Austria

Building high-quality large language models (LLMs) for enterprise Arabic applications remains challenging due to the limited availability of digitized Arabic data. In this work, we present a data synthesis and refinement strategy to help address this problem, namely, by leveraging synthetic data generation and human-in-the-loop annotation to expand our Arabic training corpus. We further present our iterative post training recipe that is essential to achieving state-of-the-art performance in aligning the model with human preferences, a critical aspect to enterprise use cases. The culmination of this effort is the release of a small, 7B, open-weight model that outperforms similarly sized peers in head-to-head comparisons and on Arabic-focused benchmarks covering cultural knowledge, instruction following, RAG, and contextual faithfulness.

ACL 2025

Command R7B Arabic: a small, enterprise-focused, multilingual, and culturally aware Arabic LLM

## Welcome to EMNLP 2022!
I am delighted to welcome you to EMNLP 2022! I believe this conference has been complicated beyond any precedent. Over the past year, it’s been thrilling to see the organization team approach each new puzzle with creativity and enthusiasm. We hope that those participating in Abu Dhabi as well as those joining remotely will leave the conference feeling newly inspired by the program and newly connected to our ever-growing community. Following EMNLP 2021 and major NLP conferences since, EMNLP 2022 is “hybrid,” serving both virtual and in-person participants.

Our key innovations for EMNLP 2022 include:

* EMNLP 2022 is “hybrid” in a second sense, as well: we allowed both direct and rolling review paper submissions, building on the pilot experiment of EMNLP 2021, which considered a small number of ARR submissions. 
* Familiar from NAACL but new to EMNLP, we’ve added an industry track.
* During the conference, “portals” will link virtual poster sessions to in-person conference participants during poster sessions each day.
* The first ACL-family conference in the United Arab Emirates.

 *Message from Noah A. Smith, University of Washington and Allen Institute for AI, Seattle, Washington, USA* 
***EMNLP 2022 General Chair***
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/9eec7d4a287ee18c278b08229290aa83.png)](https://drive.google.com/file/d/1OlPv6QBeo62VVTughj2jkiLeyHd1WnUt/view)
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/a3db7a768409f05192210d98601edb25.png)](https://emnlp2022.rocket.chat/)

To access this site you need to register. Please register [here](https://2022.emnlp.org/registration/).

Register here

EMNLP 2022

Welcome!
EMNLP 2022 will take place in Abu Dhabi from December 7th to December 11th, 2022. And it will be held in hybrid mode, both online and offline.

workshop paper

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Pretrained language models (PLMs) for African languages are continually improving, but the reasons behind these advances remain unclear. This paper presents the first systematic investigation into how knowledge about African languages is encoded in PLMs. We train layer-wise probes for six typologically diverse African languages to ana\-lyse how linguistic features are distributed. We also design control tasks, a way to interpret probe performance, for the MasakhaPOS dataset. We find PLMs adapted for African languages to encode more linguistic information about target languages than massively multilingual PLMs. Our results reaffirm previous findings that token-level syntactic information concentrates in middle-to-last layers, while sentence-level semantic information is distributed across all layers. Through control tasks and probing baselines, we confirm that performance reflects the internal know\-ledge of PLMs rather than probe memorisation. Our study applies established interpretability techniques to African-language PLMs. In doing so, we highlight the internal mechanisms underlying the success of strategies like active learning and multilingual adaptation.

Designing and Contextualising Probes for African Languages


The integration of Artificial Intelligence (Al) in agriculture has significantly impacted decision making processes for farmers, particularly in regions such as Kenya, where access to accurate and timely advisory services is crucial. This paper explores the deployment of Retrieval Augmented Generation (RAG) agents powered by fine-tuned quantized language models to enhance Al-driven agricultural advisory services. By optimizing model efficiency through quantization and fine-tuning, our aim is to deliver a specialized language model in agriculture and to ensure real-time, cost-effective and contextually relevant recommendations for smallholder farmers. Our approach takes advantage of localized agricultural datasets and natural language processing techniques to improve the accessibility and accuracy of advisory responses in local Kenyan languages. We show that the proposed model has the potential to improve information delivery and automation of complex and monotonous tasks, making it a viable solution to sustainable agricultural intelligence in Kenya and beyond.

