United States

Context:
Despite the impressive capabilities of Large Language Models (LLMs), they pose significant risks in many domains and therefore require guardrails throughout the lifecycle.


Problem:
Many such guardrails are trained as classifiers with domain-specific human text datasets obtained from sources such as social media and they achieve reasonable performance against closed-domain benchmarks. When deployed in the real world, however, the guardrails have to deal with machine text in an open domain, and their performance deteriorates drastically, rendering them almost unusable due to a high level of false refusal.


Solution:
In this paper, using a self-harm detector as an example, we demonstrate the specific challenges facing guardrail deployment due to the data drift between training and production environments. More specifically, we formed two hypotheses about the potential causes, i.e. closed vs. open domain, human vs. LLM-generated text, and conducted five experiments to explore various potential remedies, including their respective advantages and disadvantages.


Evaluation:
While focusing on one example, our experience and knowledge of LLM guardrails give us great confidence that our work contributes to a more thorough understanding of guardrail deployment and can be generalized as a methodology to build more robust domain-specific guardrails in real-world applications.

NAACL 2025

Challenges and Remedies of Domain-Specific Classifiers as LLM Guardrails: Self-Harm as a Case Study

self-harm

guardrails

large language models

It is my great pleasure and honor to welcome you to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), held in San Diego, California, USA, July 2–7, 2026. ACL 2026 continues our fields 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.

It is exciting to see the many developments in the field reflected at our conference, such as the advancement of large language models (born out of our community) into many application directions. This is not without challenges, partly due to unsolved problems, and partly due to misuse of the technology. All this is reflected well at ACL 2026. The conference also reflects that the field is not only about advancing technology, but also the science of fundamentally understanding language and how it is use by many different speaker communities. 
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) 
<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing')">Conference Handbook</button></html>

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 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.aclweb.org/registration/) first.

**Online Registration Form**: https://acl.swoogo.com/acl2026

Registration Required

ACL 2026

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

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

Manual assignment of Anatomical Therapeutic Chemical (ATC) codes to prescription records is a significant bottleneck in healthcare research and operations at Ontario Health and InterRAI Canada, requiring extensive expert time and effort. To automate this process while maintaining data privacy, we develop a practical approach using locally deployable large language models (LLMs). Inspired by recent advances in automatic International Classification of Diseases (ICD) coding, our method frames ATC coding as a hierarchical information extraction task, guiding LLMs through the ATC ontology level-by-level to reduce complexity. We evaluate our approach using GPT-4 as a performance ceiling and focus development on open-source Llama models suitable for privacy-sensitive deployment. Testing across Health Canada drug product data, RABBITS benchmark, and real clinical notes from Ontario Health, our method achieves 78% exact match accuracy with GPT-4 and 60% with Llama 3.1 70B on Health Canada product names, with similar performance on actual clinical prescriptions. We investigate knowledge grounding strategies by augmenting LLM prompts with drug definitions, finding modest improvements in accuracy. Further, we demonstrate that fine-tuned Llama 3.1 8B achieves performance comparable to zero-shot Llama 3.1 70B, suggesting that effective ATC coding is feasible with limited computational resources. Our results establish the viability of automated ATC coding in privacy-sensitive healthcare environments while highlighting practical considerations for deployment. This work provides Ontario Health and InterRAI Canada with a foundation for automating ATC coding processes in healthcare settings, without compromising data privacy or security.

Zero-Shot ATC Coding with Large Language Models for Clinical Assessments

Large Language Models (LLMs) have impacted the writing process, enhancing productivity by collaborating with humans in content creation platforms. However, generating high-quality, user-aligned text to satisfy real-world content creation needs remains challenging. We propose WritingPath, a framework that uses explicit outlines to guide LLMs in generating goal-oriented, high-quality text. Our approach draws inspiration from structured writing planning and reasoning paths, focusing on reflecting user intentions throughout the writing process. To validate our approach in real-world scenarios, we construct a diverse dataset from unstructured blog posts to benchmark writing performance and introduce a comprehensive evaluation framework assessing the quality of outlines and generated texts. Our evaluations with various LLMs demonstrate that the WritingPath approach significantly enhances text quality according to evaluations by both LLMs and professional writers.

