English
Related papers

Related papers: Scale Determines Whether Language Models Organize …

200 papers

We explore the topology of representation manifolds arising in autoregressive neural language models trained on raw text data. In order to study their properties, we introduce tools from computational algebraic topology, which we use as a…

Computation and Language · Computer Science 2024-06-11 Stephen Fitz , Peter Romero , Jiyan Jonas Schneider

For responsible decision making in safety-critical settings, machine learning models must effectively detect and process edge-case data. Although existing works show that predictive uncertainty is useful for these tasks, it is not evident…

Machine Learning · Computer Science 2022-08-09 Mark Penrod , Harrison Termotto , Varshini Reddy , Jiayu Yao , Finale Doshi-Velez , Weiwei Pan

A language model (LM) is a mapping from a linguistic context to an output token. However, much remains to be known about this mapping, including how its geometric properties relate to its function. We take a high-level geometric approach to…

Computation and Language · Computer Science 2025-05-01 Emily Cheng , Diego Doimo , Corentin Kervadec , Iuri Macocco , Jade Yu , Alessandro Laio , Marco Baroni

Reliable deployment of language models requires two capabilities that appear distinct but share a common geometric foundation: predicting whether a model will accept targeted behavioral control, and detecting when its internal structure…

Machine Learning · Computer Science 2026-04-30 Prashant C. Raju

Aligning large language models (LLMs) through supervised fine-tuning is essential for tailoring them to specific applications. Recent studies suggest that alignment primarily adjusts a model's presentation style rather than its foundational…

Computation and Language · Computer Science 2025-04-09 Guangyuan Shi , Zexin Lu , Xiaoyu Dong , Wenlong Zhang , Xuanyu Zhang , Yujie Feng , Xiao-Ming Wu

Transformer models learn to encode and decode an input text, and produce contextual token embeddings as a side-effect. The mapping from language into the embedding space maps words expressing similar concepts onto points that are close in…

Computation and Language · Computer Science 2025-09-03 Vivi Nastase , Paola Merlo

Fine-tuning Large Language Models (LLMs) remains structurally uncertain despite parameter-efficient methods such as Low-Rank Adaptation (LoRA), as the layer-specific roles of internal representations are poorly understood, leading to…

Reasoning is an integral part of many tasks performed by language models (LMs). However, the effects of scaling model sizes and data on reasoning abilities at pretraining time remain understudied. To rigorously investigate this problem, we…

Artificial Intelligence · Computer Science 2025-09-30 Xinyi Wang , Shawn Tan , Shenbo Xu , Mingyu Jin , William Yang Wang , Rameswar Panda , Yikang Shen

Large language model (LLM) architectures are often described as functionally hierarchical: Early layers process syntax, middle layers begin to parse semantics, and late layers integrate information. The present work revisits these ideas.…

Computation and Language · Computer Science 2025-01-14 Paul C. Bogdan

Spatial reasoning is fundamental to auditory perception, yet current audio large language models (ALLMs) largely rely on unstructured binaural cues and single step inference. This limits both perceptual accuracy in direction and distance…

Sound · Computer Science 2025-10-01 Subrata Biswas , Mohammad Nur Hossain Khan , Bashima Islam

Artificial intelligence models are increasingly scaled to improve predictive accuracy, yet it remains unclear whether scale improves the quality of post-hoc explanations. We investigate this relationship by evaluating 11 computer vision…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Mateusz Cedro , Marcin Chlebus

Despite the ubiquity of large language models (LLMs) in AI research, the question of embodiment in LLMs remains underexplored, distinguishing them from embodied systems in robotics where sensory perception directly informs physical action.…

Computation and Language · Computer Science 2024-05-28 Philipp Wicke , Lennart Wachowiak

Geometric constraints impact the formation of a broad range of spatial networks, from amino acid chains folding to proteins structures to rearranging particle aggregates. How the network of interactions dynamically self-organizes in such…

Molecular Networks · Quantitative Biology 2016-10-19 Nora Molkenthin , Marc Timme

A recent body of work has demonstrated that Transformer embeddings can be linearly decomposed into well-defined sums of factors, that can in turn be related to specific network inputs or components. There is however still a dearth of work…

Computation and Language · Computer Science 2023-10-12 Timothee Mickus , Raúl Vázquez

Next-token prediction (NTP) over large text corpora has become the go-to paradigm to train large language models. Yet, it remains unclear how NTP influences the mapping of linguistic patterns to geometric properties of the resulting model…

Computation and Language · Computer Science 2025-02-20 Yize Zhao , Tina Behnia , Vala Vakilian , Christos Thrampoulidis

We study empirical scaling laws for language model performance on the cross-entropy loss. The loss scales as a power-law with model size, dataset size, and the amount of compute used for training, with some trends spanning more than seven…

The performance of Large Language Models is influenced by their characteristics such as architecture, model sizes, decoding methods and so on. Due to differences in structure or function, the weights in different layers of large models have…

Machine Learning · Computer Science 2025-09-03 Chunming Ye , Songzhou Li , Xu Xu

Increasing the number of parameters in language models is a common strategy to enhance their performance. However, smaller language models remain valuable due to their lower operational costs. Despite their advantages, smaller models…

Computation and Language · Computer Science 2024-10-16 Richard Diehl Martinez , Pietro Lesci , Paula Buttery

Deep learning (DL) creates impactful advances following a virtuous recipe: model architecture search, creating large training data sets, and scaling computation. It is widely believed that growing training sets and models should improve…

We introduce a self-supervised speech pre-training method called TERA, which stands for Transformer Encoder Representations from Alteration. Recent approaches often learn by using a single auxiliary task like contrastive prediction,…

Audio and Speech Processing · Electrical Eng. & Systems 2021-08-05 Andy T. Liu , Shang-Wen Li , Hung-yi Lee
‹ Prev 1 3 4 5 6 7 10 Next ›