Enhancing AI-Driven Farming Advisory in Kenya with Efficient RAG Agents via Quantized Fine-Tuned Language Models

Generative AI models are primarily accessed through chat interfaces, where user queries often contain typographical errors. While these models perform well in English, their robustness to noisy inputs in low-resource languages like Yorùbá remains underexplored. This work investigates a Yorùbá question-answering (QA) task by introducing synthetic typographical noise into clean inputs. We design a probabilistic noise injection strategy that simulates realistic human typos. In our experiments, each character in a clean sentence is independently altered, with noise levels ranging from 10% to 40%. We evaluate performance across three strong multilingual models using two complementary metrics: (1) a multilingual BERTScore to assess semantic similarity between outputs on clean and noisy inputs, and (2) an LLM-as-judge approach, where the best Yorùbá-capable model rates fluency, comprehension, and accuracy on a 1–5 scale. Results show that while English QA performance degrades gradually, Yorùbá QA suffers a sharper decline. At 40% noise, GPT-4o experiences over a 50% drop in comprehension ability, with similar declines for Gemini 2.0 Flash and Claude 3.7 Sonnet. We conclude with recommendations for noise-aware training and dedicated noisy Yorùbá benchmarks to enhance LLM robustness in low-resource settings.

Evaluating Robustness of LLMs to Typographical Noise in Yorùbá QA

The performance of Automatic Speech Recognition (ASR) depends on the availability of transcribed speech datasets—often scarce or non-existent for many of the world’s languages. This study investigates alternative strategies to bridge the data gap using zero-shot cross-lingual transfer, leveraging transliteration as a method to utilize data from other languages. We experiment with transliteration from various source languages and demonstrate ASR performance in a low-resourced language, Amharic. We find that source data that align with the character distribution of the test data achieves the best performance, regardless of language family. We also experiment with fine-tuning with minimal transcribed data in the target language. Our findings demonstrate that transliteration, particularly when combined with a strategic choice of source languages, is a viable approach for improving ASR in zero-shot and low-resourced settings.

Exploring Transliteration-Based Zero-Shot Transfer for Amharic ASR

Automatic Speech Recognition (ASR) technologies have seen significant advancements, yet many widely spoken languages remain underrepresented. This paper explores the fine-tuning of OpenAI's Whisper Tiny model (39M parameters) for Swahili, a lingua franca for over 100 million people across East Africa. Using a dataset of 5,520 Swahili audio samples, we analyze the model's performance, error patterns, and limitations after fine-tuning. Our results demonstrate the potential of fine-tuning for improving transcription accuracy, while also highlighting persistent challenges such as phonetic misinterpretations, named entity recognition failures, and difficulties with morphologically complex words. We provide recommendations for improving Swahili ASR, including scaling to larger model variants, architectural adaptations for agglutinative languages, and data enhancement strategies. This work contributes to the growing body of research on adapting pre-trained multilingual ASR systems to low-resource languages, emphasizing the need for approaches that account for the unique linguistic features of Bantu languages.

Fine-tuning Whisper Tiny for Swahili ASR: Challenges and Recommendations for Low-Resource Speech Recognition

Neural Machine Translation (NMT) systems face significant challenges when working with low-resource languages, particularly in domain adaptation tasks. These difficulties arise due to limited training data and suboptimal model generalization, As a result, selecting an optimal model for translation is crucial for achieving strong performance on in-domain data, particularly in scenarios where fine-tuning is not feasible or practical. In this paper, we investigate strategies for selecting the most suitable NMT model for a given domain using bandit-based algorithms, including Upper Confidence Bound, Linear UCB, Neural Linear Bandit, and Thompson Sampling. Our method effectively addresses the resource constraints by facilitating optimal model selection with high confidence. We evaluate the approach across three African languages and domains, demonstrating its robustness and effectiveness in both scenarios where target data is available and where it is absent.

