United States

Watermarking is a prominent technique to trace the usage of specific large language models (LLMs) by injecting patterns into model-generated content. An ideal watermark should be imperceptible, easily detectable, and robust to text alterations, yet existing methods typically face trade-offs among these properties. This paper utilizes a key-centered scheme to unify existing methods by decomposing a watermark into two components: a key module and a mark module. We show that the trade-off issue is the reflection of the conflict between the scale of the key sampling space during generation and the complexity of key restoration during detection within the key module. To this end, we introduce WaterPool, a simple yet effective key module that preserves a complete key sampling space for imperceptibility while utilizing semantics-based search to improve the key restoration process. WaterPool can integrate seamlessly with existing watermarking techniques, significantly enhancing their performance, achieving near-optimal imperceptibility, and markedly improving their detection efficacy and robustness (+12.73% for KGW, +20.27% for EXP, +7.27% for ITS).

NAACL 2025

WaterPool: A Language Model Watermark Mitigating Trade-Offs among Imperceptibility, Efficacy and Robustness

watermark

safety

poster

### Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Welcome to the 2025 meeting of the Nations of the Americas Chapter of the Association for Computational Linguistics! I am proud to help organize the first NAACL conference to carry the new name of our organization, one that emphasizes inclusion for all of the Americas. I am also pleased to welcome you to Albuquerque, New Mexico, a state whose unique blend of cultural influences will make for an excellent backdrop for NAACL 2025, especially with this year’s special theme on NLP in a Multicultural World. 
**[Continue reading...](https://drive.google.com/file/d/1jX-qGhqVSZZCIrAnJaz798pflu5Irrdn/view?usp=sharing)**

*- Colin Cherry, Google, NAACL 2025 General Chair* 

[![](https://assets.underline.io/markdown_image/1/image/b087f8a4dc5816d6e1a6514e59c59ac3.png)](https://drive.google.com/file/d/1T96GzPqObXrMln2BMByCSXTSizjTg69P/view?usp=sharing)

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Please log in to explore this event.

To access NAACL 2025 event page you are required to register. Please follow [**this link**](https://2025.naacl.org/registration/registration/) to register. Access will depend on your registration type.

Please register!

Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Effective organization of in-context learning (ICL) demonstrations is key to improving the quality of large language model (LLM) responses. To create better sample-label pairs that instruct LLM understanding, we introduce logit separability, a criterion to assess the clarity of both samples and class-related words at the logit level. This facilitates the optimization of sample and label selection, enhancing the precision of information provided in ICL demonstrations. Additionally, we find that incorporating multiple class-related words for each sample, rather than relying on a single class name, improves performance by offering a broader range of label information. Building on these insights, we propose LICL, a logit separability-based method that jointly organizes samples and integrates multiple class-related words into each sample-label pair. Evaluations across seven classification datasets show that this approach significantly improves ICL performance by providing clearer instructions and richer label information.

Logit Separability-Driven Samples and Multiple Class-Related Words Selection for Advancing In-Context Learning

Tracking a patient's cognitive status early in the onset of the disease provides an opportunity to diagnose and intervene in Alzheimer's disease (AD). However, relying solely on magnetic resonance imaging (MRI) images with traditional classification and regression models may not fully extract finer-grained information. This study proposes a multi-task Fusion Language Image Question Answering model (FLIQA-AD) to perform AD identification and Mini Mental State Examination (MMSE) prediction. Specifically, a 3D Adapter is introduced in Vision Transformer (ViT) model for image feature extraction. The patient electronic health records (EHR) information and questions related to the disease work as text prompts to be encoded. Then, an ADFormer model, which combines self-attention and cross-attention mechanisms, is used to capture the correlation between EHR information and structure features. After that, the extracted brain structural information and textual content are combined as input sequences for the large language model (LLM) to identify AD and predict the corresponding MMSE score. Experimental results demonstrate the strong discrimination and MMSE prediction performance of the model, as well as question-answer capabilities.

FLIQA-AD: a Fusion Model with Large Language Model for Better Diagnose and MMSE Prediction of Alzheimer’s Disease

We present lightweight flow matching multilingual text-to-speech (TTS) systems for Ojibwe, Mi'kmaq, and Maliseet, three Indigenous languages in North America. Our results show that training a multilingual TTS model on three typologically similar languages can improve the performance over monolingual models, especially when data are scarce. Attention-free architectures are highly competitive with self-attention architecture with higher memory efficiency. Our research provides technical development to language revitalization for low-resource languages but also highlights the cultural gap in human evaluation protocols, calling for a more community-centered approach to human evaluation.

Developing multilingual speech synthesis system for Ojibwe, Mi’kmaq, and Maliseet

Large language models (LLMs) have shown impressive performance in \emph{code} understanding and generation, making coding tasks a key focus for researchers due to their practical applications and value as a testbed for LLM evaluation. Data synthesis and filtering techniques have been widely adopted and shown to be highly effective in this context. In this paper, we present a focused survey and taxonomy of these techniques, emphasizing recent advancements. We highlight key challenges, explore future research directions, and offer practical guidance for new researchers entering the field.

Mastering the Craft of Data Synthesis for CodeLLMs

In multi-agent scenarios, the ability to anticipate and respond to opponents is essential, particularly in environments involving adversarial and collaborative interactions. In this paper, we introduce Explicit Models of Opponents (EMO) based on Large Language Models (LLMs), enabling agents to better predict and adapt to diverse, dynamic multi-agent interactions. Unlike traditional methods that often simplify multi-agent interactions using a single opponent model, EMO constructs an individual model for each opponent and aligns these models working in synergy through a bi-level feedback-refinement framework. We test EMO alongside several reasoning methods in multi-player deduction games, where agents must infer hidden information about their opponents. The results show that EMO significantly enhances agents' decision-making, outperforming traditional single-model approaches. Our findings demonstrate that EMO can be a powerful tool for enhancing LLM-based agents in complex multi-agent systems.

