Skip to content
GCC AI Research

Search

Results for "GPT-3.5"

Ara-HOPE: Human-Centric Post-Editing Evaluation for Dialectal Arabic to Modern Standard Arabic Translation

arXiv ·

The paper introduces Ara-HOPE, a human-centric post-editing evaluation framework for Dialectal Arabic to Modern Standard Arabic (DA-MSA) translation. Ara-HOPE includes a five-category error taxonomy and a decision-tree annotation protocol designed to address the challenges of dialect-specific MT errors. Evaluation of Jais, GPT-3.5, and NLLB-200 shows dialect-specific terminology and semantic preservation remain key challenges. Why it matters: The new framework and public dataset will help improve the evaluation and development of dialect-aware MT systems for Arabic.

PG-Video-LLaVA: Pixel Grounding Large Video-Language Models

arXiv ·

MBZUAI researchers introduce PG-Video-LLaVA, a large multimodal model with pixel-level grounding capabilities for videos, integrating audio cues for enhanced understanding. The model uses an off-the-shelf tracker and grounding module to localize objects in videos based on user prompts. PG-Video-LLaVA is evaluated on video question-answering and grounding benchmarks, using Vicuna instead of GPT-3.5 for reproducibility.

Prediction of Arabic Legal Rulings using Large Language Models

arXiv ·

This paper introduces a predictive analysis of Arabic court decisions, utilizing 10,813 real commercial court cases. The study evaluates LLaMA-7b, JAIS-13b, and GPT3.5-turbo models under zero-shot, one-shot, and fine-tuned training paradigms, also experimenting with summarization and translation. GPT-3.5 models significantly outperformed others, exceeding JAIS model performance by 50%, while also demonstrating the unreliability of most automated metrics. Why it matters: This research bridges computational linguistics and Arabic legal analytics, offering insights for enhancing judicial processes and legal strategies in the Arabic-speaking world.

LAraBench: Benchmarking Arabic AI with Large Language Models

arXiv ·

LAraBench introduces a benchmark for Arabic NLP and speech processing, evaluating LLMs like GPT-3.5-turbo, GPT-4, BLOOMZ, Jais-13b-chat, Whisper, and USM. The benchmark covers 33 tasks across 61 datasets, using zero-shot and few-shot learning techniques. Results show that SOTA models generally outperform LLMs in zero-shot settings, though larger LLMs with few-shot learning reduce the gap. Why it matters: This benchmark helps assess and improve the performance of LLMs on Arabic language tasks, highlighting areas where specialized models still excel.

Taqyim: Evaluating Arabic NLP Tasks Using ChatGPT Models

arXiv ·

This paper evaluates the performance of GPT-3.5 and GPT-4 on seven Arabic NLP tasks including sentiment analysis, translation, and diacritization. GPT-4 outperforms GPT-3.5 on most tasks. The study provides an analysis of sentiment analysis and introduces a Python interface, Taqyim, for evaluating Arabic NLP tasks. Why it matters: The evaluation of LLMs on Arabic NLP tasks helps to identify strengths and weaknesses, guiding future research and development efforts in the field.

Polyglot programs: NLP for Arabic and the globe’s diverse dialects

MBZUAI ·

MBZUAI researchers presented studies at EMNLP and ArabicNLP conferences on improving NLP for diverse languages, especially Arabic. One study evaluated ChatGPT and GPT-4's performance across Arabic dialects, finding limitations compared to English. GPT-4 showed better performance than GPT-3.5 in Arabic. Why it matters: This research highlights the need for NLP models to better support the linguistic diversity of Arabic and other languages to avoid widening existing technological gaps.