English
Related papers

Related papers: ParaScopes: What do Language Models Activations En…

200 papers

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

Large language models (LLMs) based on Transformer have been widely applied in the filed of natural language processing (NLP), demonstrating strong performance, particularly in handling short text tasks. However, when it comes to long…

Computation and Language · Computer Science 2025-07-09 Yijun Liu , Jinzheng Yu , Yang Xu , Zhongyang Li , Qingfu Zhu

Most vision-language models (VLMs) apply a large language model (LLM) as the decoder, where the response tokens are generated sequentially through autoregression. Therefore, the number of output tokens can be the bottleneck of the…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Sixun Dong , Juhua Hu , Steven Li , Wei Wen , Qi Qian

Many applications of large language models (LLMs) require long-context understanding, but models continue to struggle with such tasks. We hypothesize that conventional next-token prediction training could contribute to this, because each…

Computation and Language · Computer Science 2025-03-13 Falko Helm , Nico Daheim , Iryna Gurevych

Understanding the internal representations of large language models (LLMs) is a central challenge in interpretability research. Existing feature interpretability methods often rely on strong assumptions about the structure of…

Machine Learning · Computer Science 2025-09-30 Yifan Luo , Zhennan Zhou , Bin Dong

While there is much recent interest in studying why Transformer-based large language models make predictions the way they do, the complex computations performed within each layer have made their behavior somewhat opaque. To mitigate this…

Computation and Language · Computer Science 2023-06-06 Byung-Doh Oh , William Schuler

Language models typically need to be trained or finetuned in order to acquire new knowledge, which involves updating their weights. We instead envision language models that can simply read and memorize new data at inference time, thus…

Machine Learning · Computer Science 2022-03-18 Yuhuai Wu , Markus N. Rabe , DeLesley Hutchins , Christian Szegedy

Although Transformers with fully connected self-attentions are powerful to model long-term dependencies, they are struggling to scale to long texts with thousands of words in language modeling. One of the solutions is to equip the model…

Computation and Language · Computer Science 2022-04-27 Haozhe Ji , Rongsheng Zhang , Zhenyu Yang , Zhipeng Hu , Minlie Huang

The usage of transformers has grown from learning about language semantics to forming meaningful visiolinguistic representations. These architectures are often over-parametrized, requiring large amounts of computation. In this work, we…

Computation and Language · Computer Science 2020-07-09 Prajjwal Bhargava

The ability to automatically identify whether an entity is referenced in a future context can have multiple applications including decision making, planning and trend forecasting. This paper focuses on detecting implicit future references…

Computation and Language · Computer Science 2025-02-24 Puneet Prashar , Krishna Mohan Shukla , Adam Jatowt

Training large language models (LLMs) on Python execution traces grounds them in code execution and enables the line-by-line execution prediction of whole Python programs, effectively turning them into neural interpreters (FAIR CodeGen Team…

Machine Learning · Computer Science 2026-03-11 Maximilian Beck , Jonas Gehring , Jannik Kossen , Gabriel Synnaeve

Language models trained on large text corpora encode rich distributional information about real-world environments and action sequences. This information plays a crucial role in current approaches to language processing tasks like question…

Machine Learning · Computer Science 2023-02-07 Belinda Z. Li , William Chen , Pratyusha Sharma , Jacob Andreas

Transformers achieve unrivalled performance in modelling language, but remain inefficient in terms of memory and time complexity. A possible remedy is to reduce the sequence length in the intermediate layers by pooling fixed-length segments…

Computation and Language · Computer Science 2023-10-25 Piotr Nawrot , Jan Chorowski , Adrian Łańcucki , Edoardo M. Ponti

We explore neural language modeling for speech recognition where the context spans multiple sentences. Rather than encode history beyond the current sentence using a cache of words or document-level features, we focus our study on the…

Computation and Language · Computer Science 2019-11-13 Sarangarajan Parthasarathy , William Gale , Xie Chen , George Polovets , Shuangyu Chang

Speech-to-text translation has many potential applications for low-resource languages, but the typical approach of cascading speech recognition with machine translation is often impossible, since the transcripts needed to train a speech…

Computation and Language · Computer Science 2018-06-19 Sameer Bansal , Herman Kamper , Karen Livescu , Adam Lopez , Sharon Goldwater

Recent language modeling performance has been greatly improved by the use of external memory. This memory encodes the context so that similar contexts can be recalled during decoding. This similarity depends on how the model learns to…

Computation and Language · Computer Science 2022-10-31 Severino Trotta , Lucie Flek , Charles Welch

Information flows by routes inside the network via mechanisms implemented in the model. These routes can be represented as graphs where nodes correspond to token representations and edges to operations inside the network. We automatically…

Computation and Language · Computer Science 2024-04-18 Javier Ferrando , Elena Voita

Language and vision-language models have shown impressive performance across a wide range of tasks, but their internal mechanisms remain only partly understood. In this work, we study how individual attention heads in text-generative models…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Lorenzo Basile , Valentino Maiorca , Diego Doimo , Francesco Locatello , Alberto Cazzaniga

Using more test-time computation during language model inference, such as generating more intermediate thoughts or sampling multiple candidate answers, has proven effective in significantly improving model performance. This paper takes an…

Machine Learning · Computer Science 2025-08-20 Xingwu Chen , Miao Lu , Beining Wu , Difan Zou

Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on NLP tasks, but their black-box nature, which leads to a lack of interpretability, has been a major concern. My…

Computation and Language · Computer Science 2024-12-06 Ximing Wen