English
Related papers

Related papers: Towards Understanding the Relationship between In-…

200 papers

What factors contribute to the relative success and corresponding difficulties of in-context learning for Large Language Models (LLMs)? Drawing on insights from the literature on human concept learning, we test LLMs on carefully designed…

Computation and Language · Computer Science 2024-12-05 Leroy Z. Wang , R. Thomas McCoy , Shane Steinert-Threlkeld

Compositional generalization is the capability of a model to understand novel compositions composed of seen concepts. There are multiple levels of novel compositions including phrase-phrase level, phrase-word level, and word-word level.…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Chuanhao Li , Zhen Li , Chenchen Jing , Xiaomeng Fan , Wenbo Ye , Yuwei Wu , Yunde Jia

We propose a simple data augmentation protocol aimed at providing a compositional inductive bias in conditional and unconditional sequence models. Under this protocol, synthetic training examples are constructed by taking real training…

Computation and Language · Computer Science 2020-05-20 Jacob Andreas

Despite their strong performance on many tasks, pre-trained language models have been shown to struggle on out-of-distribution compositional generalization. Meanwhile, recent work has shown considerable improvements on many NLP tasks from…

Computation and Language · Computer Science 2022-10-26 Linlu Qiu , Peter Shaw , Panupong Pasupat , Tianze Shi , Jonathan Herzig , Emily Pitler , Fei Sha , Kristina Toutanova

Transformers can under some circumstances generalize to novel problem instances whose constituent parts might have been encountered during training, but whose compositions have not. What mechanisms underlie this ability for compositional…

Machine Learning · Computer Science 2025-02-18 Simon Schug , Seijin Kobayashi , Yassir Akram , João Sacramento , Razvan Pascanu

Regression models often fail to generalize effectively in regions characterized by highly imbalanced label distributions. Previous methods for deep imbalanced regression rely on gradient-based weight updates, which tend to overfit in…

Machine Learning · Computer Science 2024-11-21 Ismail Nejjar , Faez Ahmed , Olga Fink

A leading hypothesis for the surprising generalization of neural networks is that the dynamics of gradient descent bias the model towards simple solutions, by searching through the solution space in an incremental order of complexity. We…

Machine Learning · Computer Science 2020-01-01 Daniel Gissin , Shai Shalev-Shwartz , Amit Daniely

Humans exhibit remarkable compositional reasoning by integrating knowledge from various sources. For example, if someone learns ( B = f(A) ) from one source and ( C = g(B) ) from another, they can deduce ( C=g(B)=g(f(A)) ) even without…

Artificial Intelligence · Computer Science 2025-10-14 Yutong Yin , Zhaoran Wang

Recurrent neural networks have recently been used for learning to describe images using natural language. However, it has been observed that these models generalize poorly to scenes that were not observed during training, possibly depending…

Computer Vision and Pattern Recognition · Computer Science 2016-08-30 Yuval Atzmon , Jonathan Berant , Vahid Kezami , Amir Globerson , Gal Chechik

Large language models (LLMs) exhibit remarkable task generalization, solving tasks they were never explicitly trained on with only a few demonstrations. This raises a fundamental question: When can learning from a small set of tasks…

Machine Learning · Computer Science 2025-06-10 Amirhesam Abedsoltan , Huaqing Zhang , Kaiyue Wen , Hongzhou Lin , Jingzhao Zhang , Mikhail Belkin

We study implicit reasoning, i.e. the ability to combine knowledge or rules within a single forward pass. While transformer-based large language models store substantial factual knowledge and rules, they often fail to compose this knowledge…

Computation and Language · Computer Science 2026-04-10 Harsh Kohli , Srinivasan Parthasarathy , Huan Sun , Yuekun Yao

Communication is compositional if complex signals can be represented as a combination of simpler subparts. In this paper, we theoretically show that inductive biases on both the training framework and the data are needed to develop a…

Machine Learning · Computer Science 2024-04-04 Łukasz Kuciński , Tomasz Korbak , Paweł Kołodziej , Piotr Miłoś

Machine Learning Interatomic Potentials play a fundamental role in computational chemistry and materials science, enabling applications from molecular dynamics simulations to drug design and materials discovery. While recent approaches can…

Machine Learning · Computer Science 2026-05-12 Amir Masoud Nourollah , Irtaza Khalid , Stefano Leoni , Steven Schockaert

To apply neural sequence models such as the Transformers to music generation tasks, one has to represent a piece of music by a sequence of tokens drawn from a finite set of pre-defined vocabulary. Such a vocabulary usually involves tokens…

Sound · Computer Science 2021-01-08 Wen-Yi Hsiao , Jen-Yu Liu , Yin-Cheng Yeh , Yi-Hsuan Yang

Deep learning has led researchers to rethink the relationship between memorization and generalization. In many settings, memorization does not hurt generalization due to implicit regularization and may help by memorizing long-tailed…

Machine Learning · Computer Science 2025-10-22 Mo Zhou , Haoyang Ma , Rong Ge

Question answering models struggle to generalize to novel compositions of training patterns, such to longer sequences or more complex test structures. Current end-to-end models learn a flat input embedding which can lose input syntax…

Computation and Language · Computer Science 2021-11-08 Yu Gai , Paras Jain , Wendi Zhang , Joseph E. Gonzalez , Dawn Song , Ion Stoica

Large-scale models trained on broad data have recently become the mainstream architecture in computer vision due to their strong generalization performance. In this paper, the main focus is on an emergent ability in large vision models,…

Computer Vision and Pattern Recognition · Computer Science 2023-02-02 Yuanhan Zhang , Kaiyang Zhou , Ziwei Liu

We introduce a dataset of concept learning tasks that helps uncover implicit biases in large language models. Using in-context concept learning experiments, we found that language models may have a bias toward upward monotonicity in…

Computation and Language · Computer Science 2025-11-27 Leroy Z. Wang

Large language models have demonstrated strong capabilities to learn in-context, where exemplar input-output pairings are appended to the prompt for demonstration. However, existing work has demonstrated the ability of models to learn…

Computation and Language · Computer Science 2025-02-11 Stephanie Schoch , Yangfeng Ji

In-context learning (ICL) research often considers learning a function in-context through a uniform sample of input-output pairs. Here, we investigate how presenting a compositional subtask curriculum in context may alter the computations a…

Machine Learning · Computer Science 2025-06-17 Jin Hwa Lee , Andrew K. Lampinen , Aaditya K. Singh , Andrew M. Saxe