Austria

We transparently create two German-only decoder models, LLäMmlein 120M and 1B, from scratch and publish them, along with the training data, for the (German) NLP research community to use. The model training involved several key steps, including data preprocessing/filtering, the creation of a German tokenizer, the training itself, as well as the evaluation of the final models on various benchmarks, also against existing models. Throughout the training process, multiple checkpoints were saved in equal intervals and analyzed using the German SuperGLEBer benchmark to gain insights into the models&#39; learning process.

Compared to state-of-the-art models on the SuperGLEBer benchmark, both LLäMmlein models performed competitively, consistently matching or surpassing models with similar parameter sizes. The results show that the models&#39; quality scales with size as expected, but performance improvements on some tasks plateaued early during training, offering valuable insights into resource allocation for future models.

ACL 2025

LLäMmlein 🐑: Transparent, Compact and Competitive German-Only Language Models from Scratch

from scratch

german

## Welcome to 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics!
This year, the conference is in Mexico City. NAACL was actually already planned for Mexico City in 2021, but due to the pandemic the entire conference was moved online. This year, finally, we get to go! So it is my sincere pleasure to welcome you to Mexico City, whether in person or virtually. Having the conference in Mexico City is a good opportunity to emphasize that NAACL is our flagship conference for ACL members not only in North America but also in Central and South America, even though NAACL has been bearing “North” in its name. At this year’s conference, we have a theme to match, with a theme track on the Languages of Latin America to showcase the linguistic diversity of the region.
 
The opportunity to present at NAACL should not depend on a researcher’s travel budget, or their family status. This is why it is so important to make virtual participation at NAACL as good an experience as possible – but we want to also provide a good experience for in-person participants. As a community, we are still working out the best way to do that. This year at NAACL, we are trying out a big virtual poster session ahead of the conference, with the hope that this will make make for a lively and interactive experience. At the same time, we are reducing virtual oral presentations, which seem to be particularly tricky to make to work well. A big thanks to the NAACL program chairs and to Luciana Benotti for all their ideas and work to improve the virtual experience. And participants, virtual as well as in-person: Please let us know what worked for you and what didn’t, so we can continue to improve hybrid conferences. 
 
I have been lucky to work with many amazing people. Without their insight, dedication and patience, and without the many hours of work they put in, NAACL would not have been possible. A huge thank you to the program chairs Helena Gomez, Kevin Duh, and Steve Bethard – you are the best! 
 
Finally, I would like to thank all authors, invited speakers and panelists, area chairs and reviewers, the volunteers organizing and chairing sessions, and all attendees, in-person and virtual. Thank you for helping us make NAACL 2024 come to life. 
 
Welcome and hope you all enjoy the conference! 
Katrin Erk 
The University of Texas at Austin 
NAACL-2024 General Chair 
*You can read the full Welcome message in the [Conference Handbook (downloadable)](https://drive.google.com/file/d/1H1NvW0VASQjkSCYgw3mr-3l4yYDSxz6B/view?usp=sharing)*

To access the event page you need to register [**here.**](http://acl.swoogo.com/naacl2024) 
Your access to the event page is limited based on your registration type. If you registered for workshops only, you will gain access to full workshops content on the day of the workshops program.

Please register!

NAACL 2024

2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics

We transparently create two German-only decoder models, LLäMmlein 120M and 1B, from scratch and publish them, along with the training data, for the (German) NLP research community to use. The model training involved several key steps, including data preprocessing/filtering, the creation of a German tokenizer, the training itself, as well as the evaluation of the final models on various benchmarks, also against existing models. Throughout the training process, multiple checkpoints were saved in equal intervals and analyzed using the German SuperGLEBer benchmark to gain insights into the models' learning process.

Compared to state-of-the-art models on the SuperGLEBer benchmark, both LLäMmlein models performed competitively, consistently matching or surpassing models with similar parameter sizes. The results show that the models' quality scales with size as expected, but performance improvements on some tasks plateaued early during training, offering valuable insights into resource allocation for future models.

poster

### 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)

Nonverbal communication is integral to human interaction, with gestures, facial expressions, and body language conveying critical aspects of intent and emotion. However, existing large language models (LLMs) fail to effectively incorporate these nonverbal elements, limiting their capacity to create fully immersive conversational experiences. We introduce MARS, a multimodal language model designed to understand and generate nonverbal cues alongside text, bridging this gap in conversational AI.
Our key innovation is VENUS, a large-scale dataset comprising annotated videos with time-aligned text, facial expressions, and body language.
Leveraging VENUS, we train MARS with a next-token prediction objective, combining text with vector-quantized nonverbal representations to achieve multimodal understanding and generation within a unified framework.
Based on various analyses of the VENUS datasets, we validate its substantial scale and high effectiveness. Our quantitative and qualitative results demonstrate that MARS successfully generates text and nonverbal languages, corresponding to conversational input.
Our dataset and code are available at https://github.com/winston1214/nonverbal-conversation.

Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues

Word Sense Disambiguation (WSD) is a key task in Natural Language Processing (NLP), involving selecting the correct meaning of a word based on its context. With Pretrained Language Models (PLMs) like BERT and DeBERTa now well established, significant progress has been made in understanding contextual semantics. Nevertheless, how well these models inherently disambiguate word senses remains uncertain. In this work, we evaluate several encoder-only PLMs across two popular inventories (i.e. WordNet and the Oxford Dictionary of English) by analyzing their ability to separate word senses without any task-specific fine-tuning. We compute centroids of word senses and measure similarity to assess performance across different layers. Our results show that DeBERTa-v3 delivers the best performance on the task, with the middle layers (specifically the 7th and 8th layers) achieving the highest accuracy, outperforming the output layer by approximately 15 percentage points. Our experiments also explore the inherent structure of WordNet and ODE sense inventories, highlighting their influence on the overall model behavior and performance. Finally, based on our findings, we develop a small, efficient model for the WSD task that attains robust performance while significantly reducing the carbon footprint.

How Much Do Pretrained Language Models Know About Word Senses?

With the increasing intelligence and autonomy of LLM Agents, their potential applications in the legal domain are becoming increasingly apparent. However, existing general-domain benchmarks are unable to fully capture the complexity and subtle nuances inherent in real-world judicial cognition and decision-making. Therefore, we propose LegalAgentBench, a comprehensive benchmark specifically designed to evaluate LLM Agents in the Chinese legal domain. LegalAgentBench includes 17 corpora from real-world legal scenarios and provides 37 tools for interacting with external knowledge. To cover tasks of varying difficulty and types, we designed a scalable task construction process that enables a more precise evaluation of performance in both tool utilization and reasoning. Moreover, Beyond assessing performance through the success rate of final outcomes, LegalAgentBench incorporates keyword analysis during intermediate processes to calculate progress rates, facilitating a more fine-grained evaluation. We evaluated eight popular LLMs, highlighting the strengths, limitations, and potential areas for improvement of existing models and methods. LegalAgentBench sets a new benchmark for the practical application of LLMs in the legal domain, with its code and data available at https://github.com/CSHaitao/LegalAgentBench.

LegalAgentBench: Evaluating LLM Agents in Legal Domain

The surge in online content has created an urgent demand for robust detection systems, especially in non-English contexts where current tools demonstrate significant limitations. We introduce forePLay, a novel Polish-language dataset for erotic content detection, comprising over 24,000 annotated sentences. The dataset features a multidimensional taxonomy that captures ambiguity, violence, and socially unacceptable behaviors. Our comprehensive evaluation demonstrates that specialized Polish language models achieve superior performance compared to multilingual alternatives, with transformer-based architectures showing particular strength in handling imbalanced categories. The dataset and accompanying analysis establish essential frameworks for developing linguistically-aware content moderation systems, while highlighting critical considerations for extending such capabilities to morphologically complex languages.

Behind Closed Words: Creating and Investigating the forePLay Annotated Dataset for Polish Erotic Discourse

In-context learning (ICL) has demonstrated significant potential in enhancing the capabilities of large language models (LLMs) during inference. It's well-established that ICL heavily relies on selecting effective demonstrations to achieve outputs that better align with the expected results. As for demonstration selection, previous approaches have typically relied on intuitive metrics to evaluate the effectiveness of demonstrations, which often results in limited robustness and poor cross-model generalization capabilities. To tackle these challenges, we propose a novel method, **D**emonstration **Va**lidation (**D.Va**), which integrates a demonstration validation perspective into this field. By introducing the demonstration validation mechanism, our method effectively identifies demonstrations that are both effective and highly generalizable. **D.Va** surpasses all existing retrieval-based in-context learning techniques across both natural language understanding (NLU) and natural language generation (NLG) tasks. Additionally, we demonstrate the robustness and generalizability of our approach across various language models and retrieval models.

