Related papers: Reflective Translation: Improving Low-Resource Mac…

Like humans, large language models (LLMs) do not always generate the best output on their first try. Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through…

Modern Large Language Models (LLMs) have shown rapid improvements in reasoning capabilities, driven largely by reinforcement learning (RL) with verifiable rewards. Here, we ask whether these LLMs can self-improve without the need for…

In this study, we investigated the effects of self-reflection in large language models (LLMs) on problem-solving performance. We instructed nine popular LLMs to answer a series of multiple-choice questions to provide a performance baseline.…

Reliable evaluation benchmarks designed for replicability and comprehensiveness have driven progress in machine learning. Due to the lack of a multilingual benchmark, however, vision-and-language research has mostly focused on English…

Self-reflection on learning experiences constitutes a fundamental cognitive process, essential for the consolidation of knowledge and the enhancement of learning efficacy. However, traditional methods to facilitate reflection often face…

Trained on various human-authored corpora, Large Language Models (LLMs) have demonstrated a certain capability of reflecting specific human-like traits (e.g., personality or values) by prompting, benefiting applications like personalized…

Language pairs with limited amounts of parallel data, also known as low-resource languages, remain a challenge for neural machine translation. While the Transformer model has achieved significant improvements for many language pairs and has…

The reliability of multilingual Large Language Model (LLM) evaluation is currently compromised by the inconsistent quality of translated benchmarks. Existing resources often suffer from semantic drift and context loss, which can lead to…

As language models (LMs) demonstrate their capabilities in various fields, their application to tasks requiring multi-round interactions has become increasingly popular. These tasks usually have complex dynamics, so supervised fine-tuning…

Language models are the foundation of current neural network-based models for natural language understanding and generation. However, research on the intrinsic performance of language models on African languages has been extremely limited,…

Large Language Models (LLMs) are powerful models for generation tasks, but they may not generate good quality outputs in their first attempt. Apart from model fine-tuning, existing approaches to improve prediction accuracy and quality…

The promise of Large Language Models (LLMs) in Natural Language Processing has often been overshadowed by their limited performance in low-resource languages such as Bangla. To address this, our paper presents a pioneering approach that…

Large language models (LLMs) have demonstrated impressive performance on several tasks and are increasingly deployed in real-world applications. However, especially in high-stakes settings, it becomes vital to know when the output of an LLM…

This paper reports the Machine Translation (MT) systems submitted by the IIITT team for the English->Marathi and English->Irish language pairs LoResMT 2021 shared task. The task focuses on getting exceptional translations for rather…

In this work, we investigate methods for the challenging task of translating between low-resource language pairs that exhibit some level of similarity. In particular, we consider the utility of transfer learning for translating between…

Evaluating conversational systems in multi-turn settings remains a fundamental challenge. Conventional pipelines typically rely on manually defined rubrics and fixed conversational context$-$a static approach that limits coverage and fails…

How do we perform efficient inference while retaining high translation quality? Existing neural machine translation models, such as Transformer, achieve high performance, but they decode words one by one, which is inefficient. Recent…

We enhance auto-regressive language models by conditioning on document chunks retrieved from a large corpus, based on local similarity with preceding tokens. With a $2$ trillion token database, our Retrieval-Enhanced Transformer (RETRO)…

Unlike classical lexical overlap metrics such as BLEU, most current evaluation metrics for machine translation (for example, COMET or BERTScore) are based on black-box large language models. They often achieve strong correlations with human…

Machine translation systems for high resource languages perform exceptionally well and produce high quality translations. Unfortunately, the vast majority of languages are not considered high resource and lack the quantity of parallel…