English
Related papers

Related papers: Is it a "Good" Encoding of Mixed Choice? (Technica…

200 papers

Large language models (LLMs) have exhibited impressive competence in various tasks, but their internal mechanisms on mathematical problems are still under-explored. In this paper, we study a fundamental question: how language models encode…

Computation and Language · Computer Science 2024-11-15 Fangwei Zhu , Damai Dai , Zhifang Sui

This document provides the supplementary material including a comprehensive related work, the complete proofs and extended evaluation results that support the manuscript, "Unified Characterization and Precoding for Non-Stationary Channels",…

Signal Processing · Electrical Eng. & Systems 2022-02-07 Zhibin Zou , Maqsood Careem , Aveek Dutta , Ngwe Thawdar

Despite their growing capabilities, language models still frequently reproduce content from their training data, generate repetitive text, and favor common grammatical patterns and vocabulary. A possible cause is the decoding strategy: the…

Computation and Language · Computer Science 2026-01-15 Giorgio Franceschelli , Mirco Musolesi

Pre-trained language models (PLMs) have gained increasing popularity due to their compelling prediction performance in diverse natural language processing (NLP) tasks. When formulating a PLM-based prediction pipeline for NLP tasks, it is…

Computation and Language · Computer Science 2022-10-17 Yuxin Xiao , Paul Pu Liang , Umang Bhatt , Willie Neiswanger , Ruslan Salakhutdinov , Louis-Philippe Morency

This thesis argues that the currently widely used Natural Language Processing algorithms possibly have various limitations related to the properties of the texts they handle and produce. With the wide adoption of these tools in rapid…

Computation and Language · Computer Science 2024-09-17 Josef Jon

Large language models (LLMs) have shown impressive performance in \emph{code} understanding and generation, making coding tasks a key focus for researchers due to their practical applications and value as a testbed for LLM evaluation. Data…

Separation logic is successful for software verification of heap-manipulating programs. Numbers are necessary to be added to separation logic for verification of practical software where numbers are important. However, properties of the…

Logic in Computer Science · Computer Science 2026-05-25 Sohei Ito , Makoto Tatsuta

An efficient numerical algorithm for the computation of linking number is presented. The algorithm keep tracks or rounding error so that it can ensure the correctness of the results.

Algebraic Topology · Mathematics 2020-01-01 Enrico Bertolazzi , Riccardo Ghiloni , Ruben Specogna

Vulnerability detection is garnering increasing attention in software engineering, since code vulnerabilities possibly pose significant security. Recently, reusing various code pre-trained models has become common for code embedding without…

Software Engineering · Computer Science 2024-08-12 Yu Zhao , Lina Gong , Zhiqiu Huang , Yongwei Wang , Mingqiang Wei , Fei Wu

In machine learning, metric elicitation refers to the selection of performance metrics that best reflect an individual's implicit preferences for a given application. Currently, metric elicitation methods only consider metrics that depend…

Machine Learning · Computer Science 2025-01-03 Chethan Bhateja , Joseph O'Brien , Afnaan Hashmi , Eva Prakash

We consider a large-scale matrix multiplication problem where the computation is carried out using a distributed system with a master node and multiple worker nodes, where each worker can store parts of the input matrices. We propose a…

Information Theory · Computer Science 2018-01-25 Qian Yu , Mohammad Ali Maddah-Ali , A. Salman Avestimehr

We tackle the problem of deciding whether two probabilistic programs are equivalent in Probabilistic NetKAT, a formal language for specifying and reasoning about the behavior of packet-switched networks. We show that the problem is…

Programming Languages · Computer Science 2018-03-28 Steffen Smolka , Praveen Kumar , Nate Foster , Justin Hsu , David Kahn , Dexter Kozen , Alexandra Silva

Text embeddings are essential for many tasks, such as document retrieval, clustering, and semantic similarity assessment. In this paper, we study how to contrastively train text embedding models in a compute-optimal fashion, given a suite…

Machine Learning · Computer Science 2024-11-22 Alicja Ziarko , Albert Q. Jiang , Bartosz Piotrowski , Wenda Li , Mateja Jamnik , Piotr Miłoś

Large Language Models (LLMs) exhibit impressive performance on a range of NLP tasks, due to the general-purpose linguistic knowledge acquired during pretraining. Existing model interpretability research (Tenney et al., 2019) suggests that a…

Finetuning is a common practice widespread across different communities to adapt pretrained models to particular tasks. Text classification is one of these tasks for which many pretrained models are available. On the other hand, ensembles…

Computation and Language · Computer Science 2024-10-29 Sebastian Pineda Arango , Maciej Janowski , Lennart Purucker , Arber Zela , Frank Hutter , Josif Grabocka

Computation codes in network information theory are designed for the scenarios where the decoder is not interested in recovering the information sources themselves, but only a function thereof. K\"orner and Marton showed for distributed…

Information Theory · Computer Science 2017-07-28 Jingge Zhu , Sung Hoon Lim , Michael Gastpar

Instruction fine-tuning of large language models (LLMs) often involves selecting a subset of instruction training data from a large candidate pool, using a small query set from the target task. Despite growing interest, the literature on…

Machine Learning · Computer Science 2026-02-17 Nihal V. Nayak , Paula Rodriguez-Diaz , Neha Hulkund , Sara Beery , David Alvarez-Melis

The goal of this paper is to provide a rigorous information-theoretic analysis of subnetworks of interference networks. We prove two coding theorems for the compound multiple-access channel with an arbitrary number of channel states. The…

Information Theory · Computer Science 2011-02-02 Moritz Wiese , Holger Boche , Igor Bjelaković , Volker Jungnickel

Error probability distribution associated with a given Clifford measurement circuit is described exactly in terms of the circuit error-equivalence group, or the circuit subsystem code previously introduced by Bacon, Flammia, Harrow, and…

Quantum Physics · Physics 2020-08-12 Leonid P. Pryadko

Two indicators are classically used to evaluate the quality of rule-based classification systems: predictive accuracy, i.e. the system's ability to successfully reproduce learning data and coverage, i.e. the proportion of possible cases for…

Artificial Intelligence · Computer Science 2020-04-07 Nassim Dehouche