Related papers: Emergent Structured Representations Support Flexib…

Language models (LMs) trained on large quantities of text have been claimed to acquire abstract linguistic representations. Our work tests the robustness of these abstractions by focusing on the ability of LMs to learn interactions between…

Large Language Models (LLMs) have shown remarkable ability in solving complex tasks, making them a promising tool for enhancing tabular learning. However, existing LLM-based methods suffer from high resource requirements, suboptimal…

Large language models (LLMs) can perform reasoning computations both internally within their latent space and externally by generating explicit token sequences like chains of thought. Significant progress in enhancing reasoning abilities…

Recent advancements in large language models (LLMs) have enhanced natural-language reasoning. However, their limited parametric memory and susceptibility to hallucination present persistent challenges for tasks requiring accurate,…

Large Language Models (LLMs) are important tools for reasoning and problem-solving, while they often operate passively, answering questions without actively discovering new ones. This limitation reduces their ability to simulate human-like…

Reasoning in large language models is predominantly evaluated through labeled benchmarks, conflating task performance with the quality of internal inference. Here we study reasoning as an intrinsic dynamical process by examining the…

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…

The increasing prevalence of Large Language Models (LLMs) demands effective safeguards for their operation, particularly concerning their tendency to generate out-of-context responses. A key challenge is accurately detecting when LLMs stray…

Generating semantically coherent text requires a robust internal representation of linguistic structures, which traditional embedding techniques often fail to capture adequately. A novel approach, Latent Lexical Projection (LLP), is…

Large reasoning models (LRMs) achieve strong performance on mathematical reasoning tasks, often attributed to their capability to generate explicit chain-of-thought (CoT) explanations. However, recent work shows that LRMs often arrive at…

Large Language Models (LLMs) have demonstrated remarkable capabilities in various reasoning and generation tasks. However, their proficiency in complex causal reasoning, discovery, and estimation remains an area of active development, often…

The social science of large language models (LLMs) examines how these systems evoke mind attributions, interact with one another, and transform human activity and institutions. We conducted a systematic review of 270 studies, combining text…

Large language models (LLMs) excel at modeling relationships between strings in natural language and have shown promise in extending to other symbolic domains like coding or mathematics. However, the extent to which they implicitly model…

In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks without weight updates by learning from demonstration sequences. While ICL shows strong empirical performance, its internal representational mechanisms are…

Large Language Models (LLMs) have made significant advances in natural language processing, but their underlying mechanisms are often misunderstood. Despite exhibiting coherent answers and apparent reasoning behaviors, LLMs rely on…

Large language models (LLMs) excel on a variety of reasoning benchmarks, but previous studies suggest they sometimes struggle to generalize to unseen questions, potentially due to over-reliance on memorized training examples. However, the…

Relational concepts are indeed foundational to the structure of knowledge representation, as they facilitate the association between various entity concepts, allowing us to express and comprehend complex world knowledge. By expressing…

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, especially when guided by explicit chain-of-thought (CoT) reasoning that verbalizes intermediate steps. While CoT improves both interpretability and accuracy,…

Large language models (LLMs) offer emerging opportunities for psychological and behavioral research, but methodological guidance is lacking. This article provides a framework for using LLMs as psychological simulators across two primary…

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…