Related papers: Advancing Automated In-Isolation Validation in Rep…

Process reward models (PRMs) have shown success in complex reasoning tasks for large language models (LLMs). However, their application to machine translation (MT) remains underexplored due to the lack of systematic methodologies and…

Rust is a strong contender for a memory-safe alternative to C as a "systems" language, but porting the vast amount of existing C code to Rust remains daunting. In this paper, we evaluate the potential of large language models (LLMs) to…

Ensuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and reinforcement learning with human feedback have shown promise, they require a substantial…

Acquiring labelled training data remains a costly task in real world machine learning projects to meet quantity and quality requirements. Recently Large Language Models (LLMs), notably GPT-4, have shown great promises in labelling data with…

As Large Language Models (LLMs) are increasingly deployed in safety-critical domains, rigorously evaluating their robustness against adversarial jailbreaks is essential. However, current safety evaluations often overestimate robustness…

Issue localization, the process of identifying code locations that need modification to resolve software issues, is a critical yet challenging task in software development. The semantic gap between natural language issue descriptions and…

Register-Transfer Level (RTL) verification is a primary bottleneck, consuming 60-70% of development time. While Large Language Models (LLMs) show promise for RTL automation, their performance and research focus have overwhelmingly centered…

E-commerce stores enable multilingual product discovery which require accurate product title translation. Multilingual large language models (LLMs) have shown promising capacity to perform machine translation tasks, and it can also enhance…

We present a methodology for formal verification of arithmetic RTL designs that combines sequential logic equivalence checking with interactive theorem proving. An intermediate model of a Verilog module is hand-coded in Restricted…

Large Language Models (LLMs) have demonstrated impressive capabilities in code completion tasks, where they assist developers by predicting and generating new code in real-time. However, existing LLM-based code completion systems primarily…

Retrieval-augmented generation (RAG) is a promising way to improve large language models (LLMs) for generating more factual, accurate, and up-to-date content. Existing methods either optimize prompts to guide LLMs in leveraging retrieved…

Leveraging large language models for machine translation has demonstrated promising results. However, it does require the large language models to possess the capability of handling both the source and target languages in machine…

Large Language Models (LLMs) have demonstrated remarkable capabilities in modeling sequential textual data and generalizing across diverse tasks. However, adapting LLMs to effectively handle structural data, such as knowledge graphs or web…

Code translation aims to transform code between programming languages while preserving functionality, with applications in cross-platform development and software migration. Recent advances in Large Language Models (LLMs) have improved code…

Recent studies have demonstrated that test-time compute scaling effectively improves the performance of small language models (sLMs). However, prior research has mainly examined test-time compute scaling with an additional larger model as a…

The migration process between different third-party libraries is hard, complex and error-prone. Typically, during a library migration, developers need to find methods in the new library that are most adequate in replacing the old methods of…

Machine translation software has seen rapid progress in recent years due to the advancement of deep neural networks. People routinely use machine translation software in their daily lives, such as ordering food in a foreign restaurant,…

Deployed reinforcement learning agents often face safety requirements that are specified only after training, such as new hazard maps, revised risk thresholds, or behavioral alignment constraints. We study zero-update deployment-time…

LLMs have shown immense potential for code translation, yet they often struggle to ensure both syntactic correctness and semantic consistency. While preference-based learning offers a promising alignment strategy, it is hindered by…

Repository-level code completion remains a challenging task for existing code large language models (code LLMs) due to their limited understanding of repository-specific context and domain knowledge. While retrieval-augmented generation…