# SandboxAQ's submission to MRL 2024 Shared Task on Multi-lingual Multi-task Information Retrieval

Source: [SandboxAQ's submission to MRL 2024 Shared Task on Multi-lingual Multi-task Information Retrieval](<https://www.sota2.com/research/paper/68fa756b1e209131cea67c5e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:41:59.710Z

Authors: Isidora Chara Tourni, Sayontan Ghosh, Brenda Miao, Constantijn van der Poel

Published: 2024-10-28T20:15:45.000Z

## Abstract

This paper explores the problems of Question Answering (QA) and Named Entity Recognition (NER) in five diverse languages. We tested five Large Language Models with various prompting methods, including zero-shot, chain-of-thought reasoning, and translation techniques. Our results show that while some models consistently outperform others, their effectiveness varies significantly across tasks and languages. We saw that advanced prompting techniques generally improved QA performance but had mixed results for NER; and we observed that language difficulty patterns differed between tasks. Our findings highlight the need for task-specific approaches in multilingual NLP and suggest that current models may develop different linguistic competencies for different tasks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2410.21501>)

[PDF](<https://arxiv.org/pdf/2410.21501.pdf>)
