English
Related papers

Related papers: Function Induction and Task Generalization: An Int…

200 papers

Large Language Models (LLMs) have demonstrated remarkable in-context learning (ICL) capabilities. In this study, we explore a surprising phenomenon related to ICL: LLMs can perform multiple, computationally distinct ICL tasks…

This book chapter is an introduction to and an overview of the information-theoretic, task independent utility function "Empowerment", which is defined as the channel capacity between an agent's actions and an agent's sensors. It quantifies…

Artificial Intelligence · Computer Science 2013-10-09 Christoph Salge , Cornelius Glackin , Daniel Polani

While Large Language Models (LLMs) have demonstrated exceptional multitasking abilities, fine-tuning these models on downstream, domain-specific datasets is often necessary to yield superior performance on test sets compared to their…

Computation and Language · Computer Science 2024-03-15 Haoran Yang , Yumeng Zhang , Jiaqi Xu , Hongyuan Lu , Pheng Ann Heng , Wai Lam

Transformers often struggle with length generalization, meaning they fail to generalize to sequences longer than those encountered during training. While arithmetic tasks are commonly used to study length generalization, certain tasks are…

Machine Learning · Computer Science 2025-04-18 Hanseul Cho , Jaeyoung Cha , Srinadh Bhojanapalli , Chulhee Yun

Much research in machine learning involves finding appropriate inductive biases (e.g. convolutional neural networks, momentum-based optimizers, transformers) to promote generalization on tasks. However, quantification of the amount of…

Machine Learning · Computer Science 2024-06-25 Akhilan Boopathy , William Yue , Jaedong Hwang , Abhiram Iyer , Ila Fiete

We apply foundation models to data discovery and exploration tasks. Foundation models include large language models (LLMs) that show promising performance on a range of diverse tasks unrelated to their training. We show that these models…

Databases · Computer Science 2024-04-09 Moe Kayali , Anton Lykov , Ilias Fountalis , Nikolaos Vasiloglou , Dan Olteanu , Dan Suciu

Knowledge editing for large language models can offer an efficient solution to alter a model's behavior without negatively impacting the overall performance. However, the current approaches encounter issues with limited generalizability…

Computation and Language · Computer Science 2024-04-30 Ningyu Zhang , Bozhong Tian , Siyuan Cheng , Xiaozhuan Liang , Yi Hu , Kouying Xue , Yanjie Gou , Xi Chen , Huajun Chen

Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves…

Computer Vision and Pattern Recognition · Computer Science 2023-07-25 Yining Hong , Haoyu Zhen , Peihao Chen , Shuhong Zheng , Yilun Du , Zhenfang Chen , Chuang Gan

Reinforcement learning (RL)-based post-training often improves the reasoning performance of large language models (LLMs) beyond the training domain, while supervised fine-tuning (SFT) frequently leads to general capabilities forgetting.…

Computation and Language · Computer Science 2026-04-29 Dan Shi , Zhuowen Han , Simon Ostermann , Renren Jin , Josef van Genabith , Deyi Xiong

Understanding the inner workings of machine learning models like Transformers is vital for their safe and ethical use. This paper provides a comprehensive analysis of a one-layer Transformer model trained to perform n-digit integer…

Machine Learning · Computer Science 2024-04-25 Philip Quirke , Fazl Barez

Mechanistic interpretability research seeks to reveal the inner workings of large language models, yet most work focuses on classification or generative tasks rather than summarization. This paper presents an interpretability framework for…

Computation and Language · Computer Science 2025-05-26 Anurag Mishra

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…

Artificial Intelligence · Computer Science 2026-03-03 Ely Hahami , Ishaan Sinha , Lavik Jain , Josh Kaplan , Jon Hahami

Multi--task learning seeks to improve the generalization error by leveraging the common information shared by multiple related tasks. One challenge in multi--task learning is identifying formulations capable of uncovering the common…

Machine Learning · Computer Science 2026-03-06 Ayed M. Alrashdi , Oussama Dhifallah , Houssem Sifaou

Understanding how agents learn to generalize -- and, in particular, to extrapolate -- in high-dimensional, naturalistic environments remains a challenge for both machine learning and the study of biological agents. One approach to this has…

Machine Learning · Computer Science 2021-06-15 Simon N. Segert , Jonathan D. Cohen

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Language models (LMs) struggle to perform such reasoning consistently. We propose an approach to pinpoint and rectify multi-hop…

Computation and Language · Computer Science 2024-11-11 Mansi Sakarvadia

Contextualized embeddings use unsupervised language model pretraining to compute word representations depending on their context. This is intuitively useful for generalization, especially in Named-Entity Recognition where it is crucial to…

Computation and Language · Computer Science 2020-01-23 Bruno Taillé , Vincent Guigue , Patrick Gallinari

In-context learning is a surprising and important phenomenon that emerged when modern language models were scaled to billions of learned parameters. Without modifying a large language model's weights, it can be tuned to perform various…

Computation and Language · Computer Science 2023-03-15 Noam Wies , Yoav Levine , Amnon Shashua

Many computer vision tasks address the problem of scene understanding and are naturally interrelated e.g. object classification, detection, scene segmentation, depth estimation, etc. We show that we can leverage the inherent relationships…

Computer Vision and Pattern Recognition · Computer Science 2021-03-18 Yao Lu , Sören Pirk , Jan Dlabal , Anthony Brohan , Ankita Pasad , Zhao Chen , Vincent Casser , Anelia Angelova , Ariel Gordon

Neural network models often generalize poorly to mismatched domains or distributions. In NLP, this issue arises in particular when models are expected to generalize compositionally, that is, to novel combinations of familiar words and…

Computation and Language · Computer Science 2021-11-10 Wang Zhu , Peter Shaw , Tal Linzen , Fei Sha

We introduce the task of predicting adverbial presupposition triggers such as also and again. Solving such a task requires detecting recurring or similar events in the discourse context, and has applications in natural language generation…

Computation and Language · Computer Science 2018-06-13 Andre Cianflone , Yulan Feng , Jad Kabbara , Jackie Chi Kit Cheung