Related papers: Frame Representation Hypothesis: Multi-Token LLM I…
This paper presents several novel findings on the explainability of vision reflection in large multimodal models (LMMs). First, we show that prompting an LMM to verify the prediction of a specialized vision model can improve recognition…
This paper introduces a novel Bayesian learning model to explain the behavior of Large Language Models (LLMs), focusing on their core optimization metric of next token prediction. We develop a theoretical framework based on an ideal…
Large Language Models (LLMs) are transforming scientific hypothesis generation and validation by enabling information synthesis, latent relationship discovery, and reasoning augmentation. This survey provides a structured overview of…
Advances in the general capabilities of large language models (LLMs) have led to their use for information retrieval, and as components in automated decision systems. A faithful representation of probabilistic reasoning in these models may…
Much of the knowledge encoded in transformer language models (LMs) may be expressed in terms of relations: relations between words and their synonyms, entities and their attributes, etc. We show that, for a subset of relations, this…
Estimating the difficulty of input questions as perceived by large language models (LLMs) is essential for accurate performance evaluation and adaptive inference. Existing methods typically rely on repeated response sampling, auxiliary…
Large language models have exhibited impressive performance across a broad range of downstream tasks in natural language processing. However, how a language model predicts the next token and generates content is not generally understandable…
Large language models (LLMs) are powerful AI tools that can generate and comprehend natural language text and other complex information. However, the field lacks a mathematical framework to systematically describe, compare and improve LLMs.…
Differential framing of issues can lead to divergent world views on important issues. This is especially true in domains where the information presented can reach a large audience, such as traditional and social media. Scalable and reliable…
Despite significant progress in transformer interpretability, an understanding of the computational mechanisms of large language models (LLMs) remains a fundamental challenge. Many approaches interpret a network's hidden representations but…
Large Language Models (LLMs), benefiting from the auto-regressive modelling approach performed on massive unannotated texts corpora, demonstrates powerful perceptual and reasoning capabilities. However, as for extending auto-regressive…
Although natural language is the default medium for Large Language Models (LLMs), its limited expressive capacity creates a profound bottleneck for complex problem-solving. While recent advancements in AI have relied heavily on scaling,…
Accurate molecular property prediction is a critical challenge with wide-ranging applications in chemistry, materials science, and drug discovery. Molecular representation methods, including fingerprints and graph neural networks (GNNs),…
Word representation has always been an important research area in the history of natural language processing (NLP). Understanding such complex text data is imperative, given that it is rich in information and can be used widely across…
The opaque nature of Large Language Models (LLMs) has led to significant research efforts aimed at enhancing their interpretability, primarily through post-hoc methods. More recent in-hoc approaches, such as Concept Bottleneck Models…
Despite Large Language Models' remarkable capabilities, understanding their internal representations remains challenging. Mechanistic interpretability tools such as sparse autoencoders (SAEs) were developed to extract interpretable features…
We propose a novel framework that leverages large language models (LLMs) to guide the rank selection in tensor network models for higher-order data analysis. By utilising the intrinsic reasoning capabilities and domain knowledge of LLMs,…
The extraordinary success of recent Large Language Models (LLMs) on a diverse array of tasks has led to an explosion of scientific and philosophical theorizing aimed at explaining how they do what they do. Unfortunately, disagreement over…
Recent works have argued that high-level semantic concepts are encoded "linearly" in the representation space of large language models. In this work, we study the origins of such linear representations. To that end, we introduce a simple…
We investigate whether large language models encode latent knowledge of frame semantics, focusing on frame identification, a core challenge in frame semantic parsing that involves selecting the appropriate semantic frame for a target word…