United States

Enterprise customers are increasingly adopting language models for critical communication tasks, such as drafting emails, crafting sales pitches, and composing casual messages. Deploying such models across different regions requires them to understand diverse cultural and linguistic contexts and to generate safe and respectful responses. For enterprise applications, it is crucial to mitigate reputational risks, maintain trust, and ensure compliance by effectively identifying and handling unsafe or offensive language. To address this, we develop SweEval, a benchmark simulating real-world scenarios with variations in tone (positive or negative) and context (formal or informal). The prompts explicitly instruct the model to include specific swear words while completing the task. This benchmark evaluates whether LLMs comply with or resist such inappropriate instructions and assesses their alignment with ethical frameworks, cultural nuances, and language comprehension capabilities. In order to advance research in building ethically aligned AI systems for enterprise use and beyond, we will open-source this dataset upon acceptance.

NAACL 2025

SweEval: Do LLMs Really Swear? A Benchmark for Testing Limits for Enterprise Use

llm benchmarks

llm safety

multilingual llms

responsible ai

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

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

The retrieval-augmented generation (RAG) technique enables generative AI models to extract accurate facts from external unstructured data sources. For structured data, RAG is further augmented by function calls to query databases. This paper presents an industrial case study that implements RAG in a large financial institution's call center. The study showcases experiences and architecture for a scalable RAG deployment. It also introduces enhancements to RAG for retrieving facts from structured data sources using data embeddings, achieving low latency and high reliability. Our optimized production application demonstrates an average response time of only 7.33 seconds. Additionally, the paper compares various open-source and closed-source models for answer generation in an industrial context.

Implementing Retrieval Augmented Generation Technique on Unstructured and Structured Data Sources in a Call Center of a Large Financial Institution

Language localization is the adaptation of written content to different linguistic and cultural contexts. Ability to localize written content is crucial for global businesses to provide consistent and reliable customer experience across diverse markets. Traditional methods have approached localization as an application of machine translation (MT), but localization requires more than linguistic conversion – content needs to align with the target audience's cultural norms, linguistic nuances, and technical requirements. This difference is prominent for long-form text, where multiple facts are present in a creative choice of language. We propose a novel prompt approach for Large Languages Models (LLMs), called Break-Ideate-Generate (BrIdGe), for language localization. BrIdGe 'breaks' the source content into granular facts, 'ideates' an action plan for content creation in the target language by organizing the granular facts, and finally executes the plan to 'generate' localized content. This approach emulates the cognitive processes humans employ in writing that begin with identifying important points, followed by brainstorming on how to structure and organize the output. We evaluated the BrIdGe methodology from multiple perspectives, including impact of BrIdGe prompt on different LLMs and performance comparisons with traditional MT models and direct translation through LLMs on public benchmark and proprietary e-commerce datasets. Through human and LLM-based automated evaluations across content in multiple languages, we demonstrate effectiveness of BrIdGe in generating fluent localized content while preserving factual consistency between source and target languages.

Break-Ideate-Generate (BrIdGe): Moving beyond Translations for Localization using LLMs

Hand-crafting high quality prompts to optimize the performance of language models is a complicated and labor-intensive process. Furthermore, when migrating to newer, smaller, or weaker models (possibly due to latency or cost gains), prompts need to be updated to re-optimize the task performance. We propose Concept Distillation (CD), an automatic prompt optimization technique for enhancing weaker models on complex tasks. CD involves: (1) collecting mistakes made by weak models with a base prompt (initialization), (2) using a strong model to generate reasons for these mistakes and create rules/concepts for weak models (induction), and (3) filtering these rules based on validation set performance and integrating them into the base prompt (deduction/verification). We evaluated CD on NL2Code and mathematical reasoning tasks, observing significant performance boosts for small and weaker language models. Notably, Mistral-7B's accuracy on Multi-Arith increased by 20%, and Phi-3-mini-3.8B's accuracy on HumanEval rose by 34%. Compared to other automated methods, CD offers an effective, cost-efficient strategy for improving weak models' performance on complex tasks and enables seamless workload migration across different language models without compromising performance.

Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting

Large Language Models (LLMs) offer the potential to automate hiring by matching job descriptions with candidate resumes, streamlining recruitment processes, and reducing operational costs. However, biases inherent in these models may lead to unfair hiring practices, reinforcing societal prejudices and undermining workplace diversity. This study examines the performance and fairness of LLMs in job-resume matching tasks within the English language and U.S. context. It evaluates how factors such as gender, race, and educational background influence model decisions, providing critical insights into the fairness and reliability of LLMs in HR applications.
Our findings indicate that while recent models have reduced biases related to explicit attributes like gender and race, implicit biases concerning educational background remain significant. These results highlight the need for ongoing evaluation and the development of advanced bias mitigation strategies to ensure equitable hiring practices when using LLMs in industry settings.

Evaluating Bias in LLMs for Job-Resume Matching: Gender, Race, and Education

General vision-language models (VLMs) trained on web data struggle to understand and converse about real-world e-commerce product images. We propose a cost-efficient approach for collecting training data to train a generative VLM for e-commerce product images. The key idea is to leverage large-scale, loosely-coupled image-text pairs from e-commerce stores, use a pretrained LLM to generate multimodal instruction-following data, and fine-tune a general vision-language model using LoRA. Our instruction-finetuned model, VIT-Pro, can understand and respond to queries about product images, covering diverse concepts and tasks. VIT-Pro outperforms several general-purpose VLMs on multiple vision tasks in the e-commerce domain.