Navigating the Path of Writing: Outline-guided Text Generation with Large Language Models

Large Language Models (LLMs) have achieved significant success in open-domain question answering. However, they continue to face challenges such as hallucinations and knowledge cutoffs. These issues can be mitigated through in-context learning by providing LLMs with relevant context before generating answers. Recent literature proposes Knowledge Graph Prompting (KGP) which integrates knowledge graphs with an LLM-based traversal agent to substantially enhance document retrieval quality. 
However, KGP requires costly fine-tuning with large datasets and remains prone to hallucination. 
In this paper, we propose CuriousLLM, an enhancement that integrates a curiosity-driven reasoning mechanism into an LLM agent. This mechanism enables the agent to generate relevant follow-up questions, thereby guiding the information retrieval process more efficiently.
Central to our approach is the development of the new Follow-upQA dataset, which includes questions and supporting evidence as input, with follow-up questions serving as ground truths. 
These follow-up questions either inquire about what is still missing to fully answer the user's query or use special tokens to signify that the retrieved evidence is sufficient. 
Our experiments show that CuriousLLM significantly boosts LLM performance in multi-document question answering (MD-QA), circumventing the substantial computational costs and latency from the original KGP framework.

CuriousLLM: Elevating Multi-Document Question Answering with LLM-Enhanced Knowledge Graph Reasoning

Data scarcity is one of the main problems when it comes to real-world applications of transformer-based models. This is especially evident for task-oriented dialogue (TOD) systems, which require specialized datasets, that are usually not readily available, hindering many companies from adding TOD systems to their services. This study therefore investigates a novel approach to sourcing annotated dialogues from existing monologue material.
Focusing on a real-world example from the travel industry, where a company handles travel inquiries via email, we investigate whether these monologues can be transformed into dialogue formats suitable for training TOD systems. To this end, we fine-tune state-of-the-art Large Language Models for the task of rewriting monologue e-mails as dialogues and annotating them.
To ensure the quality and validity of the generated data, we employ crowd workers to evaluate the dialogues across multiple criteria and to provide gold-standard annotations for the test dataset. We further evaluate the usefulness of the dialogues for training TOD systems.
Our evaluation shows that the dialogues and annotations are of high quality and can serve as a valuable starting point for training TOD systems.
Finally, we make the annotated dataset publicly available to foster future research.

MonoTODia: Translating Monologue Requests to Task-Oriented Dialogues

Predicting how long a patient is going to stay in an Intensive Care Unit (ICU) is considered an important problem for hospital administrators. While a number of studies have deployed classification models that use structured clinical variables, recent advances in language models have opened up the possibilities of using unstructured text data like nursing notes, discharge summaries etc. for ICU length-of-stay(LoS) prediction. In this paper, we propose a technique that analyses nursing notes to predict the remaining length of stay of a patient in the ICU. We propose a joint model of latent note categorization for the prediction. This latent categorization allows the model to identify high-level health contexts that influence patterns of disease severity for a patient. We evaluate the performance of our model on the openly available MIMIC-III dataset. Our preliminary results demonstrate that the proposed model outperforms competitive baselines.

Predicting ICU Length of Stay for Patients using Latent Categorization of Health Conditions

With the rise of online retail, customer reviews have become a critical factor in shaping purchasing decisions. The sheer volume of customer reviews being generated continuously presents a challenge for consumers who must sift through an overwhelming amount of feedback. To address this issue, we introduce RevieWeaver, a novel framework that extracts key product features and provides concise review summaries. Our innovative approach not only scales efficiently to 30 million reviews but also ensures reproducibility and controllability. Moreover, it delivers unbiased and reliable assessments of products that accurately reflect the input reviews.

