India

Recently, Large Language Models (LLMs) have dominated much of the artificial intelligence scene with their ability to process and generate natural languages. However, the majority of LLM research and development remains English-centric, leaving low-resource languages such as those in the Southeast Asian (SEA) region under-represented. To address this representation gap, we introduce Llama-SEA-LION-v3-8B-IT and Gemma-SEA-LION-v3-9B-IT, two cutting-edge multilingual LLMs designed for SEA languages. The SEA-LION family of LLMs supports 11 SEA languages, namely English, Chinese, Indonesian, Vietnamese, Malay, Thai, Burmese, Lao, Filipino, Tamil, and Khmer. Our work leverages large-scale multilingual continued pre-training with a comprehensive post-training regime involving multiple stages of instruction fine-tuning, alignment, and model merging. Evaluation results on multilingual benchmarks indicate that our models achieve state-of-the-art performance across LLMs supporting SEA languages. We open-source the models to benefit the wider SEA community.

IJCNLP-AACL 2025

SEA-LION: Southeast Asian Languages in One Network

multilingual benchmarking

model alignment

instruction fine-tuning

open-source language models

continued pre-training

southeast asian languages

low-resource languages

multilingual nlp

large language models

cross-lingual transfer

### 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**. 

ACL 2025

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

technical paper

### Welcome to IJCNLP-AACL 2025! 
 It is a great honor to host this joint conference in Mumbai, India, from December 20 to 24, 2025. The joint conferences of IJCNLP and AACL are organized with alternating leadership in the Asia-Pacific region. The event is run by the Asian Federation of Natural Language Processing (AFNLP) in odd years, and by AACL in even years, while it is organized solely by ACL when the annual ACL meeting is held in the region. This year, the conference is primarily organized by AFNLP. 
*Kentaro Inui
MBZUAI, UAE
General Chair, IJCNLP-AACL 2025* 
Read full message and download the Conference Handbook [**here**](https://drive.google.com/file/d/1UTwxkAqSqI-GAoJC3wE1zZt5VP1Y8GX0/view?usp=sharing).

The 14th IJCNLP & 4th AACL will be held in Mumbai, India from December 20th to December 24th, 2025.

Subword segmentation is typically applied in preprocessing and stays fixed during training. Alternatively, it can be learned during training to optimise the training objective. In this paper we study the learning dynamics of subword segmentation: if a language model can dynamically optimise tokenisation, how do its subwords evolve during pretraining and finetuning? To explore this, we extend the subword segmental language model (SSLM), a framework for learning subwords during training, to support pretraining and finetuning. We train models for three typologically diverse languages to study learning dynamics across the morphological spectrum: Isi-Xhosa is conjunctive (long word forms composed of many morphemes), Setswana is disjunctive (morphemes written as separate words), and English represents a typological middle ground. We analyse subword dynamics from a linguistic perspective, tracking morphology, productivity, and fertility. We identify four stages of subword learning, with the morphologically complex isi-Xhosa exhibiting greater instability. During finetuning, subword boundaries shift to become finer-grained. Lastly, we show that learnable subwords offers a promising approach to improve text generation and cross-lingual transfer for low-resource, morphologically complex languages.

The Learning Dynamics of Subword Segmentation for Morphologically Diverse Languages

We investigate cross-lingual fine-tuning for idiomatic expression identification, addressing the limited availability of annotated data in many languages. We evaluate encoder and generative decoder models to examine their ability to generalize idiom identification across languages. Additionally, we conduct an explainability study using linear probing and LogitLens to analyze how idiomatic meaning is represented across model layers. Results show consistent cross-lingual transfer, with English emerging as a strong source language. All code and models are released to support future research.

Not Just a Piece of Cake: Cross-Lingual Fine-Tuning for Idiom Identification

Large Language Models (LLMs) have shown remarkable capabilities, but their development has primarily focused on English and other high-resource languages, leaving many languages underserved. We present our latest Hindi-English bi-lingual LLM with ~3% average improvement in benchmark scores over both languages, outperforming models twice its size. Using a curated dataset composed of English and Hindi instruction data of 485K samples, we instruction tuned models such as Qwen-2.5-14B-Instruct and Phi-4 to improve performance over both English and Hindi. Our experiments encompassing seven different LLMs of varying parameter sizes and over 140 training attempts with varying English-Hindi training data ratios demonstrated that it is possible to significantly improve multilingual performance without compromising native performance. Further, our approach avoids resource-intensive techniques like vocabulary expansion or architectural modifications, thus keeping the model size small. Our results indicate that modest fine-tuning with culturally and locally informed data can bridge performance gaps without incurring significant computational overhead. We release our training code, datasets, and models under mit and apache licenses to aid further research towards under-represented and low-resource languages.

Improving Multilingual Capabilities with Cultural and Local Knowledge in Large Language Models While Enhancing Native Performance

Recent works on structured text translation remain limited to the sentence level, as they struggle to effectively handle the complex document-level XML or HTML structures. To address this, we propose Format Reinforcement Learning (FormatRL), which employs Group Relative Policy Optimization on top of a supervised fine-tuning model to directly optimize novel structure-aware rewards: 1) TreeSim, which measures structural similarity between predicted and reference XML trees and 2) Node-chrF, which measures translation quality at the level of XML nodes. Additionally, we propose StrucAUC, a fine-grained metric distinguishing between minor errors and major structural failures. Experiments on the SAP software-documentation benchmark demonstrate improvements across six metrics and an analysis further shows how different reward functions contribute to improvements in both structural and translation quality.

