English
Related papers

Related papers: Transformers Are Born Biased: Structural Inductive…

200 papers

Transformer-based pre-trained models with millions of parameters require large storage. Recent approaches tackle this shortcoming by training adapters, but these approaches still require a relatively large number of parameters. In this…

Computation and Language · Computer Science 2023-01-31 Chin-Lun Fu , Zih-Ching Chen , Yun-Ru Lee , Hung-yi Lee

Large Language Models (LLMs) have made significant strides in natural language processing, and a precise understanding of the internal mechanisms driving their success is essential. In this work, we analyze the trajectories of token…

Machine Learning · Computer Science 2025-03-06 Murdock Aubry , Haoming Meng , Anton Sugolov , Vardan Papyan

The advent of transformer-based language models has reshaped how AI systems process and generate text. In software engineering (SE), these models now support diverse activities, accelerating automation and decision-making. Yet, evidence…

Software Engineering · Computer Science 2026-01-12 Gianmario Voria , Moses Openja , Foutse Khomh , Gemma Catolino , Fabio Palomba

Transformers can generate predictions in two approaches: 1. auto-regressively by conditioning each sequence element on the previous ones, or 2. directly produce an output sequences in parallel. While research has mostly explored upon this…

Computer Vision and Pattern Recognition · Computer Science 2021-08-18 Andrea Alfieri , Yancong Lin , Jan C. van Gemert

Large language model (LLM) tokenizers act as structured compressors: by mapping text to discrete token sequences, they determine token count (and thus compute and context usage) and the statistical structure seen by downstream models.…

Information Theory · Computer Science 2026-01-15 Mete Erdogan , Abhiram Gorle , Shubham Chandak , Mert Pilanci , Tsachy Weissman

Transformers exhibit compositional reasoning on sequences not observed during training, a capability often attributed to in-context learning (ICL) and skill composition. We investigate this phenomenon using the Random Hierarchy Model (RHM),…

Machine Learning · Computer Science 2025-10-21 Jing Liu

We investigate the mechanisms that arise when transformers are trained to solve arithmetic on sequences where tokens are variables whose meaning is determined only through their interactions in-context. While prior work has studied…

Computation and Language · Computer Science 2026-02-26 Eric Todd , Jannik Brinkmann , Rohit Gandikota , David Bau

Transformers are neural networks that revolutionized natural language processing and machine learning. They process sequences of inputs, like words, using a mechanism called self-attention, which is trained via masked language modeling…

Disordered Systems and Neural Networks · Physics 2024-04-17 Riccardo Rende , Federica Gerace , Alessandro Laio , Sebastian Goldt

Fine-tuning pretrained contextual word embedding models to supervised downstream tasks has become commonplace in natural language processing. This process, however, is often brittle: even with the same hyperparameter values, distinct random…

Computation and Language · Computer Science 2020-02-19 Jesse Dodge , Gabriel Ilharco , Roy Schwartz , Ali Farhadi , Hannaneh Hajishirzi , Noah Smith

Artificial neural networks can acquire many aspects of human knowledge from data, making them promising as models of human learning. But what those networks can learn depends upon their inductive biases -- the factors other than the data…

Machine Learning · Computer Science 2025-02-28 Gianluca Bencomo , Max Gupta , Ioana Marinescu , R. Thomas McCoy , Thomas L. Griffiths

Transformers, adapted from natural language processing, are emerging as a leading approach for graph representation learning. Contemporary graph transformers often treat nodes or edges as separate tokens. This approach leads to…

Machine Learning · Computer Science 2023-10-04 Zihan Pengmei , Zimu Li , Chih-chan Tien , Risi Kondor , Aaron R. Dinner

Token embeddings play a crucial role in language modeling but, despite this practical relevance, their theoretical understanding remains limited. Our paper addresses the gap by characterizing the structure of embeddings obtained via…

Machine Learning · Computer Science 2025-06-26 Diyuan Wu , Aleksandr Shevchenko , Samet Oymak , Marco Mondelli

Fine-tuning pre-trained transformers is a powerful technique for enhancing the performance of base models on specific tasks. From early applications in models like BERT to fine-tuning Large Language Models (LLMs), this approach has been…

Computation and Language · Computer Science 2025-02-25 Suneel Nadipalli

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing…

The use of positional embeddings in transformer language models is widely accepted. However, recent research has called into question the necessity of such embeddings. We further extend this inquiry by demonstrating that a randomly…

Computation and Language · Computer Science 2023-05-24 Ta-Chung Chi , Ting-Han Fan , Li-Wei Chen , Alexander I. Rudnicky , Peter J. Ramadge

Both humans and large language models are able to learn language without explicit structural supervision. What inductive biases make this learning possible? We address this fundamental cognitive question by leveraging transformer language…

Computation and Language · Computer Science 2023-10-31 Isabel Papadimitriou , Dan Jurafsky

It has recently been demonstrated empirically that in-context learning emerges in transformers when certain distributional properties are present in the training data, but this ability can also diminish upon further training. We provide a…

Machine Learning · Computer Science 2025-04-29 Bryan Chan , Xinyi Chen , András György , Dale Schuurmans

Transformers have recently been shown to be capable of reliably performing logical reasoning over facts and rules expressed in natural language, but abductive reasoning - inference to the best explanation of an unexpected observation - has…

Computation and Language · Computer Science 2022-03-24 Nathan Young , Qiming Bao , Joshua Bensemann , Michael Witbrock

While there has been a large body of research attempting to circumvent tokenization for language modeling (Clark et al., 2022; Xue et al., 2022), the current consensus is that it is a necessary initial step for designing state-of-the-art…

Computation and Language · Computer Science 2025-04-11 Nived Rajaraman , Jiantao Jiao , Kannan Ramchandran

Analogy is a central faculty of human intelligence, enabling abstract patterns discovered in one domain to be applied to another. Despite its central role in cognition, the mechanisms by which Transformers acquire and implement analogical…

Artificial Intelligence · Computer Science 2026-05-28 Gouki Minegishi , Jingyuan Feng , Hiroki Furuta , Takeshi Kojima , Yusuke Iwasawa , Yutaka Matsuo