Related papers: CodePivot: Bootstrapping Multilingual Transpilatio…

Recent advances in mathematical problem-solving with language models (LMs) integrate chain-of-thought (CoT) reasoning and code execution to harness their complementary strengths. However, existing hybrid frameworks exhibit a critical…

This paper introduces a novel code-to-code search technique that enhances the performance of Large Language Models (LLMs) by including both static and dynamic features as well as utilizing both similar and dissimilar examples during…

The advent of large language models (LLMs) has significantly advanced artificial intelligence (AI) in software engineering (SE), with source code embeddings playing a crucial role in tasks such as source code clone detection and source code…

Translation-based prompting is widely used in multilingual LLMs, yet its effectiveness varies across languages and tasks. We evaluate prompting strategies across ten languages of different resource levels and four benchmarks. Our analysis…

Parallel corpora are indispensable for training neural machine translation (NMT) models, and parallel corpora for most language pairs do not exist or are scarce. In such cases, pivot language NMT can be helpful where a pivot language is…

Large Language Models (LLMs) are increasingly being applied across various domains, including code-related tasks such as code translation. Previous studies have explored using LLMs for translating code between different programming…

Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries, which are expensive and impractical for low-resource languages. To disengage from these dependencies, researchers have explored training…

In recent years, Large Language Models (LLMs) have made significant strides towards Artificial General Intelligence. However, training these models from scratch requires substantial computational resources and vast amounts of text data. In…

Large Language Models (LLMs) with vast context windows offer new avenues for in-context learning (ICL), where providing many examples ("many-shot" prompting) is often assumed to enhance performance. We investigate this assumption for the…

Non-prehensile manipulation is challenging due to complex contact interactions between objects, the environment, and robots. Model-based approaches can efficiently generate complex trajectories of robots and objects under contact…

Vision-and-Language Pre-training (VLP) has improved performance on various joint vision-and-language downstream tasks. Current approaches to VLP heavily rely on image feature extraction processes, most of which involve region supervision…

We explore efficient strategies to fine-tune decoder-only Large Language Models (LLMs) for downstream text classification under resource constraints. Two approaches are investigated: (1) attaching a classification head to a pretrained…

Low-resource machine translation (MT) has gained increasing attention as parallel data from low-resource language communities is collected, but many approaches for improving low-resource MT remain underexplored. We investigate a…

In this paper, we introduce CodingTeachLLM, a large language model (LLM) designed for coding teaching. Specially, we aim to enhance the coding ability of LLM and lead it to better teaching mode in education context. Thus, we propose an…

Cutting-edge LLMs have emerged as powerful tools for multilingual communication and understanding. However, LLMs perform worse in Common Sense Reasoning (CSR) tasks when prompted in low-resource languages (LRLs) like Hindi or Swahili…

In the era of Large Language Models (LLMs), alignment has emerged as a fundamental yet challenging problem in the pursuit of more reliable, controllable, and capable machine intelligence. The recent success of reasoning models and…

Multilingual transformer language models have recently attracted much attention from researchers and are used in cross-lingual transfer learning for many NLP tasks such as text classification and named entity recognition. However, similar…

Code translation, the automatic conversion of programs between languages, is a growing use case for Large Language Models (LLMs). However, direct one-shot translation often fails to preserve program intent, leading to errors in control…

We present a framework for optimizing prompts in vision-language models to elicit multimodal reasoning without model retraining. Using an evolutionary algorithm to guide prompt updates downstream of visual tasks, our approach improves upon…

Prompting has shown impressive success in enabling large pretrained language models (LMs) to perform diverse NLP tasks, especially when only few downstream data are available. Automatically finding the optimal prompt for each task, however,…