLMs). But how do LLMs represent relationships between languages? Every language model has an input layer that maps tokens to vectors. This…

The unusual properties of in-context learning (ICL) have prompted investigations into the internal mechanisms of large language models. Prior work typically focuses on either special attention heads or task vectors at specific layers, but…

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,…