English
Related papers

Related papers: The Generalization Ridge: Information Flow in Natu…

200 papers

Modern deep neural networks display striking examples of rich internal computational structure. Uncovering principles governing the development of such structure is a priority for the science of deep learning. In this paper, we explore the…

Machine Learning · Computer Science 2025-02-03 Liam Carroll , Jesse Hoogland , Matthew Farrugia-Roberts , Daniel Murfet

From extracting features to generating text, the outputs of large language models (LLMs) typically rely on the final layers, following the conventional wisdom that earlier layers capture only low-level cues. However, our analysis shows that…

Machine Learning · Computer Science 2025-06-17 Oscar Skean , Md Rifat Arefin , Dan Zhao , Niket Patel , Jalal Naghiyev , Yann LeCun , Ravid Shwartz-Ziv

Large Language Models (LLMs) are adept at generating responses based on information within their context. While this ability is useful for interacting with structured data like code files, another popular method, Retrieval-Augmented…

Computation and Language · Computer Science 2025-10-22 Mihir Gupte , Paolo Giusto , Ramesh S

Retrieval-augmented generation (RAG) is a promising paradigm, yet its trustworthiness remains a critical concern. A major vulnerability arises prior to generation: models often fail to balance parametric (internal) and retrieved (external)…

Computation and Language · Computer Science 2026-01-08 Xinbang Dai , Huikang Hu , Yuncheng Hua , Jiaqi Li , Yongrui Chen , Rihui Jin , Nan Hu , Guilin Qi

Natural language generation (NLG) spans a broad range of tasks, each of which serves for specific objectives and desires different properties of generated text. The complexity makes automatic evaluation of NLG particularly challenging.…

Computation and Language · Computer Science 2022-01-25 Mingkai Deng , Bowen Tan , Zhengzhong Liu , Eric P. Xing , Zhiting Hu

Large language models often reason beyond surface tokens, but the internal stage at which token-level information becomes abstract relational structure remains unclear. We investigate this question by analyzing how attention heads and…

Artificial Intelligence · Computer Science 2026-05-22 Junjie Zhang , Zhen Shen , Xisong Dong , Gang Xiong

We study a data-dependent notion of diffusion-model generalization: when a model does not memorize the training set, where do its generated samples go relative to the geometry induced by the data? To answer this, we introduce a…

Machine Learning · Statistics 2026-05-14 Ye He , Yitong Qiu , Molei Tao

The Retrieval-Augmented Generation (RAG) framework introduces a retrieval module to dynamically inject retrieved information into the input context of large language models (LLMs), and has demonstrated significant success in various NLP…

Information Retrieval · Computer Science 2025-05-27 Yi Jiang , Sendong Zhao , Jianbo Li , Haochun Wang , Bing Qin

Large Language Models (LLMs) have demonstrated superior results across a wide range of tasks, and Retrieval-augmented Generation (RAG) is an effective way to enhance the performance by locating relevant information and placing it into the…

Computation and Language · Computer Science 2024-02-22 Zixuan Ke , Weize Kong , Cheng Li , Mingyang Zhang , Qiaozhu Mei , Michael Bendersky

Retrieval-augmented generation (RAG) encounters challenges when addressing complex queries, particularly multi-hop questions. While several methods tackle multi-hop queries by iteratively generating internal queries and retrieving external…

Computation and Language · Computer Science 2026-01-30 Jiaen Lin , Jingyu Liu , Yingbo Liu

Traditional methods for deep NLG adopt pipeline approaches comprising stages such as constructing syntactic input, predicting function words, linearizing the syntactic input and generating the surface forms. Though easier to visualize,…

Computation and Language · Computer Science 2019-11-11 Ratish Puduppully , Yue Zhang , Manish Shrivastava

Retrieval-augmented generation (RAG) incorporates external knowledge into large language models (LLMs), improving their adaptability to downstream tasks and enabling information updates. Surprisingly, recent empirical evidence demonstrates…

Computation and Language · Computer Science 2026-01-08 Yang Sun , Zhiyong Xie , Lixin Zou , Dan Luo , Min Tang , Xiangyu Zhao , Yunwei Zhao , Xixun Lin , Yanxiong Lu , Chenliang Li

We prove theoretically that generalization improves not only through data scaling but also by compressing internal representations. To operationalize this insight, we introduce the Information Bottleneck Language Modeling (IBLM) objective,…

Machine Learning · Computer Science 2025-10-23 Fangyuan Yu

Retrieval-Augmented Generation (RAG) systems traditionally treat retrieval and generation as separate processes, requiring explicit textual queries to connect them. This separation can limit the ability of models to generalize across…

Computation and Language · Computer Science 2025-09-19 Wenzheng Zhang , Xi Victoria Lin , Karl Stratos , Wen-tau Yih , Mingda Chen

Unified multimodal understanding and generation models recently have achieve significant improvement in image generation capability, yet a large gap remains in instruction following and detail preservation compared to systems that tightly…

Retrieval-Augmented Generation (RAG) has become a foundational paradigm for equipping large language models (LLMs) with external knowledge, playing a critical role in information retrieval and knowledge-intensive applications. However,…

Computation and Language · Computer Science 2025-06-10 Weihang Su , Qingyao Ai , Jingtao Zhan , Qian Dong , Yiqun Liu

In-context learning (ICL) enables large language models (LLMs) to acquire new behaviors from the input sequence alone without any parameter updates. Recent studies have shown that ICL can surpass the original meaning learned in pretraining…

Machine Learning · Computer Science 2025-07-31 Yongyi Yang , Hidenori Tanaka , Wei Hu

Large scale neural models show impressive performance across a wide array of linguistic tasks. Despite this they remain, largely, black-boxes - inducing vector-representations of their input that prove difficult to interpret. This limits…

Computation and Language · Computer Science 2024-06-05 Henry Conklin , Kenny Smith

Deep learning has transformed computer vision, natural language processing, and speech recognition\cite{badrinarayanan2017segnet, dong2016image, ren2017faster, ji20133d}. However, two critical questions remain obscure: (1) why do deep…

Machine Learning · Statistics 2018-10-03 Jingwei Zhang , Tongliang Liu , Dacheng Tao

Although the Retrieval-Augmented Generation (RAG) paradigms can use external knowledge to enhance and ground the outputs of Large Language Models (LLMs) to mitigate generative hallucinations and static knowledge base problems, they still…

Computation and Language · Computer Science 2024-05-24 Diji Yang , Jinmeng Rao , Kezhen Chen , Xiaoyuan Guo , Yawen Zhang , Jie Yang , Yi Zhang
‹ Prev 1 2 3 10 Next ›