Structured Document Translation via Format Reinforcement Learning

In related work section of a scientific paper, authors collect relevant citations and structure them into coherent paragraphs that follow a logical order. Previous studies have addressed citation recommendation and related work section generation in settings where both the citations and their order are provided in advance. However, they have not adequately addressed the optimal ordering of these citations, which is a critical step for achieving fully automated related work section generation. In this study, we propose a new task, citation arrangement, which focuses on determining the optimal order of cited papers to enable fully automated related work section generation. Our approach decomposes citation arrangement into three tasks: citation clustering, paragraph ordering, and citation ordering within a paragraph. For each task, we propose a method that uses a large language model (LLM) in combination with a graph-based technique to comprehensively consider the context of each paper and the relationships among all cited papers. The experimental results show that our method is more effective than methods that generate outputs for each task using only an LLM.

Optimizing the Arrangement of Citations in Related Work Section

Multi-agent systems with smaller language models (SLMs) present a viable alternative to single agent systems powered by large language models (LLMs) for addressing complex problems. In this work, we study how these alternatives compare in terms of both effectiveness and efficiency. To study this trade-off, we instantiate single and multi-agent systems for the complex problems in the AppWorld environment using different sized language models.

We find that difficulties with long-trajectory learning in smaller language models (SLMs) limit their performance. Even when trained for specialized roles, SLMs fail to learn all subtasks effectively. To address this issue, we introduce a simple progressive sub-task training strategy, which introduces new sub-tasks progressively in each training epoch. We find that this novel strategy, analogous to instance level curriculum learning, consistently improves the effectiveness of multi-agents at all configurations. Our Pareto analysis shows that fine-tuned multi-agent systems yield better effectiveness-efficiency trade-offs. Additional ablations and analyses shows the importance of our progressive training strategy and its ability to reduce subtask error rates.

ProST: Progressive Sub-task Training for Pareto-Optimal Multi-agent Systems Using Small Language Models

Speech-to-Speech Translation (S2ST) converts speech from one language to speech in a different language. While various S2ST models exist, none adequately support Indic languages, primarily due to the lack of a suitable dataset. We fill this gap by introducing Indic-S2ST, a multilingual and multimodal many-to-many S2ST data of approximately 600 hours in 14 Indic languages, including Indian-accented English. To the best of our knowledge, this is the largest data for the S2ST task with parallel speech and text in 14 scheduled Indic languages. Our data also supports Automatic Speech Recognition (ASR), Text-to-Speech (TTS) synthesis, Speech-to-Text translation (ST), and Machine Translation (MT) due to parallel speech and text alignment. Thus, our data may be useful to train a model like
Meta’s SeamlessM4T for Indic languages. We also propose Indic-S2UT, a discrete unit-based S2ST model for Indic languages. To showcase the utility of the data, we present baseline results on the Indic-S2ST data using the Indic-S2UT. The dataset and codes are available at https://github.com/Nivedita5/Indic-S2ST/blob/main/README.md.

Indic-S2ST: a Multilingual and Multimodal Many-to-Many Indic Speech-to-Speech Translation Dataset

Large language models are powerful but costly. We ask whether meta-learning can make the pretraining of small language models not only faster but also more interpretable. We integrate first–order MAML with subset-masked LM pretraining, producing four LLama-style decoder-only models (11M–570M params), and evaluate on multilingual Universal NER. Compared with vanilla training, our hybrid setup (i) reaches the same loss up to 1.6× sooner, (ii) yields modest but consistent average gains on Universal NER at medium/large scales under equal compute (+2–3 percentage points), and (iii) and (iii) reveals phase-like learning dynamics: models first diversify their representations, then compress them in a pattern that aligns with improved episodic accuracy. These observations are correlational, not causal, and we do not claim generality beyond NER or across seeds. We also document a trade-off: perplexity on Paloma (a diverse language modeling benchmark spanning 18 domains) is worse at most scales. Code, checkpoints and analysis logs are released.

Learning Dynamics of Meta-Learning in Small Model Pretraining

Large language models show strong performance on knowledge intensive tasks such as fact checking and question answering, yet they often struggle with numerical reasoning. We present a systematic evaluation of state-of-the-art models for veracity prediction on numerical claims and evidence pairs using controlled perturbations, including label flipping probes, to test robustness. Our results indicate that even leading proprietary systems experience accuracy drops of up to 62% under certain perturbations. No model proves to be robust across all conditions. We further find that increasing context length generally reduces accuracy, but when extended context is enriched with perturbed demonstrations, most models substantially recover. These findings highlight critical limitations in numerical fact-checking and suggest that robustness remains an open challenge for current language models.

NumPert: Numerical Perturbations to Probe Language Models for Veracity Prediction

Large language models (LLMs) have the potential to be powerful instruments for psychotherapy. However, there is a shortage of practical tools to support their use in production. We develop a novel, iterative process of updating conversational context for tracking EIS (Emotional Intelligence Scale) instantaneously, and test Llama-70b. Through this, we show that (1) EIS varies more on psychotherapeutic (emotional support) conversations than control (emotionally unstimulating) conversations and (2) model responses can be systematically classified to identify consistent patterns. Thus, EIS is a valid indicator of empathetic model behavior. Rises in the EIS score correspond to prosocial behavior, and falls correspond to detached, unsocial behavior. These results suggest that psychometric questionnaires like EIS can provide a structured lens for observing empathetic stability of models and offer a foundation for future work on their role in psychotherapy.

Downloads

Next from IJCNLP-AACL 2025

The Learning Dynamics of Subword Segmentation for Morphologically Diverse Languages

Similar lecture

SEA-HELM: Southeast Asian Holistic Evaluation of Language Models