In-Domain African Languages Translation Using LLMs and Multi-armed Bandits

Despite the increasing prevalence of smishing attacks targeting Mobile Money Transfer systems, there is a notable lack of publicly available SMS phishing datasets in this domain. This study seeks to address this gap by creating a specialized dataset designed to detect smishing attacks aimed at Mobile Money Transfer users. The data set consists of crowd-sourced text messages from Mozambican mobile users, meticulously annotated into two categories: legitimate messages (ham) and fraudulent smishing attempts (spam). The messages are written in Portuguese, often incorporating microtext styles and linguistic nuances unique to the Mozambican context. We also investigate the effectiveness of LLMs in detecting smishing. Using in-context learning approaches, we evaluate the models' ability to identify smishing attempts without requiring extensive task-specific training. The data set is released under an open license at the following link: huggingface-Anonymous.

MOZ-Smishing: A Benchmark Dataset for Detecting Mobile Money Frauds

Despite advances in multilingual natural language processing (NLP) and machine translation (MT), African languages remain underrepresented due to data scarcity, tokenisation inefficiencies, and bias in AI models. Large-scale systems such as Meta AI’s No Language Left Behind (NLLB) and the Flores-200 benchmark have improved low-resource language support, yet critical gaps persist, particularly in healthcare, where accuracy and trust are essential. This study systematically reviews over 30 peer-reviewed papers, technical reports, and datasets to assess the effectiveness of existing multilingual NLP models, specifically Masakhane-MT, Masakhane-NER, and AfromT, in African healthcare contexts. The analysis focuses on four languages with available evaluation data: Swahili, Yoruba, Hausa, and Igbo. Findings show that while AI tools such as medical chatbots and disease surveillance systems demonstrate promise, current models face persistent challenges including domain adaptation failures, cultural and linguistic bias, and limited explainability. Use cases like Ubenwa’s infant cry analysis tool and multilingual health translation systems illustrate both potential and risk, especially where translation errors or opacity may impact clinical decisions. The paper highlights the need for ethically grounded, domain-specific NLP approaches that reflect Africa’s linguistic diversity. We recommend strategies to address dataset imbalance, reduce bias, and improve explainability, while also calling for increased computational infrastructure and local AI governance. These steps are critical to making AI-driven healthcare solutions equitable, transparent, and effective for Africa’s multilingual populations.

Multilingual NLP for African Healthcare Bias, Translation, and Explainability Challenges

Morphological parsing is the task of decomposing words into morphemes, the smallest units of meaning in a language, and labelling their grammatical roles. It is a particularly challenging task for agglutinative languages, such as the Nguni languages of South Africa, which construct words by concatenating multiple morphemes. A morphological parsing system can be framed as a pipeline with two separate components, a segmenter followed by a tagger. This paper investigates the use of neural methods to build morphological taggers for the four Nguni languages. We compare two classes of approaches: training neural sequence labellers (LSTMs and neural CRFs) from scratch and finetuning pretrained language models. We compare performance across these two categories, as well as to a traditional rule-based morphological parser. Neural taggers comfortably outperform the rule-based baseline and models trained from scratch tend to outperform pretrained models. We also compare parsing results across different upstream segmenters and with varying linguistic input features. Our findings confirm the viability of employing neural taggers based on pre-existing morphological segmenters for the Nguni languages.

Neural Morphological Tagging for Nguni Languages

This research article examines the effectiveness of various pretraining strategies for developing machine translation models tailored to low-resource languages. Although this work considers several low-resource languages, including Afrikaans, Swahili, and Zulu, the translation model is specifically developed for Lingala, an under-resourced African language, building upon the pretraining approach introduced by Reid and Artetxe (2021), originally designed for high-resource languages. Through a series of comprehensive experiments, we explore different pretraining methodologies, including the integration of multiple languages and the use of both monolingual and parallel data during the pretraining phase. Our findings indicate that pretraining on multiple languages and leveraging both monolingual and parallel data significantly enhance translation quality. This study offers valuable insights into effective pretraining strategies for low-resource machine translation, helping to bridge the performance gap between high-resource and low-resource languages. The results contribute to the broader goal of developing more inclusive and accurate NLP models for marginalized communities and underrepresented populations. The code and datasets used in this study are publicly available to facilitate further research and ensure reproducibility, with the exception of certain data that may no longer be accessible due to changes in public availability.

Downloads

Next from ACL 2025

Designing and Contextualising Probes for African Languages

Similar lecture

Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Processing