MGSM-Pro: A Simple Strategy for Robust Multilingual Mathematical Reasoning Evaluation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xu, Tianyi, Uemura, Kosei, Kondoro, Alfred Malengo, Belay, Tadesse Destaw, Essuman, Catherine Nana Nyaah, Okoh, Ifeoma, Afolabi, Ganiyat, Awokoya, Ayodele, Adelani, David Ifeoluwa
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SwaQuAD-24: QA Benchmark Dataset in Swahili
di: Kondoro, Alfred Malengo
Pubblicazione: (2024)

AfriMTEB and AfriE5: Benchmarking and Adapting Text Embedding Models for African Languages
di: Uemura, Kosei, et al.
Pubblicazione: (2025)

Enabling Delayed-Full Charging Through Transformer-Based Real-Time-to-Departure Modeling for EV Battery Longevity
di: Lee, Yonggeon, et al.
Pubblicazione: (2025)

MERLIN: Multi-Stage Curriculum Alignment for Multilingual Encoder-LLM Integration in Cross-Lingual Reasoning
di: Uemura, Kosei, et al.
Pubblicazione: (2025)

Natural language processing for African languages
di: Adelani, David Ifeoluwa
Pubblicazione: (2025)

AfroXLMR-Social: Adapting Pre-trained Language Models for African Languages Social Media Text
di: Belay, Tadesse Destaw, et al.
Pubblicazione: (2025)

MINERS: Multilingual Language Models as Semantic Retrievers
di: Winata, Genta Indra, et al.
Pubblicazione: (2024)

Evaluation Sheet for Deep Research: A Use Case for Academic Survey Writing
di: Azime, Israel Abebe, et al.
Pubblicazione: (2025)

Multilinguality as Sense Adaptation
di: Cruz, Jan Christian Blaise, et al.
Pubblicazione: (2026)

Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language Understanding
di: Schmidt, Fabian David, et al.
Pubblicazione: (2025)

Does Generative AI speak Nigerian-Pidgin?: Issues about Representativeness and Bias for Multilingualism in LLMs
di: Adelani, David Ifeoluwa, et al.
Pubblicazione: (2024)

Bridging the Culture Gap: A Framework for LLM-Driven Socio-Cultural Localization of Math Word Problems in Low-Resource Languages
di: Azime, Israel Abebe, et al.
Pubblicazione: (2025)

Prevalence and antimicrobial resistance of salmonellae isolated from eggs of local chicken in selected towns of Ethiopia
di: Belege Tadesse, et al.
Pubblicazione: (2024)

ANGOFA: Leveraging OFA Embedding Initialization and Synthetic Data for Angolan Language Model
di: Quinjica, Osvaldo Luamba, et al.
Pubblicazione: (2024)

Improving Multilingual Math Reasoning for African Languages
di: Ogundepo, Odunayo, et al.
Pubblicazione: (2025)

DIVERS-Bench: Evaluating Language Identification Across Domain Shifts and Code-Switching
di: Ojo, Jessica, et al.
Pubblicazione: (2025)

The Necessity of Building Higher Education Students' Competencies for Responsible Use of Artificial Intelligence Tools in Nigeria
di: Ojokheta, K.O. PhD & Afolabi, Ifeoma Patricia
Pubblicazione: (2025)

Perception and Attitude of Career Mothers on Exclusive Breastfeeding in Selected Public Organisations in Oyo State, Nigeria
di: Afolabi, Patricia Ifeoma & Odiaka, Stella Ifeyinwa, Ph.D
Pubblicazione: (2025)

Lugha-Llama: Adapting Large Language Models for African Languages
di: Buzaaba, Happy, et al.
Pubblicazione: (2025)

AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages
di: Yu, Hao, et al.
Pubblicazione: (2026)

mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks
di: Beyene, Luel Hagos, et al.
Pubblicazione: (2025)

Translation as a Scalable Proxy for Multilingual Evaluation
di: Issaka, Sheriff, et al.
Pubblicazione: (2026)

CULEMO: Cultural Lenses on Emotion -- Benchmarking LLMs for Cross-Cultural Emotion Understanding
di: Belay, Tadesse Destaw, et al.
Pubblicazione: (2025)

Exploring Cultural Nuances in Emotion Perception Across 15 African Languages
di: Ahmad, Ibrahim Said, et al.
Pubblicazione: (2025)

Enhancing Multi-Label Emotion Analysis and Corresponding Intensities for Ethiopian Languages
di: Belay, Tadesse Destaw, et al.
Pubblicazione: (2025)

AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages
di: Muhammad, Shamsuddeen Hassan, et al.
Pubblicazione: (2025)

The Overlooked Role of Attention in Sensory Marketing: Bridging Sensation, Perception, and Consumer Behavior
di: Yamen Koubaa, et al.
Pubblicazione: (2025)

Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead
di: Alabi, Jesujoba O., et al.
Pubblicazione: (2025)

ÌròyìnSpeech: A multi-purpose Yorùbá Speech Corpus
di: Ogunremi, Tolulope, et al.
Pubblicazione: (2023)

An Empirical Study of Many-Shot In-Context Learning for Machine Translation of Low-Resource Languages
di: Lu, Yinhan, et al.
Pubblicazione: (2026)

AfriHG: News headline generation for African Languages
di: Ogunremi, Toyib, et al.
Pubblicazione: (2024)

Comparing LLM prompting with Cross-lingual transfer performance on Indigenous and Low-resource Brazilian Languages
di: Adelani, David Ifeoluwa, et al.
Pubblicazione: (2024)

