中文
相关论文

相关论文: Token-wise Decomposition of Autoregressive Languag…

200 篇论文

Token prediction stability remains a challenge in autoregressive generative models, where minor variations in early inference steps often lead to significant semantic drift over extended sequences. A structured modulation mechanism was…

Discrete diffusion models have recently become competitive with autoregressive models for language modeling, even outperforming them on reasoning tasks requiring planning and global coherence, but they require more computation at inference…

机器学习 · 计算机科学 2026-02-04 Andre He , Sean Welleck , Daniel Fried

Tokenization -- the process of decomposing a given text into a sequence of subwords called tokens -- is one of the key components in the development of language models. Particularly, auto-regressive language models generate texts token by…

计算与语言 · 计算机科学 2026-02-19 Daiki Chijiwa , Taku Hasegawa , Kyosuke Nishida , Shin'ya Yamaguchi , Tomoya Ohba , Tamao Sakao , Susumu Takeuchi

Predictions of word-by-word conditional probabilities from Transformer-based language models are often evaluated to model the incremental processing difficulty of human readers. In this paper, we argue that there is a confound posed by the…

计算与语言 · 计算机科学 2024-10-01 Byung-Doh Oh , William Schuler

Autoregressive language models have demonstrated a remarkable ability to extract latent structure from text. The embeddings from large language models have been shown to capture aspects of the syntax and semantics of language. But what…

机器学习 · 计算机科学 2026-01-09 Liyi Zhang , Michael Y. Li , R. Thomas McCoy , Theodore R. Sumers , Jian-Qiao Zhu , Thomas L. Griffiths

Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to commit at every step, preventing it from exploring or…

计算与语言 · 计算机科学 2026-03-24 Lorenzo Noci , Gregor Bachmann , Seyed-Mohsen Moosavi-Dezfooli , Moin Nabi

In this work, we study the representation space of contextualized embeddings and gain insight into the hidden topology of large language models. We show there exists a network of latent states that summarize linguistic properties of…

计算与语言 · 计算机科学 2022-06-06 Yao Fu , Mirella Lapata

Next-word predictions from autoregressive neural language models show remarkable sensitivity to syntax. This work evaluates the extent to which this behavior arises as a result of a learned ability to maintain implicit representations of…

计算与语言 · 计算机科学 2022-11-18 Tiwalayo Eisape , Vineet Gangireddy , Roger P. Levy , Yoon Kim

Language Generation Models produce words based on the previous context. Although existing methods offer input attributions as explanations for a model's prediction, it is still unclear how prior words affect the model's decision throughout…

计算与语言 · 计算机科学 2023-05-23 Javier Ferrando , Gerard I. Gállego , Ioannis Tsiamas , Marta R. Costa-jussà

Large Language Models (LLMs) are trained with next-token prediction, implemented in autoregressive Transformers via causal masking for parallelism. This creates a subtle misalignment: residual connections tie activations to the current…

We take a physics-based approach to studying how the internal hidden states of large language models change from token to token during inference. Across 20 open-source transformer models (135M-3B parameters), we find that a quantity…

计算与语言 · 计算机科学 2025-08-13 Lorenzo Tomaz , Judd Rosenblatt , Thomas Berry Jones , Diogo Schwerz de Lucena

This research aims to unravel how large language models (LLMs) iteratively refine token predictions through internal processing. We utilized a logit lens technique to analyze the model's token predictions derived from intermediate…

计算与语言 · 计算机科学 2025-06-10 Jaturong Kongmanee

Transformer-based models generate hidden states that are difficult to interpret. In this work, we analyze hidden states and modify them at inference, with a focus on motion forecasting. We use linear probing to analyze whether interpretable…

机器学习 · 计算机科学 2025-05-19 Omer Sahin Tas , Royden Wagner

Standard autoregressive language models generate text by repeatedly selecting a discrete next token, coupling prediction with irreversible commitment at every step. We show that token selection is not the only viable autoregressive…

计算与语言 · 计算机科学 2026-04-07 Oshri Naparstek

We analyze how large language models (LLMs) represent out-of-context words, investigating their reliance on the given context to capture their semantics. Our likelihood-guided text perturbations reveal a correlation between token likelihood…

计算与语言 · 计算机科学 2023-03-16 Valeria Ruscio , Valentino Maiorca , Fabrizio Silvestri

Large language models (LLMs) contain substantial factual knowledge which is commonly elicited by multiple-choice question-answering prompts. Internally, such models process the prompt through multiple transformer layers, building varying…

计算与语言 · 计算机科学 2025-01-31 Didier Chételat , Joseph Cotnareanu , Rylee Thompson , Yingxue Zhang , Mark Coates

An agent's intention often remains hidden behind the black-box nature of embodied policies. Communication using natural language statements that describe the next action can provide transparency towards the agent's behavior. We aim to…

机器人学 · 计算机科学 2025-04-15 Theodor Wulff , Rahul Singh Maharjan , Xinyun Chi , Angelo Cangelosi

Next-token prediction serves as the dominant component in current neural language models. During the training phase, the model employs teacher forcing, which predicts tokens based on all preceding ground truth tokens. However, this approach…

计算与语言 · 计算机科学 2024-10-28 Yongjing Yin , Junran Ding , Kai Song , Yue Zhang

When a language model generates text, the selection of individual tokens might lead it down very different reasoning paths, making uncertainty difficult to quantify. In this work, we consider whether reasoning language models represent the…

计算与语言 · 计算机科学 2025-11-07 Amir Zur , Atticus Geiger , Ekdeep Singh Lubana , Eric Bigelow

Transformers have achieved state-of-the-art performance in language modeling tasks. However, the reasons behind their tremendous success are still unclear. In this paper, towards a better understanding, we train a Transformer model on a…

机器学习 · 统计学 2024-06-06 Michael E. Sander , Raja Giryes , Taiji Suzuki , Mathieu Blondel , Gabriel Peyré
‹ 上一页 1 2 3 10 下一页 ›