English
Related papers

Related papers: How much do contextualized representations encode …

200 papers

Token prediction stability remains a challenge in autoregressive generative models, where minor variations in early inference steps often lead to significant semantic drift over extended sequences. A structured modulation mechanism was…

In order to assess the short-term memory performance of non-linear random neural networks, we introduce a measure to quantify the dependence of a neural representation upon the past context. We study this measure both numerically and…

Disordered Systems and Neural Networks · Physics 2016-03-08 Gilles Wainrib

We use large language models (LLMs) to uncover long-ranged structure in English texts from a variety of sources. The conditional entropy or code length in many cases continues to decrease with context length at least to $N\sim 10^4$…

Statistical Mechanics · Physics 2026-01-01 Colin Scheibner , Lindsay M. Smith , William Bialek

Dense document embeddings are central to neural retrieval. The dominant paradigm is to train and construct embeddings by running encoders directly on individual documents. In this work, we argue that these embeddings, while effective, are…

Computation and Language · Computer Science 2024-11-11 John X. Morris , Alexander M. Rush

Multimodal foundation models aim to create a unified representation space that abstracts away from surface features like language syntax or modality differences. To investigate this, we study the internal representations of three recent…

Computation and Language · Computer Science 2025-02-21 Hyunji Lee , Danni Liu , Supriti Sinhamahapatra , Jan Niehues

Extending large language models (LLMs) to process longer inputs is crucial for a wide range of applications. However, the substantial computational cost of transformers and limited generalization of positional encoding restrict the size of…

Computation and Language · Computer Science 2025-06-11 Howard Yen , Tianyu Gao , Danqi Chen

Conversational speech recognition is regarded as a challenging task due to its free-style speaking and long-term contextual dependencies. Prior work has explored the modeling of long-range context through RNNLM rescoring with improved…

Sound · Computer Science 2020-11-19 Kun Wei , Pengcheng Guo , Hang Lv , Zhen Tu , Lei Xie

This study investigates the existence of positional biases in Transformer-based models for text representation learning, particularly in the context of web document retrieval. We build on previous research that demonstrated loss of…

Information Retrieval · Computer Science 2024-10-29 João Coelho , Bruno Martins , João Magalhães , Jamie Callan , Chenyan Xiong

Large Language Models (LLMs) often exhibit behavioral artifacts such as laziness (premature truncation of responses or partial compliance with multi-part requests), decoding suboptimality (failure to select higher-quality sequences due to…

Artificial Intelligence · Computer Science 2025-12-25 Yiqing Ma , Jung-Hua Liu

This work investigates context compression for Large Language Models (LLMs) using learned compression tokens to reduce the memory and computational demands of processing long sequences. We demonstrate that pre-trained LLMs can be fine-tuned…

Computation and Language · Computer Science 2025-11-12 Dmitrii Tarasov , Elizaveta Goncharova , Kuznetsov Andrey

Transformer-based language models (LMs) are powerful and widely-applicable tools, but their usefulness is constrained by a finite context window and the expensive computational cost of processing long text documents. We propose to adapt…

Computation and Language · Computer Science 2023-11-07 Alexis Chevalier , Alexander Wettig , Anirudh Ajith , Danqi Chen

Transformer-based language models benefit from conditioning on contexts of hundreds to thousands of previous tokens. What aspects of these contexts contribute to accurate model prediction? We describe a series of experiments that measure…

Computation and Language · Computer Science 2021-06-17 Joe O'Connor , Jacob Andreas

As large language models increasingly gain popularity in real-world applications, processing extremely long contexts, often exceeding the model's pre-trained context limits, has emerged as a critical challenge. While existing approaches to…

Large Language Models (LLMs) have demonstrated remarkable performance across various tasks. However, they are prone to contextual hallucination, generating information that is either unsubstantiated or contradictory to the given context.…

Computation and Language · Computer Science 2025-04-29 Siyi Liu , Kishaloy Halder , Zheng Qi , Wei Xiao , Nikolaos Pappas , Phu Mon Htut , Neha Anna John , Yassine Benajiba , Dan Roth

Pre-trained Transformer models have achieved successes in a wide range of NLP tasks, but are inefficient when dealing with long input sequences. Existing studies try to overcome this challenge via segmenting the long sequence followed by…

Computation and Language · Computer Science 2022-03-16 Xiangyang Mou , Mo Yu , Bingsheng Yao , Lifu Huang

Large Language Models (LLMs) face significant challenges in long-context processing, including quadratic computational costs, information forgetting, and the context fragmentation inherent in retrieval-augmented generation (RAG). We propose…

Computation and Language · Computer Science 2026-02-10 Zhuoen Chen , Dongfang Li , Meishan Zhang , Baotian Hu , Min Zhang

This study reports an unintuitive finding that positional encoding enhances learning of recurrent neural networks (RNNs). Positional encoding is a high-dimensional representation of time indices on input data. Most famously, positional…

Machine Learning · Computer Science 2024-11-28 Takashi Morita

A major limitation for the broader scope of problems solvable by transformers is the quadratic scaling of computational complexity with input size. In this study, we investigate the recurrent memory augmentation of pre-trained transformer…

Computation and Language · Computer Science 2024-02-07 Aydar Bulatov , Yuri Kuratov , Yermek Kapushev , Mikhail S. Burtsev

In this work we explore recent advances in Recurrent Neural Networks for large scale Language Modeling, a task central to language understanding. We extend current models to deal with two key challenges present in this task: corpora and…

Computation and Language · Computer Science 2016-02-15 Rafal Jozefowicz , Oriol Vinyals , Mike Schuster , Noam Shazeer , Yonghui Wu

State-space models are a low-complexity alternative to transformers for encoding long sequences and capturing long-term dependencies. We propose LOCOST: an encoder-decoder architecture based on state-space models for conditional text…

‹ Prev 1 4 5 6 7 8 10 Next ›