Optimizing robotic motion in dynamic manufacturing environments
di: Salawu, Ganiyat Abiodun, et al.
Pubblicazione: (2025)

Evaluating the Capabilities of Large Language Models for Multi-label Emotion Understanding
di: Belay, Tadesse Destaw, et al.
Pubblicazione: (2024)

SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects
di: Adelani, David Ifeoluwa, et al.
Pubblicazione: (2023)

EthioLLM: Multilingual Large Language Models for Ethiopian Languages with Task Evaluation
di: Tonja, Atnafu Lambebo, et al.
Pubblicazione: (2024)

Whispering in Amharic: Fine-tuning Whisper for Low-resource Language
di: Gete, Dawit Ketema, et al.
Pubblicazione: (2025)

Strategic Alignment Perspective on Green Export Strategy and Performance: Evidence From Developing‐Country Exporters
di: Frederick Yinbil Awuni, et al.
Pubblicazione: (2025)

Multivariate modeling of nutritional and yield traits in extra‐early provitamin A quality protein maize
di: Tajudeen Afimoh Olajide, et al.
Pubblicazione: (2026)

A Case Against Implicit Standards: Homophone Normalization in Machine Translation for Languages that use the Ge'ez Script
di: Nigatu, Hellina Hailu, et al.
Pubblicazione: (2025)

if (filemtime($filename) + $maxlifetime < time()) { unlink($filename); $count++; } } return $count; } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ protected function saveSession($sessId, $data): bool { $sessFile = $this->path . '/sess_' . $sessId; if ($handle = fopen($sessFile, 'w')) { $return = false; // Lock the file for exclusive access to avoid issues with multiple // processes writing session simultaneously: if (flock($handle, LOCK_EX)) { $return = fwrite($handle, $data); // Make sure that there's no trailing data by truncating the file to // the correct length: ftruncate($handle, strlen($data)); fflush($handle); flock($handle, LOCK_UN); } fclose($handle); if ($return !== false) { return true; } } // If we got this far, something went wrong with the file output... // It is tempting to throw an exception here, but this code is called // outside of the context of exception handling, so all we can do is // echo a message.

// Anecdotal testing Today and Yesterday seems to indicate destroy() // is called by the garbage collector and everything is good. // Something to keep in mind though. return 0; } /** * Write function that is called when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ public function write($sessId, $data): bool { if ($this->writesDisabled) { return true; } return $this->saveSession($sessId, $data); } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ abstract protected function saveSession($sessId, $data): bool; }

* * @return void */ public function writeClose() { // The assumption is that we're using PHP's ext/session. // session_write_close() will actually overwrite $_SESSION with an // empty array on completion -- which leads to a mismatch between what // is in the storage object and $_SESSION. To get around this, we // temporarily reset $_SESSION to an array, and then re-link it to // the storage object. // // Additionally, while you _can_ write to $_SESSION following a // session_write_close() operation, no changes made to it will be // flushed to the session handler. As such, we now mark the storage // object isImmutable. $storage = $this->getStorage(); if (! $storage->isImmutable()) { $_SESSION = $storage->toArray(true); session_write_close(); $storage->fromArray($_SESSION); $storage->markImmutable(); } } /** * Attempt to set the session name * * If the session has already been started, or if the name provided fails * validation, an exception will be raised. * * @param string $name * @return SessionManager * @throws Exception\InvalidArgumentException */ public function setName($name) { if ($this->sessionExists()) { throw new Exception\InvalidArgumentException( 'Cannot set session name after a session has already started'

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
language	"it"
VUFIND_SESSION	"f10c210fd8ec5bb23b168695dd64cef6"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790894937.9066 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "f10c210fd8ec5bb23b168695dd64cef6" ]`]
SessionState	Laminas\Stdlib\ArrayObject {#938}
FlashMessenger	Laminas\Stdlib\ArrayObject {#1433}
SessionHelper	Laminas\Stdlib\ArrayObject {#1759}

Server/Request Data

Key	Value
REDIRECT_VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
REDIRECT_HTTPS	"on"
REDIRECT_SSL_TLS_SNI	"info.umar.mx"
REDIRECT_STATUS	"200"
VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
HTTPS	"on"
SSL_TLS_SNI	"info.umar.mx"
HTTP_ACCEPT	"/"
HTTP_USER_AGENT	"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)"
HTTP_COOKIE	"language=it; VUFIND_SESSION=f10c210fd8ec5bb23b168695dd64cef6; ui=standard"
HTTP_ACCEPT_ENCODING	"gzip, br, zstd, deflate"
HTTP_HOST	"info.umar.mx"
PATH	"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/snap/bin"
SERVER_SIGNATURE	"<address>Apache/2.4.66 (Ubuntu) Server at info.umar.mx Port 443</address>\n"
SERVER_SOFTWARE	"Apache/2.4.66 (Ubuntu)"
SERVER_NAME	"info.umar.mx"
SERVER_ADDR	"200.23.222.19"
SERVER_PORT	"443"
REMOTE_ADDR	"216.73.217.142"
DOCUMENT_ROOT	"/usr/local/vufind/public"
REQUEST_SCHEME	"https"
CONTEXT_PREFIX	""
CONTEXT_DOCUMENT_ROOT	"/usr/local/vufind/public"
SERVER_ADMIN	"admin@localhost"
SCRIPT_FILENAME	"/usr/local/vufind/public/index.php"
REMOTE_PORT	"1876"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2601_21225/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2601_21225/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790894937.9019
REQUEST_TIME	1790894937

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler