India

Large language models (LLMs) are increasingly applied in domains that demand reliable and interpretable reasoning. 
While formal methods can generate provably correct proofs, these proofs are often inaccessible to non-expert users. 
This raises a natural question: can LLMs, when given a verified proof, faithfully interpret its reasoning and communicate it clearly? 
We introduce $ProofTeller$, a benchmark that evaluates this ability across three tasks: 
(1) identifying key proof steps, 
(2) summarizing the reasoning, and 
(3) explaining the result in concise natural language. 
The benchmark covers three domains: _Biology_, _Drones_, and _Recipes_, representing scientific, safety-critical, and everyday reasoning scenarios. 
We find a consistent near-conclusion bias: LLMs tend to focus on steps closest to the final proof conclusion rather than on the most informative ones. 
A targeted human study confirms that explanations based on such steps are rated less appropriate for end users. 
These findings indicate that even when reasoning is provided, current LLMs face challenges in communicating key information in a useful manner, highlighting the need for LLMs that can communicate important details reliably.

IJCNLP-AACL 2025

ProofTeller: Exposing recency bias in LLM reasoning and its side effects on communication

recency bias

reasoning

### 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.

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.

SEA-LION: Southeast Asian Languages in One Network

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

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

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

Table question answering (TQA) focuses on answering questions based on tabular data. Developing TQA systems targets effective interaction with tabular data for tasks such as cell retrieval and data analysis. While recent work has leveraged fine-tuning to improve TQA systems, existing approaches often under-utilize available data and neglect the potential of post-training for further gains. In this work, we introduce p²-TQA,  a process-based preference learning framework for TQA post-training. p²-TQA automatically constructs process-based preference data via a table-specific pipeline, eliminating the need for manual or costly data collection. It then optimizes models through contrastive learning on the collected data. Experiments show that p²-TQA effectively improves TQA models by up to 5\% on in-domain datasets and 2.4\% on out-of-domain datasets with only 8,000 training instances. Furthermore, models enhanced with p²-TQA achieve competitive results against larger, more complex state-of-the-art TQA systems, while maintaining up to five times higher efficiency.

p²-TQA: A Process-based Preference Learning Framework for Self-Improving Table Question Answering 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

Theory of Mind (ToM) is the ability to understand others' mental states, which is essential for human social interaction. Although recent studies suggest that large language models (LLMs) exhibit human-level ToM capabilities, the underlying mechanisms remain unclear. "Simulation Theory" posits that we infer others' mental states by simulating their cognitive processes, which has been widely discussed in cognitive science. In this work, we propose a framework for investigating whether the ToM mechanism in LLMs is based on Simulation Theory by analyzing their internal representations. Following this framework, we successfully steered LLMs' ToM reasoning through modeled perspective-taking and counterfactual interventions. Our results suggest that Simulation Theory may partially explain the ToM mechanism in state-of-the-art LLMs, indicating parallels between human and artificial social reasoning.

Downloads

Next from IJCNLP-AACL 2025

SEA-LION: Southeast Asian Languages in One Network

Similar lecture

Natural Language Reasoning in Large Language Models: Analysis and Evaluation