VIT-Pro: Visual Instruction Tuning for Product Images

Spoken Named Entity Recognition (NER) aims
to extracting named entities from speech and
categorizing them into types like person, location, organization, etc. In this work, we present
VietMed-NER - the first spoken NER dataset
in the medical domain. To our best knowledge, our real-world dataset is the largest spoken NER dataset in the world in terms of the
number of entity types, featuring 18 distinct
types. Furthermore, we present baseline results
using various state-of-the-art pre-trained models: encoder-only and sequence-to-sequence;
and conduct quantitative and qualitative error
analysis. We found that pre-trained multilingual models generally outperform monolingual
models on reference text and ASR output, encoders outperform sequence-to-sequence models in NER tasks, and pre-trained audio data
affects ASR output but not NER performance
in the cascaded setting. By simply translating,
the dataset is applicable not just to Vietnamese
but to other languages as well. All code, data
and models are made publicly available here.

Medical Spoken Named Entity Recognition

This paper analyses the safety of Large Language Models (LLMs) in interactions with children below age of 18 years. Despite the transformative applications of LLMs in various aspects of children’s lives, such as education and therapy, there remains a significant gap in understanding and mitigating potential content harms specific to this demographic. The study acknowledges the diverse nature of children, often overlooked by standard safety evaluations, and proposes a comprehensive approach to evaluating LLM safety specifically for children. We introduce a novel Harm Taxonomy to classify potential risks that children may encounter when using LLM-powered applications. Additionally, we develop Child User Models that reflect the varied personalities and interests of children, informed by literature in childcare and psychology. These user models aim to bridge the existing gap in child safety literature across various fields. We utilize Child User Models to evaluate the safety of six state-of-the-art LLMs. Our observations reveal significant safety gaps in LLMs, particularly in categories harmful to children but not adults.

LLM Safety for Children

In real-world applications with Large Language Models (LLMs), external retrieval mechanisms—such as Search-Augmented Generation (SAG), tool utilization, and Retrieval-Augmented Generation (RAG)—are often employed to enhance the quality of augmented generations in dialogues. These approaches often come with multi-turn dialogue, where each interaction is enriched by relevant information retrieved from external sources. Existing benchmarks either assess LLMs' chat abilities in multi-turn dialogues or their use of retrieval for augmented responses in limited tasks such as knowledge QA or numeric reasoning. To address this gap, we introduce **RAD**-Bench (**R**etrieval **A**ugmented **D**ialogue), a comprehensive benchmark designed to evaluate LLMs' capabilities in multi-turn dialogues following retrievals. RAD-Bench evaluates two key abilities of LLMs: Retrieval Synthesis and Retrieval Reasoning over 6 representative scenarios, concluded from analysis of real-world tasks. By employing discriminative questions, retrieved contexts, and reference answers, our evaluation of prevalent LLMs reveals performance degradation as additional layers of conditions or constraints are applied across conversation turns, even when accurate retrieved contexts are provided.

RAD-Bench: Evaluating Large Language Models’ Capabilities in Retrieval Augmented Dialogues

Construction standards across different countries provide technical guidelines to ensure the quality and safety of buildings and facilities, with periodic revisions to accommodate advances in construction technology. However, these standards often contain overlapping or conflicting content owing to their broad scope and interdependence, complicating the revision process and creating public inconvenience. Although current expert-driven manual approaches aim to mitigate these issues, they are time-consuming, costly, and error-prone. To address these challenges, we propose conflict and overlap classification in construction standards using a large language model (COSLLM), a framework that leverages a construction domain-adapted large language model for the semantic comparison of sentences in construction standards. COSLLM utilizes a two-step reasoning process that adaptively employs chain-of-thought reasoning for the in-depth analysis of sentences suspected of overlaps or conflicts, ensuring computational and temporal efficiency while maintaining high classification accuracy. The framework achieved an accuracy of 97.9% and a macro F1-score of 0.907 in classifying real-world sentence pairs derived from Korean construction standards as overlapping, conflicting, or neutral. Furthermore, we develop and deploy a real-time web-based system powered by COSLLM to facilitate the efficient establishment and revision of construction standards.

Conflict and Overlap Classification in Construction Standards Using a Large Language Model

Proteins play critical roles in biological systems, yet 99.7% of over 227 million known protein sequences remain uncharacterized due to the limitations of experimental methods. To assist experimentalists in narrowing down hypotheses and accelerating protein characterization, we present Protein2Text, a multimodal large language model that interprets protein sequences and generates informative text to address open-ended questions about protein functions and attributes. By integrating a resampling mechanism within an adapted LLaVA framework, our model effectively maps protein sequences into a language-compatible space, enhancing its capability to handle diverse and complex queries. Trained on a newly curated dataset derived from PubMed articles and rigorously evaluated using four comprehensive benchmarks—including in-domain and cross-domain evaluations—Protein2Text outperforms several existing models in open-ended question-answering tasks. Our work also highlights the limitations of current evaluation metrics applied to template-based approaches, which may lead to misleading results, emphasizing the need for unbiased assessment methods. By making our datasets and models publicly available, we aim to support ongoing research in computational biology and protein analysis using multimodal language models.

Downloads

Next from NAACL 2025

Implementing Retrieval Augmented Generation Technique on Unstructured and Structured Data Sources in a Call Center of a Large Financial Institution

Similar lecture

Can LLMs Help You at Work? A Sandbox for Evaluating LLM Agents in Enterprise Environments