Related papers: Vector Arithmetic in Concept and Token Subspaces

When asked to summarize articles or answer questions given a passage, large language models (LLMs) can hallucinate details and respond with unsubstantiated answers that are inaccurate with respect to the input context. This paper describes…

Modern multimodal large language models (MLLMs) typically keep the language model fixed and train a visual projector that maps the pixels into a sequence of tokens in its embedding space, so that images can be presented in essentially the…

Concerns regarding the propensity of Large Language Models (LLMs) to produce inaccurate outputs, also known as hallucinations, have escalated. Detecting them is vital for ensuring the reliability of applications relying on LLM-generated…

Large Language Models (LLMs) are increasingly applied to data-intensive workflows, from database querying to developer observability. Yet the effectiveness of these systems is constrained by the volume, verbosity, and noise of real-world…

Attention mechanisms have improved the performance of NLP tasks while allowing models to remain explainable. Self-attention is currently widely used, however interpretability is difficult due to the numerous attention distributions. Recent…

We propose a method to create document representations that reflect their internal structure. We modify Tree-LSTMs to hierarchically merge basic elements such as words and sentences into blocks of increasing complexity. Our Structure…

Attention models are widely used in Vision-language (V-L) tasks to perform the visual-textual correlation. Humans perform such a correlation with a strong linguistic understanding of the visual world. However, even the best performing…

Attending to what is relevant is fundamental to both the mammalian brain and modern machine learning models such as Transformers. Yet, determining relevance remains a core challenge, traditionally offloaded to learning algorithms like…

Attention-based sequence-to-sequence models have shown promising results in automatic speech recognition. Using these architectures, one-dimensional input and output sequences are related by an attention approach, thereby replacing more…

Large language models(LLMs) excel at text generation and knowledge question-answering tasks, but they are prone to generating hallucinated content, severely limiting their application in high-risk domains. Current hallucination detection…

The pre-training of masked language models (MLMs) consumes massive computation to achieve good results on downstream NLP tasks, resulting in a large carbon footprint. In the vanilla MLM, the virtual tokens, [MASK]s, act as placeholders and…

The quadratic computational complexity of softmax transformers has become a bottleneck in long-context scenarios. In contrast, linear attention model families provide a promising direction towards a more efficient sequential model. These…

Mechanistic interpretability aims to reverse-engineer the internal computations of Large Language Models (LLMs), yet separating sparse semantic signals from high-dimensional polysemantic noise remains a significant challenge. This paper…

Large language model (LLM) inference is increasingly bottlenecked by the Key-Value (KV) cache, yet the fine-grained structure of attention-head activations remains poorly understood. We show that pretrained Transformers exhibit a pervasive…

The rapid advancement in large language models (LLMs) has significantly enhanced their ability to generate coherent and contextually relevant text, raising concerns about the misuse of AI-generated content and making it critical to detect…

Language models have made significant progress in generating coherent text and predicting next tokens based on input prompts. This study compares the next-token prediction performance of two well-known models: OpenAI's GPT-2 and Meta's…

Large language models (LLMs) have demonstrated remarkable proficiency in in-context learning (ICL), where models adapt to new tasks through example-based prompts without requiring parameter updates. However, understanding how tasks are…

Recent works have shown that transformers can solve contextual reasoning tasks by internally executing computational graphs called circuits. Circuits often use attention to logically match information from subspaces of the representation,…

Large Vision-Language Models (VLMs) have achieved remarkable success in multi-modal reasoning, but their inference time efficiency remains a significant challenge due to the memory overhead during decoding, especially when the query and…

Interpretability methods for large language models (LLMs) typically derive directions from textual supervision, which can lack external grounding. We propose using human brain activity not as a training signal but as a coordinate system for…