32 citations · 170 across the 33 of their papers we have counts for
36 papers
SkillGym: Training Skill-Use Agents with Automatic Verifiable Environment Generation
Renxi Wang, Mingshan Hee, Fajri Koto +2
Skills equip LLM agents with professional knowledge and guidance to complete long-horizon and complex tasks. Although skills have been widely adopted in recent agent paradigms and…
Training and Benchmarking Code Generation for Physics-Inspired Animations
Yanan Wang, Renxi Wang, Yongxin Wang +5
Large language models (LLMs) have been widely studied in areas such as mathematical reasoning, complex coding, and scientific problem solving. However, their ability to generate ex…
AgentFly: Scaling Agentic Reinforcement Learning with Unified Resource System
Renxi Wang, Rifo Ahmad Genadi, Bilal El Bouardi +6
Methods to build LLM agents have evolved from prompt engineering and supervised finetuning to agentic reinforcement learning (agentic RL). However, agentic RL remains bottlenecked…
Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs
Longxu Dou, Qian Liu, Fan Zhou +38
Sailor2 is a family of cutting-edge multilingual language models for South-East Asian (SEA) languages, available in 1B, 8B, and 20B sizes to suit diverse applications. Building on…
KazMMLU: Evaluating Language Models on Kazakh, Russian, and Regional Knowledge of Kazakhstan
Mukhammed Togmanov, Nurdaulet Mukhituly, Diana Turmakhan +11
Despite having a population of twenty million, Kazakhstan's culture and language remain underrepresented in the field of natural language processing. Although large language models…
LLM360 K2: Building a 65B 360-Open-Source Large Language Model from Scratch
Zhengzhong Liu, Bowen Tan, Hongyi Wang +22
We detail the training of the LLM360 K2-65B model, scaling up our 360-degree OPEN SOURCE approach to the largest and most powerful models under project LLM360. While open-source LL…
Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability
Haonan Li, Xudong Han, Zenan Zhai +32
To address this gap, we introduce Libra-Leaderboard, a comprehensive framework designed to rank LLMs through a balanced evaluation of performance and safety. Combining a dynamic le…
INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge
Angelika Romanou, Negar Foroutan, Anna Sotnikova +56
The performance differential of large language models (LLM) between languages hinders their effective deployment in many regions, inhibiting the potential economic and societal val…
Cracking the Code: Multi-domain LLM Evaluation on Real-World Professional Exams in Indonesia
Fajri Koto
While knowledge evaluation in large language models has predominantly focused on academic subjects like math and physics, these assessments often fail to capture the practical dema…
SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages
Holy Lovenia, Rahmad Mahendra, Salsabil Maulana Akbar +58
Southeast Asia (SEA) is a region rich in linguistic diversity and cultural variety, with over 1,300 indigenous languages and a population of 671 million people. However, prevailing…
CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark
David Romero, Chenyang Lyu, Haryo Akbarianto Wibowo +73
Visual Question Answering (VQA) is an important task in multimodal AI, and it is often used to test the ability of vision-language models to understand and reason on knowledge pres…
Cendol: Open Instruction-tuned Generative Large Language Models for Indonesian Languages
Samuel Cahyawijaya, Holy Lovenia, Fajri Koto +13
Large language models (LLMs) show remarkable human-like capability in various domains and languages. However, a notable quality gap arises in low-resource languages, e.g., Indonesi…
IndoCulture: Exploring Geographically-Influenced Cultural Commonsense Reasoning Across Eleven Indonesian Provinces
Fajri Koto, Rahmad Mahendra, Nurul Aisyah +1
Although commonsense reasoning is greatly shaped by cultural and geographical factors, previous studies have predominantly centered on cultures grounded in the English language, po…
BEnQA: A Question Answering and Reasoning Benchmark for Bengali and English
Sheikh Shafayat, H M Quamran Hasan, Minhajur Rahman Chowdhury Mahim +3
In this study, we introduce BEnQA, a dataset comprising parallel Bengali and English exam questions for middle and high school levels in Bangladesh. Our dataset consists of approxi…
Zero-shot Sentiment Analysis in Low-Resource Languages Using a Multilingual Sentiment Lexicon
Fajri Koto, Tilman Beck, Zeerak Talat +2
Improving multilingual language models capabilities in low-resource languages is generally difficult due to the scarcity of large-scale data in those languages. In this paper, we r…
ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic
Fajri Koto, Haonan Li, Sara Shatnawi +10
The focus of language model evaluation has transitioned towards reasoning and knowledge-intensive tasks, driven by advancements in pretraining large models. While state-of-the-art…
LLM360: Towards Fully Transparent Open-Source LLMs
Zhengzhong Liu, Aurick Qiao, Willie Neiswanger +25
The recent surge in open-source Large Language Models (LLMs), such as LLaMA, Falcon, and Mistral, provides diverse options for AI practitioners and researchers. However, most LLMs…
Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU
Fajri Koto, Nurul Aisyah, Haonan Li +1
Although large language models (LLMs) are often pre-trained on large-scale multilingual texts, their reasoning abilities and real-world knowledge are mainly evaluated based on Engl…
Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models
Neha Sengupta, Sunil Kumar Sahu, Bokang Jia +29
We introduce Jais and Jais-chat, new state-of-the-art Arabic-centric foundation and instruction-tuned open generative large language models (LLMs). The models are based on the GPT-…
NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages
Samuel Cahyawijaya, Holy Lovenia, Fajri Koto +15
Democratizing access to natural language processing (NLP) technology is crucial, especially for underrepresented and extremely low-resource languages. Previous research has focused…
Are Multilingual LLMs Culturally-Diverse Reasoners? An Investigation into Multicultural Proverbs and Sayings
Chen Cecilia Liu, Fajri Koto, Timothy Baldwin +1
Large language models (LLMs) are highly adept at question answering and reasoning tasks, but when reasoning in a situational context, human expectations vary depending on the relev…
CMMLU: Measuring massive multitask language understanding in Chinese
Haonan Li, Yixuan Zhang, Fajri Koto +5
As the capabilities of large language models (LLMs) continue to advance, evaluating their performance becomes increasingly crucial and challenging. This paper aims to bridge this g…
Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptation
Haonan Li, Fajri Koto, Minghao Wu +2
Instruction tuning has shown great promise in improving the performance of large language models. However, research on multilingual instruction tuning has been limited due to the s…
NusaCrowd: Open Source Initiative for Indonesian NLP Resources
Samuel Cahyawijaya, Holy Lovenia, Alham Fikri Aji +44
We present NusaCrowd, a collaborative initiative to collect and unify existing resources for Indonesian languages, including opening access to previously non-public resources. Thro…