English
Related papers

Related papers: Measuring In-Context Computation Complexity via Hi…

200 papers

We present an interpretable neural network approach to predicting and understanding politeness in natural language requests. Our models are based on simple convolutional neural networks directly on raw text, avoiding any manual…

Computation and Language · Computer Science 2016-10-11 Malika Aubakirova , Mohit Bansal

Large language models (LLMs) contain substantial factual knowledge which is commonly elicited by multiple-choice question-answering prompts. Internally, such models process the prompt through multiple transformer layers, building varying…

Computation and Language · Computer Science 2025-01-31 Didier Chételat , Joseph Cotnareanu , Rylee Thompson , Yingxue Zhang , Mark Coates

Existing work on understanding deep learning often employs measures that compress all data-dependent information into a few numbers. In this work, we adopt a perspective based on the role of individual examples. We introduce a measure of…

Machine Learning · Computer Science 2021-06-21 Robert J. N. Baldock , Hartmut Maennel , Behnam Neyshabur

Transformer-based models generate hidden states that are difficult to interpret. In this work, we analyze hidden states and modify them at inference, with a focus on motion forecasting. We use linear probing to analyze whether interpretable…

Machine Learning · Computer Science 2025-05-19 Omer Sahin Tas , Royden Wagner

We conjecture that hidden state vectors corresponding to individual input tokens encode information sufficient to accurately predict several tokens ahead. More concretely, in this paper we ask: Given a hidden (internal) representation of a…

Computation and Language · Computer Science 2024-03-14 Koyena Pal , Jiuding Sun , Andrew Yuan , Byron C. Wallace , David Bau

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

Estimating the difficulty of input questions as perceived by large language models (LLMs) is essential for accurate performance evaluation and adaptive inference. Existing methods typically rely on repeated response sampling, auxiliary…

Computation and Language · Computer Science 2025-09-17 Yubo Zhu , Dongrui Liu , Zecheng Lin , Wei Tong , Sheng Zhong , Jing Shao

A significant number of neural architectures for reading comprehension have recently been developed and evaluated on large cloze-style datasets. We present experiments supporting the emergence of "predication structure" in the hidden state…

Computation and Language · Computer Science 2017-06-01 Hai Wang , Takeshi Onishi , Kevin Gimpel , David McAllester

When a language model generates text, the selection of individual tokens might lead it down very different reasoning paths, making uncertainty difficult to quantify. In this work, we consider whether reasoning language models represent the…

Computation and Language · Computer Science 2025-11-07 Amir Zur , Atticus Geiger , Ekdeep Singh Lubana , Eric Bigelow

While transferring a pretrained language model, common approaches conventionally attach their task-specific classifiers to the top layer and adapt all the pretrained layers. We investigate whether one could make a task-specific selection on…

Computation and Language · Computer Science 2022-10-20 Shuo Xie , Jiahao Qiu , Ankita Pasad , Li Du , Qing Qu , Hongyuan Mei

In many computer vision tasks, for example saliency prediction or semantic segmentation, the desired output is a foreground map that predicts pixels where some criteria is satisfied. Despite the inherently spatial nature of this task…

Computer Vision and Pattern Recognition · Computer Science 2017-08-08 Nicholas Kolkin , Gregory Shakhnarovich , Eli Shechtman

Recent reasoning language models, particularly those that employ long latent chains of thought, achieve strong performance on complex agentic tasks. However, as these models operate over increasingly long time horizons, their internal…

Machine Learning · Computer Science 2026-05-27 Hans Peter Lyngsøe Raaschou-Jensen , Constanza Fierro , Anders Søgaard

Adaptive cognition requires structured internal models of objects and their relations. Predictive neural networks are often proposed to learn such world models, but how these are instantiated and how they support prediction remain unclear.…

Machine Learning · Computer Science 2026-05-11 Linda Ariel Ventura , Victoria Bosch , Tim C Kietzmann , Sushrut Thorat

Recent research towards understanding neural networks probes models in a top-down manner, but is only able to identify model tendencies that are known a priori. We propose Susceptibility Identification through Fine-Tuning (SIFT), a novel…

Computation and Language · Computer Science 2019-09-11 Jonas Pfeiffer , Aishwarya Kamath , Iryna Gurevych , Sebastian Ruder

While deep neural networks have achieved remarkable performance, they tend to lack transparency in prediction. The pursuit of greater interpretability in neural networks often results in a degradation of their original performance. Some…

Computer Vision and Pattern Recognition · Computer Science 2024-08-09 Hefeng Wu , Hao Jiang , Keze Wang , Ziyi Tang , Xianghuan He , Liang Lin

Deep learning has produced big advances in artificial intelligence, but trained neural networks often reflect and amplify bias in their training data, and thus produce unfair predictions. We propose a novel measure of individual fairness,…

Artificial Intelligence · Computer Science 2020-09-30 Krystal Maughan , Joseph P. Near

This report addresses state inference for hidden Markov models. These models rely on unobserved states, which often have a meaningful interpretation. This makes it necessary to develop diagnostic tools for quantification of state…

Statistics Theory · Mathematics 2018-10-26 Jean-Baptiste Durand , Y. Guédon

Large language models display remarkable capabilities in logical and mathematical reasoning, allowing them to solve complex tasks. Interestingly, these abilities emerge in networks trained on the simple task of next-token prediction. In…

Machine Learning · Computer Science 2024-07-31 Eran Malach

Chain-of-thought responses from language models improve performance across most benchmarks. However, it remains unclear to what extent these performance gains can be attributed to human-like task decomposition or simply the greater…

Computation and Language · Computer Science 2024-04-25 Jacob Pfau , William Merrill , Samuel R. Bowman

In continual learning scenarios, catastrophic forgetting of previously learned tasks is a critical issue, making it essential to effectively measure such forgetting. Recently, there has been growing interest in focusing on representation…

Machine Learning · Computer Science 2025-06-13 Joonkyu Kim , Yejin Kim , Jy-yong Sohn
‹ Prev 1 2 3 10 Next ›