相关论文: Ethereum's Recursive Length Prefix in ACL2

The paper is organized as a self-contained literate Prolog program that implements elements of an executable finite set theory with focus on combinatorial generation and arithmetic encodings. The complete Prolog code is available at…

Reinforcement Learning with Human Feedback (RLHF) has emerged as an influential technique, enabling the alignment of large language models (LLMs) with human preferences. Despite the promising potential of RLHF, how to protect user…

Recent advancements in large language models (LLMs) have significantly enhanced their ability to understand both natural language and code, driving their use in tasks like natural language-to-code (NL2Code) and code summarisation. However,…

Parallel decoding methods such as Jacobi decoding show promise for more efficient LLM inference as it breaks the sequential nature of the LLM decoding process and transforms it into parallelizable computation. However, in practice, it…

Smart contracts are the building blocks of the "code is law" paradigm: the smart contract's code indisputably describes how its assets are to be managed - once it is created, its code is typically immutable. Faulty smart contracts present…

Large language models (LLMs) have exhibited remarkable few-shot learning capabilities and unified the paradigm of NLP tasks through the in-context learning (ICL) technique. Despite the success of ICL, the quality of the exemplar…

The Ethereum blockchain platform supports the execution of decentralised applications or smart contracts. These typically hold and transfer digital currency to other parties on the platform; however, they have been subject to numerous…

As the largest public blockchain-based platform supporting smart contracts, Ethereum has accumulated a large number of user transaction records since its debut in 2014. Analysis of Ethereum transaction records, however, is still relatively…

This paper describes a new set of block source codes well suited for data compression. These codes are defined by sets of productions rules of the form a.l->b, where a in A represents a value from the source alphabet A and l, b are -small-…

Time series classification (TSC) is a core machine learning problem with broad applications. Recently there has been growing interest in repurposing large language models (LLMs) for TSC, motivated by their strong reasoning and…

Variable-length feedback coding has the potential to significantly enhance communication reliability in finite block length scenarios by adapting coding strategies based on real-time receiver feedback. Designing such codes, however, is…

Publicly available, large pretrained LanguageModels (LMs) generate text with remarkable quality, but only sequentially from left to right. As a result, they are not immediately applicable to generation tasks that break the unidirectional…

Code Large Language Models (CodeLLMs) have demonstrated impressive proficiency in code completion tasks. However, they often fall short of fully understanding the extensive context of a project repository, such as the intricacies of…

Some of the most significant high-level properties of currencies are the sums of certain account balances. Properties of such sums can ensure the integrity of currencies and transactions. For example, the sum of balances should not be…

We investigate Early Hybrid Automatic Repeat reQuest (E-HARQ) feedback schemes enhanced by machine learning techniques as a path towards ultra-reliable and low-latency communication (URLLC). To this end, we propose machine learning methods…

Public companies and institutional investors that hold Bitcoin face increasing pressure to show solvency, manage risk, and satisfy regulatory expectations without exposing internal wallet structures or trading strategies. This paper…

In this article, we present a Shell Language Preprocessing (SLP) library, which implements tokenization and encoding directed at parsing Unix and Linux shell commands. We describe the rationale behind the need for a new approach with…

Language Models are the underpin of all modern Natural Language Processing (NLP) tasks. The introduction of the Transformers architecture has contributed significantly into making Language Modeling very effective across many NLP task,…

High-frequency trading (HFT) uses computer algorithms to make trading decisions in short time scales (e.g., second-level), which is widely used in the Cryptocurrency (Crypto) market (e.g., Bitcoin). Reinforcement learning (RL) in financial…

Edge probing tests are classification tasks that test for grammatical knowledge encoded in token representations coming from contextual encoders such as large language models (LLMs). Many LLM encoders have shown high performance in EP…