中文
相关论文

相关论文: Language Models Learn Universal Representations of…

200 篇论文

Pretrained language models (LMs) are prone to arithmetic errors. Existing work showed limited success in probing numeric values from models' representations, indicating that these errors can be attributed to the inherent unreliability of…

计算与语言 · 计算机科学 2025-10-27 Marek Kadlčík , Michal Štefánik , Timothee Mickus , Michal Spiegel , Josef Kuchař

Large language models (LLMs) frequently make errors when handling even simple numerical problems, such as comparing two small numbers. A natural hypothesis is that these errors stem from how LLMs represent numbers, and specifically, whether…

机器学习 · 计算机科学 2025-02-04 Amit Arnold Levy , Mor Geva

Motivated by interpretability and reliability, we investigate whether large language models (LLMs) deploy universal geometric structures to encode discrete, graph-structured knowledge. To this end, we present two complementary experimental…

机器学习 · 计算机科学 2025-11-25 David D. Baek , Yuxiao Li , Max Tegmark

Humans are believed to perceive numbers on a logarithmic mental number line, where smaller values are represented with greater resolution than larger ones. This cognitive bias, supported by neuroscience and behavioral studies, suggests that…

Numbers are a basic part of how humans represent and describe the world around them. As a consequence, learning effective representations of numbers is critical for the success of large language models as they become more integrated into…

计算与语言 · 计算机科学 2025-02-04 Raja Marjieh , Veniamin Veselovsky , Thomas L. Griffiths , Ilia Sucholutsky

Large language models (LLMs) have exhibited impressive competence in various tasks, but their internal mechanisms on mathematical problems are still under-explored. In this paper, we study a fundamental question: how language models encode…

计算与语言 · 计算机科学 2024-11-15 Fangwei Zhu , Damai Dai , Zhifang Sui

Large Language Models (LLMs) have impressive capabilities, but are prone to outputting falsehoods. Recent work has developed techniques for inferring whether a LLM is telling the truth by training probes on the LLM's internal activations.…

人工智能 · 计算机科学 2024-08-20 Samuel Marks , Max Tegmark

Large language models (LLMs) are a promising venue for natural language understanding and generation. However, current LLMs are far from reliable: they are prone to generating non-factual information and, more crucially, to contradicting…

计算与语言 · 计算机科学 2024-09-24 Diego Calanzone , Stefano Teso , Antonio Vergari

Large language models (LLMs) represent a new paradigm for processing unstructured data, with applications across an unprecedented range of domains. In this paper, we address, through two arguments, whether the development and application of…

统计方法学 · 统计学 2026-02-03 Weijie Su

Large language models (LLMs) have complicated internal dynamics, but induce representations of words and phrases whose geometry we can study. Human language processing is also opaque, but neural response measurements can provide (noisy)…

计算与语言 · 计算机科学 2023-11-01 Jiaang Li , Antonia Karamolegkou , Yova Kementchedjhieva , Mostafa Abdou , Sune Lehmann , Anders Søgaard

Large Language Models (LLMs) are becoming increasingly popular in pervasive computing due to their versatility and strong performance. However, despite their ubiquitous use, the exact mechanisms underlying their outstanding performance…

计算与语言 · 计算机科学 2026-02-02 Alhassan Abdelhalim , Janick Edinger , Sören Laue , Michaela Regneri

Large Language Models (LLMs) do not differentially represent numbers, which are pervasive in text. In contrast, neuroscience research has identified distinct neural representations for numbers and words. In this work, we investigate how…

人工智能 · 计算机科学 2024-01-10 Raj Sanjay Shah , Vijay Marupudi , Reba Koenen , Khushi Bhardwaj , Sashank Varma

Large Language Models (LLMs) have recently demonstrated remarkable capabilities in natural language processing tasks and beyond. This success of LLMs has led to a large influx of research contributions in this direction. These works…

计算与语言 · 计算机科学 2024-10-18 Humza Naveed , Asad Ullah Khan , Shi Qiu , Muhammad Saqib , Saeed Anwar , Muhammad Usman , Naveed Akhtar , Nick Barnes , Ajmal Mian

While Large language models (LLMs) have proved able to address some complex reasoning tasks, we also know that they are highly sensitive to input variation, which can lead to different solution paths and final answers. Answer consistency…

计算与语言 · 计算机科学 2025-03-05 Huiyuan Lai , Xiao Zhang , Malvina Nissim

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…

计算与语言 · 计算机科学 2024-08-05 Bo Zhou , Daniel Geißler , Paul Lukowicz

Large language models (LLMs) process and predict sequences containing text to answer questions, and address tasks including document summarization, providing recommendations, writing software and solving quantitative problems. We provide a…

数值分析 · 数学 2026-02-02 Ricardo Baptista , Andrew Stuart , Son Tran

Large language models (LLMs) have demonstrated emergent abilities across diverse tasks, raising the question of whether they acquire internal world models. In this work, we investigate whether LLMs implicitly encode linear spatial world…

人工智能 · 计算机科学 2025-06-04 Matthieu Tehenan , Christian Bolivar Moya , Tenghai Long , Guang Lin

The capabilities of large language models (LLMs) have sparked debate over whether such systems just learn an enormous collection of superficial statistics or a set of more coherent and grounded representations that reflect the real world.…

机器学习 · 计算机科学 2024-03-05 Wes Gurnee , Max Tegmark

Large language models (LLMs) have led to breakthroughs in language tasks, yet the internal mechanisms that enable their remarkable generalization and reasoning abilities remain opaque. This lack of transparency presents challenges such as…

计算与语言 · 计算机科学 2024-04-17 Haiyan Zhao , Fan Yang , Bo Shen , Himabindu Lakkaraju , Mengnan Du

Large language models (LLMs) are a promising venue for natural language understanding and generation tasks. However, current LLMs are far from reliable: they are prone to generate non-factual information and, more crucially, to contradict…

机器学习 · 计算机科学 2024-04-22 Diego Calanzone , Stefano Teso , Antonio Vergari
‹ 上一页 1 2 3 10 下一页 ›