D.Va: Validate Your Demonstration First Before You Use It

The evolution of speech technology has been spurred by the rapid increase in dataset sizes. Traditional speech models generally depend on a large amount of labeled training data, which is scarce for low-resource languages. This paper presents GigaSpeech 2, a large-scale, multi-domain, multilingual speech recognition corpus. It is designed for low-resource languages and does not rely on paired speech and text data. GigaSpeech 2 comprises about 30,000 hours of automatically transcribed speech, including Thai, Indonesian, and Vietnamese, gathered from unlabeled YouTube videos. We also introduce an automated pipeline for data crawling, transcription, and label refinement. Specifically, this pipeline involves Whisper for initial transcription, MMS for forced alignment, and multi-dimensional filtering for data quality assurance. A modified Noisy Student Training is developed to further refine flawed pseudo labels iteratively, thereby enhancing model performance. Experimental results on our manually transcribed evaluation set and two public test sets from Common Voice and FLEURS confirm our corpus's high quality and broad applicability. Notably, ASR models trained on GigaSpeech 2 can reduce the word error rate for Thai, Indonesian, and Vietnamese on our challenging and realistic YouTube test set by 25% to 40% compared to Whisper large-v3, with merely 10% model parameters. Furthermore, our ASR models trained on GigaSpeech 2 yield superior performance compared to commercial services. We hope that our newly introduced corpus and pipeline will open a new avenue for low-resource speech recognition and significantly facilitate research in this area.

GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement

User sentiment on social media reveals underlying social trends, crises, and needs. Researchers have analyzed users' past messages to track the evolution of sentiments and reconstruct sentiment dynamics. However, predicting the imminent sentiment response of users to ongoing events remains understudied. In this paper, we address the problem of sentiment forecasting on social media to predict users' future sentiment based on event developments. We extract sentiment-related features to enhance modeling and propose a multi-perspective role-playing framework to simulate human response processes. Our preliminary results show significant improvements in sentiment forecasting at both microscopic and macroscopic levels.

Context-Aware Sentiment Forecasting via LLM-based Multi-Perspective Role-Playing Agents

Large language models have opened up a world of possibilities for various NLP tasks, sparking optimism for the future. Despite their potential, LLMs have yet to be widely used as agents on real mobile devices. The main challenge is the need for high-quality data sources. Time constraints and labor intensity often hinder human annotation. On the other hand, existing LLMs exhibit inadequate completion rates and need a robust data filtration strategy. Given these challenges, we develop a framework called AndroidGen to enhance the capabilities of LLM-based agents under data scarcity. In addition, we leverage AndroidGen to collect trajectories given human tasks and train open-source LLMs on these trajectories to develop an open-source mobile agent without manually labeled trajectories. We extensively evaluate AndroidGen with AndroidWorld, AitW, and various popular applications, demonstrating its improvements and revealing potential areas for future improvement. Code, model, and data are available at https://github.com/THUDM/AndroidGen.

AndroidGen: Building an Android Language Agent under Data Scarcity

As large language models (LLMs) reach human-like fluency, reliably distinguishing AI-generated text from human authorship becomes increasingly difficult. While watermarks already exist for LLMs, they often lack flexibility and struggle with attacks such as paraphrasing. To address these issues, we propose a multi-feature method for generating watermarks that combines multiple distinct watermark features into an ensemble watermark. Concretely, we combine acrostica and sensorimotor norms with the established red-green watermark to achieve a 98\% detection rate. After a paraphrasing attack, the performance remains high with 95\% detection rate. In comparison, the red-green feature alone as a baseline achieves a detection rate of 49\% after paraphrasing. The evaluation of all feature combinations reveals that the ensemble of all three consistently has the highest detection rate across several LLMs and watermark strength settings. Due to the flexibility of combining features in the ensemble, various requirements and trade-offs can be addressed. Additionally, the same detection function can be used without adaptations for all ensemble configurations. This method is particularly of interest to facilitate accountability and prevent societal harm.

Ensemble Watermarks for Large Language Models

The LLM-as-a-judge paradigm uses large language models (LLMs) for automated text evaluation, assigning a score to the input based on scoring rubrics. Existing methods for fine-tuning LLM-as-a-judge use cross-entropy (CE) loss, which neglects the numeric nature of score prediction. Recent work addresses numerical prediction limitations of LLM fine-tuning through regression-aware fine-tuning but does not consider chain-of-thought (CoT) reasoning for score prediction. In this paper, we introduce TRACT (Two-stage Regression-Aware fine-tuning with CoT), which combines CoT reasoning with regression-aware training. TRACT uses a two-stage process: first, it fine-tunes the seed LLM to generate CoTs, which serve as the training data for the second stage; next, it uses these self-generated CoTs to retrain the seed LLM. The fine-tuning objective of TRACT applies CE loss for CoT reasoning and regression-aware loss for the score. Experiments across four LLM-as-a-judge datasets and two LLMs show that TRACT significantly outperforms existing methods. Extensive ablation studies validate the effectiveness of each component in TRACT.

Downloads

Next from ACL 2025

Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues

Similar lecture

SuperGLEBer: German Language Understanding Evaluation Benchmark