English
Related papers

Related papers: Transformers generalize differently from informati…

200 papers

Large language models (LLMs) have shown incredible performance in completing various real-world tasks. The current paradigm of knowledge learning for LLMs is mainly based on learning from examples, in which LLMs learn the internal rule…

Computation and Language · Computer Science 2024-12-17 Wenkai Yang , Yankai Lin , Jie Zhou , Ji-Rong Wen

We analyze the ability of pre-trained language models to transfer knowledge among datasets annotated with different type systems and to generalize beyond the domain and dataset they were trained on. We create a meta task, over multiple…

Computation and Language · Computer Science 2021-12-16 Jaromir Savelka , Hannes Westermann , Karim Benyekhlef

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…

Computation and Language · Computer Science 2023-05-23 Javier Ferrando , Gerard I. Gállego , Ioannis Tsiamas , Marta R. Costa-jussà

Trajectory planning in autonomous driving is highly dependent on predicting the emergent behavior of other road users. Learning-based methods are currently showing impressive results in simulation-based challenges, with transformer-based…

Machine Learning · Computer Science 2024-08-08 Lars Ullrich , Alex McMaster , Knut Graichen

Large language models leverage both parametric knowledge acquired during pretraining and in-context knowledge provided at inference time. Crucially, when these sources conflict, models arbitrate based on their internal confidence,…

Computation and Language · Computer Science 2026-04-21 Minsung Kim , Dong-Kyum Kim , Jea Kwon , Nakyeong Yang , Kyomin Jung , Meeyoung Cha

For text-based AI systems to interact in the real world, causal reasoning is an essential skill. Since active interventions are costly, we study to what extent a system can learn causal reasoning from symbolic demonstrations of causal…

Transformer language models have demonstrated impressive generalization capabilities in natural language domains, yet we lack a fine-grained understanding of how such generalization arises. In this paper, we investigate length…

Computation and Language · Computer Science 2025-08-05 Ziyang Cai , Nayoung Lee , Avi Schwarzschild , Samet Oymak , Dimitris Papailiopoulos

Diffusion models generalize well in practice. However, an optimal diffusion model fully memorizes the training data and therefore fails to generalize, raising the question of what induces generalization in a real diffusion model. We show…

Machine Learning · Computer Science 2026-05-21 Tim Kaiser , Markus Kollmann

An important task for the design of Question Answering systems is the selection of the sentence containing (or constituting) the answer from documents relevant to the asked question. Most previous work has only used the target sentence to…

Computation and Language · Computer Science 2020-06-03 Ivano Lauriola , Alessandro Moschitti

Learning to use tools to solve a variety of tasks is an innate ability of humans and has been observed of animals in the wild. However, the underlying mechanisms that are required to learn to use tools are abstract and widely contested in…

Neural and Evolutionary Computing · Computer Science 2019-07-04 Sam Wenke , Dan Saunders , Mike Qiu , Jim Fleming

To answer a question, language models often need to integrate prior knowledge learned during pretraining and new information presented in context. We hypothesize that models perform this integration in a predictable way across different…

Computation and Language · Computer Science 2024-06-18 Kevin Du , Vésteinn Snæbjarnarson , Niklas Stoehr , Jennifer C. White , Aaron Schein , Ryan Cotterell

Despite the empirical success of prompt tuning in adapting pretrained language models to new tasks, theoretical analyses of its capabilities remain limited. Existing theoretical work primarily addresses universal approximation properties,…

Machine Learning · Computer Science 2025-09-03 Maxime Meyer , Mario Michelessa , Caroline Chaux , Vincent Y. F. Tan

This paper introduces Filtered Corpus Training, a method that trains language models (LMs) on corpora with certain linguistic constructions filtered out from the training data, and uses it to measure the ability of LMs to perform linguistic…

Computation and Language · Computer Science 2024-08-08 Abhinav Patil , Jaap Jumelet , Yu Ying Chiu , Andy Lapastora , Peter Shen , Lexie Wang , Clevis Willrich , Shane Steinert-Threlkeld

We empirically investigate how pre-training on data of different modalities, such as language and vision, affects fine-tuning of Transformer-based models to Mujoco offline reinforcement learning tasks. Analysis of the internal…

Machine Learning · Computer Science 2022-11-21 Shiro Takagi

Language models are typically evaluated on their success at predicting the distribution of specific words in specific contexts. Yet linguistic knowledge also encodes relationships between contexts, allowing inferences between word…

Computation and Language · Computer Science 2023-11-09 Michael Wilson , Jackson Petty , Robert Frank

Large Language Models (LLMs) based on Transformers excel at text processing, but their reliance on prompts for specialized behavior introduces computational overhead. We propose a modification to a Transformer architecture that eliminates…

Machine Learning · Computer Science 2025-06-09 Andrey Zhmoginov , Jihwan Lee , Max Vladymyrov , Mark Sandler

Transformer based language models exhibit intelligent behaviors such as understanding natural language, recognizing patterns, acquiring knowledge, reasoning, planning, reflecting and using tools. This paper explores how their underlying…

Machine Learning · Computer Science 2023-11-15 Sumeet S. Singh

Humans readily generalize, applying prior knowledge to novel situations and stimuli. Advances in machine learning and artificial intelligence have begun to approximate and even surpass human performance, but machine systems reliably…

Artificial Intelligence · Computer Science 2025-12-10 Leonidas A. A. Doumas , Guillermo Puebla , Andrea E. Martin

Training autonomous agents that can learn new tasks from only a handful of demonstrations is a long-standing problem in machine learning. Recently, transformers have been shown to learn new language or vision tasks without any weight…

Machine Learning · Computer Science 2023-12-08 Sharath Chandra Raparthy , Eric Hambro , Robert Kirk , Mikael Henaff , Roberta Raileanu

We study theoretical guarantees for solving linear systems in-context using a linear transformer architecture. For in-domain generalization, we provide neural scaling laws that bound the generalization error in terms of the number of tasks…

Machine Learning · Computer Science 2025-05-27 Frank Cole , Yulong Lu , Wuzhe Xu , Tianhao Zhang