RevieWeaver: Weaving Together Review Insights by Leveraging LLMs and Semantic Similarity

Existing zero-shot product attribute value (aspect) extraction approaches in e-Commerce industry rely on uni-modal or multi-modal models, where the sellers are asked to provide detailed textual inputs (product descriptions) for the products. However, manually providing (typing) the product descriptions is time-consuming and frustrating for the sellers. Thus, we propose a cross-modal zero-shot attribute value generation framework (ViOC-AG) based on CLIP, which only requires product images as the inputs. ViOC-AG follows a text-only training process, where a task-customized text decoder is trained with the frozen CLIP text encoder to alleviate the modality gap and task disconnection. During the zero-shot inference, product aspects are generated by the frozen CLIP image encoder connected with the trained task-customized text decoder. OCR tokens and outputs from a frozen prompt-based LLM correct the decoded outputs for out-of-domain attribute values. Experiments show that ViOC-AG significantly outperforms other fine-tuned vision-language models for zero-shot attribute value extraction.

Visual Zero-Shot E-Commerce Product Attribute Value Extraction

Typical evaluations of Large Language Models (LLMs) report a single metric per dataset, often representing the model's best-case performance under carefully selected settings. Unfortunately, this approach overlooks model robustness and reliability in real-world applications. For instance, simple paraphrasing of prompts on the MMLU-Pro dataset causes accuracy fluctuations of up to 10%, while reordering answer choices in the AGIEval dataset results in accuracy differences of up to 6.1%. While some studies discuss issues with LLM robustness, there is no unified or centralized framework for evaluating the robustness of language models. To address this gap and consolidate existing research on model robustness, we present SCORE (**S**ystematic **CO**nsistency and **R**obustness **E**valuation), a comprehensive framework for non-adversarial evaluation of LLMs. The SCORE framework evaluates models by repeatedly testing them on the same benchmarks in various setups to give a realistic estimate of their accuracy and consistency. 
We will make the code publicly available to facilitate further development and research.

SCORE: Systematic COnsistency and Robustness Evaluation for Large Language Models

The advancement of large language models (LLMs) has led to a greater challenge of having a rigorous and systematic evaluation of complex tasks performed, especially in enterprise applications. Therefore, LLMs need to be benchmarked with enterprise datasets for a variety of NLP tasks. This work explores benchmarking strategies focused on LLM evaluation, with a specific emphasis on both English and Japanese. The proposed evaluation framework encompasses 25 publicly available domain-specific English benchmarks from diverse enterprise domains like financial services, legal, climate, cyber security, and 2 public Japanese finance benchmarks. The diverse performance of 8 models across different enterprise tasks highlights the importance of selecting the right model based on the specific requirements of each task. Code and prompts are available on GitHub.

Evaluating Large Language Models with Enterprise Benchmarks

Self-attention has revolutionized natural language processing by capturing long-range dependencies and improving context understanding. However, it comes with high computational costs and struggles with sequential data's inherent directionality. This paper investigates and presents a simplified approach called "shared weight self-attention," where a single weight matrix is used for Keys, Queries, and Values instead of separate matrices for each. This approach cuts training parameters by more than half and significantly reduces training time. Our method not only improves efficiency but also achieves strong performance on tasks from the GLUE benchmark, even outperforming the standard BERT baseline in handling noisy and out-of-domain data. Experimental results show a 66.53% reduction in parameter size within the attention block and competitive accuracy improvements of 3.81% and 1.06% over symmetric and pairwise attention-based BERT models, respectively. The source code will be publicly available.

Downloads

Next from NAACL 2025

Zero-Shot ATC Coding with Large Language Models for Clinical Assessments

Similar lecture

Peering Behind the Shield: Guardrail Identification in Large Language Models