A full understanding of the behavior of a large language model (LLM) requires our grasp of its input token space. If this space differs from our assumptions, our comprehension of and conclusions about the LLM will likely be flawed. We elucidate the structure of the token embeddings both empirically and theoretically. We present a novel statistical test assuming that the neighborhood around each token has a relatively flat and smooth structure as the null hypothesis. Failing to reject the null is uninformative, but rejecting it at a specific token $ψ$ implies an irregularity in the token subspace in a $ψ$-neighborhood, $B(ψ)$. The structure assumed in the null is a generalization of a manifold with boundary called a \emph{smooth fiber bundle} (which can be split into two spatial regimes -- small and large radius), so we denote our new hypothesis test as the ``fiber bundle hypothesis.'' By running our test over several open-source LLMs, each with unique token embeddings, we find that the null is frequently rejected, and so the evidence suggests that the token subspace is not a fiber bundle and hence also not a manifold. As a consequence of our findings, when an LLM is presented with two semantically equivalent prompts, if one prompt contains a token implicated by our test, the response to that prompt will likely exhibit less stability than the other.
Tokens, the oft-overlooked appetizer: Large language models, the distributional hypothesis, and meaning
Computational Story Lab(计算故事实验室);Vermont Complex Systems Institute(佛蒙特复杂系统研究所);University of Vermont(佛蒙特大学);Department of Computer Science(计算机科学系);St. Michael’s College(圣米歇尔学院);Communication Media and Marginalization Lab(传播媒体与边缘化实验室);Northeastern University(东北大学);Department of Mathematics & Statistics(数学与统计学系)
Are language models aware of the road not taken? Token-level uncertainty and hidden state dynamics
Department of Linguistics, Stanford University(斯坦福大学语言学系);Department of Psychology, Harvard University(哈佛大学心理学系);Center for Brain Science, Harvard University(哈佛大学脑科学中心);Physics of Intelligence Group, NTT Research(NTT研究物理智能小组)
HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction
Institute for Artificial Intelligence, Peking University, Beijing(北京大学人工智能研究院);Huawei(华为);School of Integrated Circuits, Peking University, Beijing(北京大学集成电路学院)
Is my model perplexed for the right reason? Contrasting LLMs' Benchmark Behavior with Token-Level Perplexity
College of Informatics, University of Amsterdam(阿姆斯特丹大学信息学学院);Department of Medical Informatics, Amsterdam University Medical Center(阿姆斯特丹大学医学中心医学信息学系);ILLC, University of Amsterdam(阿姆斯特丹大学逻辑、语言与计算研究所)
Token-Efficient Leverage Learning in Large Language Models
School of Computer Science(计算机学院);Beijing University of Posts and Telecommunications(北京邮电大学);College of information science and electronic engineering(信息科学与电子工程学院);Zhejiang University(浙江大学);School of Artificial Intelligence(人工智能学院)
I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?
Responsible AI Research Centre(负责任人工智能研究中心);Australian Institute for Machine Learning(澳大利亚机器学习研究所);Adelaide University(阿德莱德大学);School of Computer Science and Engineering(计算机科学与工程学院);The University of New South Wales(新南威尔士大学);Halıcıoğlu Data Science Institute(哈利奇奥格卢数据科学研究所);University of California San Diego(加州大学圣地亚哥分校);School of Mathematics and Statistics(数学与统计学学院);The University of Melbourne(墨尔本大学)