LLM-Based Explicit Models of Opponents for Multi-Agent Games

The Knowledge Graph Completion (KGC) task aims to infer the missing entity from an incomplete triple. Existing embedding-based methods rely solely on triples in the KG, which is vulnerable to specious relation patterns and long-tail entities. On the other hand, text-based methods struggle with the semantic gap between KG triples and natural language. Apart from triples, entity contexts (e.g., labels, descriptions, aliases) also play a significant role in augmenting KGs. To address these limitations, we propose KGR3, a context-enriched framework for KGC. KGR3 is composed of three modules. Firstly, the Retrieval module gathers supporting triples from the KG, collects plausible candidate answers from a base embedding model, and retrieves context for each related entity. Then, the Reasoning module employs a large language model to generate potential answers for each query triple. Finally, the Re-ranking module combines candidate answers from the two modules mentioned above, and fine-tunes an LLM to provide the best answer. Extensive experiments on widely used datasets demonstrate that KGR3 consistently improves various KGC methods. Specifically, the best variant of KGR3 achieves absolute Hits@1 improvements of 12.3% and 5.6% on the FB15k237 and WN18RR datasets.

Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion

Recently, mobile AI agents have gained increasing attention. Given a task, mobile AI agents can interact with mobile devices in multiple steps and finally form a GUI flow that solves the task. However, existing agents tend to focus on most task-relevant elements at each step, leading to local optimal solutions and ignoring the overall GUI flow. To address this issue, we constructed a training dataset called MobileReach, which breaks the task into page reaching and operation subtasks. Furthermore, we propose ReachAgent, a two-stage framework that focuses on improving its task-completion abilities. It utilizes the page reaching and page operation subtasks, along with reward-based preference GUI flows, to further enhance the agent. Experimental results show that ReachAgent significantly improves the Intersection over Union (IoU) Accuracy and Text Accuracy by 7.12% and 7.69% on the step-level and 4.72% and 4.63% on the task-level compared to the SOTA agent. Our data and code will be released upon acceptance.

ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation

Hypernetworks are a class of meta-networks that generate weights for main neural networks. Their unique parameter spaces necessitate exploring suitable optimization strategies to enhance performance, especially for language models. However, a comprehensive investigation into optimization strategies for hypernetworks remains absent. To address this gap, we analyze the loss landscape of hypernetworks and propose that restart optimization strategies can improve their performance for language models. We find that hypernetworks have inherently more complicated loss landscapes compared to conventional networks due to their distinct parameter spaces. Consequently, a restart strategy that periodically resets the learning rate can facilitate better convergence for hypernetworks. Through experiments on instruction tuning and multi-task training, we demonstrate that the restart strategy consistently enhances the performance of hypernetworks for language models, often more effectively than for conventional deep neural networks. Our findings highlight the importance of tailored optimization techniques to unlock the full potential of hypernetworks in natural language processing tasks.

Enhancing Language Model Hypernetworks with Restart: A Study on Optimization

Large language models, despite their remarkable success in recent years, still exhibit severe cultural bias. Therefore, in this paper, we introduce CultureInstruct, a large-scale instruction-tuning dataset designed to reduce cultural bias in LLMs. CultureInstruct is constructed with an automatic pipeline, utilizing public web sources and a specialized LLM to generate instruction. Our data comprises 430K instructions, ranging from classic NLP tasks to complex reasoning. CultureInstruct also covers 11 most relevant topics to cultural knowledge, making it highly diverse. Our experiments show that fine-tuning LLMs with CultureInstruct results in consistent improvements across three types of cultural benchmarks, including (i) general cultural knowledge, (ii) human opinions and values, and (iii) linguistic cultural bias. Our best model, Qwen2-Instruct 72B + CultureInstruct, outperforms GPT-4o Mini and GPT-4o with 18.47% and 13.07% average relative improvements on cultural benchmarks.

CultureInstruct: Curating Multi-Cultural Instructions at Scale

Recent advancements in large multimodal models (LMMs) have showcased impressive code generation capabilities, primarily evaluated through image-to-code benchmarks. However, these benchmarks are limited to specific visual programming scenarios where the logic reasoning and the multimodal understanding capacities are split apart. To fill this gap, we propose ScratchEval, a novel benchmark designed to evaluate the visual programming reasoning ability of LMMs. ScratchEval is based on Scratch, a block-based visual programming language widely used in children's programming education. By integrating visual elements and embedded programming logic, ScratchEval requires the model to process both visual information and code structure, thereby comprehensively evaluating its programming intent understanding ability. Our evaluation approach goes beyond the traditional image-to-code mapping and focuses on unified logical thinking and problem-solving abilities, providing a more comprehensive and challenging framework for evaluating the visual programming ability of LMMs. ScratchEval not only fills the gap in existing evaluation methods, but also provides new insights for the future development of LMMs in the field of visual programming.

WaterPool: A Language Model Watermark Mitigating Trade-Offs among Imperceptibility, Efficacy and Robustness

Downloads

Next from NAACL 2025

Logit Separability-Driven Samples and Multiple Class-Related Words Selection for Advancing In-Context Learning

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES