United States

Large Multimodal Models (LMMs) exhibit impressive performance across various multimodal tasks. However, their effectiveness in cross-cultural contexts remains limited due to the predominantly Western-centric nature of most data and models. Conversely, multi-agent models have shown significant capability in solving complex tasks. Our study evaluates the collective performance of LMMs in a multi-agent interaction setting for the novel task of cultural image captioning. Our contributions are as follows: (1) We introduce MosAIC, a Multi-Agent framework to enhance cross-cultural Image Captioning using LMMs with distinct cultural personas; (2) We provide a dataset of culturally enriched image captions in English for images from China, India, and Romania across three datasets: GeoDE, GD-VCR, CVQA; (3) We propose a culture-adaptable metric for evaluating cultural information within image captions; and (4) We show that the multi-agent interaction outperforms single-agent models across different metrics, and offer valuable insights for future research.

NAACL 2025

The Power of Many: Multi-Agent Multimodal Models for Cultural Image Captioning

cultural image captioning

multi-agent collaboration

vision-language model

### 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

technical paper

Time complexity is a theoretic measure to determine the amount of time the algorithm needs
for its execution. In reality, developers write
algorithms into code snippets within limited
resources, making the calculation of a code’s
time complexity a fundamental task. However,
determining the precise time complexity of a
code is theoretically undecidable. In response,
recent advancements have leaned toward deploying datasets for code time complexity prediction and initiating preliminary experiments
for this challenge. We investigate the challenge
in low-resource scenarios where only a few labeled instances are given for training. Remarkably, we are the first to introduce TCProF: a
Time-Complexity Prediction SSL Framework
as an effective solution for code time complexity prediction in low-resource settings. TCProF
significantly boosts performance by integrating our augmentation, symbolic modules, and
a co-training mechanism, achieving a more
than 60% improvement over self-training approaches. We further provide an extensive comparative analysis between TCProF, ChatGPT,
and Gemini-Pro, offering a detailed evaluation
of our approach.

TCProF: Time-Complexity Prediction SSL Framework

While large language models (LLMs) excel in generating coherent and contextually rich outputs, their capacity to efficiently handle long-form contexts is limited by fixed-length position embeddings. Additionally, the computational cost of processing long sequences increases quadratically, making it challenging to extend context length. To address these challenges, we propose Long-form Context Injection with Recurrent Compression (LCIRC), a method that enables the efficient processing long-form sequences beyond the model's length limit through recurrent compression without retraining the entire model. We further introduce query dependent context modeling, which selectively compresses query-relevant information, ensuring that the model retains the most pertinent content. Our empirical results demonstrate that Query Dependent LCIRC (QD-LCIRC) significantly improves LLM's ability to manage extended contexts, making it well-suited for tasks that require both comprehensive context understanding and query relevance.

LCIRC: A Recurrent Compression Approach for Efficient Long-form Context and Query Dependent Modeling in LLMs

As Large Language Models (LLMs) increasingly influence content generation across diverse platforms, there is a heightened urgency to regulate their outputs to ensure safe usage. However, defining safety is complex, given that entities across domains may interpret it through varied lenses and develop safety detectors—models trained to identify specific unsafe content based on predefined criteria. To address this complexity, we introduce the approach of Adaptive Integration of Detectors (AID) to orchestrate the strengths of multiple pretrained detectors to ensure comprehensive effectiveness in diverse scenarios. AID employs a Mixture-of-Experts (MoE) framework, wherein it dynamically assigns and learns data-adaptive weights for each detector using domain-specific annotated data and LLM-extracted features. We provide theoretical insights into why MoE can be effective by showing its optimality in a Neyman-Pearson setting. Our experimental studies using various detection tasks curated from benchmark datasets demonstrate AID's ability to synergistically combine the unique capabilities of individual detectors. For example, it is observed that AID can improve the area under the curve (AUC) by an absolute value of 0.07 to 0.21, with a median of 0.12, compared to the best individual detectors developed for specific safety aspects. The improvement is particularly significant for complex detection tasks that mix different unsafe data sources.

AID: Adaptive Integration of Detectors for Safe AI with Language Models

Differentially private SGD (DPSGD) enables privacy-preserving training of language models, but often reduces utility, diversity, and linguistic quality. We introduce DPRefine, a three-phase method that initializes a model using data synthesis from a small pre-trained LM with rigorous filtering, applies DP finetuning on private data, and performs self-distillation to refine outputs. This approach significantly outperforms vanilla DPSGD, with AlpacaEval preferring DPRefine’s generations in 78.38% of cases across all datasets and metrics, while also demonstrating substantial improvements in lexical diversity, achieving 85.31% in MSTTR and 86.82% in Jaccard similarity. Our fine-grained analysis reveals that DPRefine reduces linguistic errors in generated text by 84%, mitigating grammar errors, spelling mistakes, and missing punctuation commonly associated with DPSGD. It also reduces inconsistencies present in non-private models, such as fabricated details and misattributed quotes. We find that small models like GPT-2 and T5 are effective for initialization and distillation, highlighting their potential in enabling scalable and efficient deployment of high-performing, privacy-preserving language models with improved linguistic quality and consistency.

Differentially Private Learning Needs Better Model Initialization and Self-Distillation

Due to the scarcity of agent-oriented pre-training data, LLM-based autonomous agents typically rely on complex prompting or extensive fine-tuning, which often fails to introduce new capabilities while preserving strong generalizability. We introduce Hephaestus-Forge, the first large-scale pre-training corpus designed to enhance the fundamental capabilities of LLM agents in API function calling, intrinsic reasoning and planning, and adapting to environmental feedback. Hephaestus-Forge comprises 103B agent-specific data encompassing 76,537 APIs, including both tool documentation to introduce knowledge of API functions and function calling trajectories to strengthen intrinsic reasoning. To explore effective training protocols, we investigate scaling laws to identify the optimal recipe in data mixing ratios. By continual pre-training on Hephaestus-Forge, Hephaestus outperforms small- to medium-scale open-source LLMs and rivals commercial LLMs on three agent benchmarks, demonstrating the effectiveness of our pre-training corpus in enhancing fundamental agentic capabilities and generalization of LLMs to new tasks or environments.

Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training

Retrieval-augmented generation (RAG) enhances the question answering (QA) abilities of large language models (LLMs) by integrating external knowledge. However, adapting general-purpose RAG systems to specialized fields such as science and medicine poses unique challenges due to distribution shifts and limited access to domain-specific data. To tackle this, we propose SimRAG, a self-training approach that equips LLMs with joint capabilities of question answering and question generation for domain adaptation. Our method first fine-tunes LLMs on instruction-following, question-answering, and search-related data. Then, it prompts LLMs to generate diverse domain-relevant questions from unlabeled corpora, with an additional filtering strategy to retain high-quality synthetic examples. By leveraging these synthetic examples, the LLMs can improve their performance on domain-specific RAG tasks. Experiments on 11 datasets across three different domains verify the efficacy of SimRAG over baselines by 1.2%--8.6%.

SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains

Power consumption plays a crucial role in on-device streaming speech recognition, significantly influencing the user experience. This study explores how the configuration of weight parameters in speech recognition models affects their overall energy efficiency. We found that the influence of these parameters on power consumption varies depending on factors such as invocation frequency and memory allocation. Leveraging these insights, we propose design principles that enhance on-device speech recognition models by reducing power consumption with minimal impact on accuracy. Our approach, which adjusts model components based on their specific energy sensitivities, achieves up to 47% lower energy usage while preserving comparable model accuracy and improving real-time performance compared to leading methods.

Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions

Beyond conventional paradigms of translating speech and text, recently, there has been interest in automated transcreation of images to facilitate localization of visual content across different cultures. Attempts to define this as a formal Machine Learning (ML) problem have been impeded by the lack of automatic evaluation mechanisms, with previous work relying solely on human evaluation. In this paper, we seek to close this gap by proposing a suite of automatic evaluation metrics inspired by machine translation (MT) metrics, categorized into: a) Object-based, b) Embedding-based, and c) VLM-based. Drawing on theories from translation studies and real-world transcreation practices, we identify three critical dimensions of image transcreation: cultural relevance, semantic equivalence and visual similarity, and design our metrics to evaluate systems along these axes. Our results show that proprietary VLMs best identify cultural relevance and semantic equivalence, while vision-encoder representations are adept at measuring visual similarity. Meta-evaluation across 7 countries shows our metrics agree strongly with human ratings, with average segment-level correlations ranging from 0.55-0.87. Finally, through a discussion of the merits and demerits of each metric, we offer a robust framework for automated image transcreation evaluation, grounded in both theoretical foundations and practical application. Our code can be found here: https://github.com/simran-khanuja/automatic-eval-transcreation

Towards Automatic Evaluation for Image Transcreation

Text simplification is crucial for improving accessibility and comprehension for English as a Second Language (ESL) learners. This study goes a step further and aims to facilitate ESL learners' language acquisition by simplification. Specifically, we propose simplifying complex sentences to appropriate levels for learners while also increasing vocabulary coverage of the target level in the simplifications. We achieve this without a parallel corpus by conducting reinforcement learning on a large language model. Our method employs token-level and sentence-level rewards, and iteratively trains the model on its self-generated outputs to guide the model to search for simplification hypotheses that satisfy the target attributes. Experiment results on CEFR-SP and TurkCorpus datasets show that the proposed method can effectively increase the frequency and diversity of vocabulary of the target level by more than 20% compared to baseline models, while maintaining high simplification quality.

Aligning Sentence Simplification with ESL Learner's Proficiency for Language Acquisition

In languages without orthographic word boundaries, NLP models perform _word segmentation_, either as an explicit preprocessing step or as an implicit step in an end-to-end computation. This paper shows that Chinese NLP models are vulnerable to _morphological garden path errors_—errors caused by a failure to resolve local word segmentation ambiguities using sentence-level morphosyntactic context. We propose a benchmark, _ERAS_, that tests a model's vulnerability to morphological garden path errors by comparing its behavior on sentences with and without local segmentation ambiguities. Using ERAS, we show that word segmentation models make morphological garden path errors on locally ambiguous sentences, but do not make equivalent errors on unambiguous sentences. We further show that sentiment analysis models with character-level tokenization make implicit garden path errors, even without an explicit word segmentation step in the pipeline. Our results indicate that models' segmentation of Chinese text often fails to account for morphosyntactic context.

Downloads

Next from NAACL 2025

TCProF: Time-Complexity Prediction SSL Framework

Similar lecture

Navigating the Cultural Kaleidoscope: A Hitchhiker’s Guide to Sensitivity in Large Language Models