United States

As the prevalence of phishing attacks continues to rise, there is an increasing demand for more robust detection technologies. With recent advances in AI, we discuss how to construct a reliable and practical phishing detection system using language models. For this system, we introduce the first large-scale Korean dataset for phishing detection, encompassing six types of phishing attacks. We consider multiple factors for building a real-time detection system for edge devices, such as model size, Speech-To-Text quality, split length, training technique and multi-task learning. We evaluate the model&#39;s ability twofold: in-domain, and unseen attack detection performance which is referred to as zero-day performance. Additionally, we demonstrate the importance of accurate comparison groups and evaluation datasets, showing that voice phishing detection performs reasonably well while smishing detection remains challenging. Both the dataset and the trained model will be available upon request.

NAACL 2025

Towards Reliable and Practical Phishing Detection

phishing detection

dataset

real-time

### 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**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

As the prevalence of phishing attacks continues to rise, there is an increasing demand for more robust detection technologies. With recent advances in AI, we discuss how to construct a reliable and practical phishing detection system using language models. For this system, we introduce the first large-scale Korean dataset for phishing detection, encompassing six types of phishing attacks. We consider multiple factors for building a real-time detection system for edge devices, such as model size, Speech-To-Text quality, split length, training technique and multi-task learning. We evaluate the model's ability twofold: in-domain, and unseen attack detection performance which is referred to as zero-day performance. Additionally, we demonstrate the importance of accurate comparison groups and evaluation datasets, showing that voice phishing detection performs reasonably well while smishing detection remains challenging. Both the dataset and the trained model will be available upon request.

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

Leveraging large language models (LLMs) for complex natural language tasks typically requires long-form prompts to convey detailed requirements and information, which results in increased memory usage and inference costs. To mitigate these challenges, multiple efficient methods have been proposed, with prompt compression gaining significant research interest. This survey provides an overview of prompt compression techniques, categorized into hard prompt methods and soft prompt methods. First, the technical approaches of these methods are compared, followed by an exploration of various ways to understand their mechanisms, including the perspectives of attention optimization, Parameter-Efficient Fine-Tuning (PEFT), modality integration, and new synthetic language. We also examine the downstream adaptations of various prompt compression techniques. Finally, the limitations of current prompt compression methods are analyzed, and several future directions are outlined, such as optimizing the compression encoder, combining hard and soft prompts methods, and leveraging insights from multimodality.

Prompt Compression for Large Language Models: A Survey

This paper presents LLaMA-Berry, an advanced mathematical reasoning framework to enhance the problem-solving ability of large language models (LLMs). The framework combines Monte Carlo Tree Search with Self-Refine (SR-MCTS) to optimize the reasoning paths and utilizes a pairwise reward model to evaluate different paths globally. By leveraging the self-critique and rewriting capabilities of LLMs, our SR-MCTS overcomes the inefficiencies and limitations of conventional step-wise and greedy search algorithms, enabling a more efficient exploration of solution spaces. To guide the search process, we propose the Pairwise Preference Reward Model (PPRM), which predicts pairwise preferences between solutions through instruction-following capabilities trained by Reinforcement Learning from Human Feedback (RLHF). Finally, the Enhanced Borda Count (EBC) method is adopted to synthesize pairwise preferences into global quantile scores for evaluations. This approach mitigates the challenges of scoring variability and non-independent distributions in mathematical reasoning tasks. The framework has been tested on general and advanced benchmarks, showing superior search efficiency and performance compared to existing open-source and closed-source methods, particularly in complex Olympiad-level benchmarks, including AIME24 and AMC23.

LLaMA-Berry: Pairwise Optimization for Olympiad-level Mathematical Reasoning via O1-like Monte Carlo Tree Search

In this work we systematically investigate how specific attributes of preference datasets affect the alignment and downstream performance of LLMs in instruction-following tasks. We use a novel synthetic data generation pipeline to generate 48,000 unique instruction-following prompts with combinations of 23 verifiable constraints that enable fine-grained and automated quality assessments of model responses. With our synthetic prompts, we use rejection sampling (RS) and Monte Carlo Tree Search (MCTS) to obtain preference pairs. Then, we perform experiments investigating the effects of (1) the presence of shared prefixes between the chosen and rejected responses, (2) the contrast and quality of the chosen, rejected responses and (3) the complexity of the training prompts. Our experiments reveal that shared prefixes provide marginal but consistent improvements and greater stability across challenging training configurations. While high-contrast preference pairs generally outperform low-contrast pairs, combining both often yields the best performance. Additionally, training on prompts of moderate difficulty leads to better generalization across different tasks. Our findings provide actionable insights into optimizing preference data curation for instruction-following tasks, offering a scalable and effective framework for enhancing LLM training and alignment.

A Systematic Examination of Preference Learning through the Lens of Instruction-Following

We introduce DateLogicQA, a human-curated benchmark of 190 questions specifically designed to understand temporal bias in Large Language Models (LLMs). Covering seven date formats across past, present, and future contexts, DateLogicQA examines four reasoning types: commonsense, factual, conceptual, and numerical. Through human-led evaluations of 12 state-of-the-art LLMs, we identify Representation-Level Bias, arising from suboptimal embeddings that distort date semantics, and Logical-Level Bias, manifesting when correct date tokens yield flawed temporal reasoning. Our findings underscore persistent challenges in handling various date formats and temporal contexts, revealing the need for more robust pretraining data, targeted post-training methods, and precise tokenization strategies. By illuminating these biases, we provide actionable insights to guide the development of LLMs for accurate temporal reasoning across diverse real-world applications.

DateLogicQA: Benchmarking Temporal Biases in Large Language Models

Large Language Models (LLMs) have recently demonstrated remarkable generative abilities, producing coherent text even with long input sequences. 
In the medical domain, LLMs have opened new research questions about their ability to interpret complex medical documents and extract useful information for a variety of purposes. 
Recent work has shown promising LLM performance on generation and summarization of clinical reports, doctor-patient interactions, patient progress notes, etc.
In this paper, we evaluate a suite of open-source models ranging from 1B to 70B parameters on a recent discharge report summarization dataset through in-context learning and fine-tuning. 
We show that zero-shot 8B parameter models outperform past zero-shot work on this dataset, and that efficient fine-tuning of small 3B parameter models on fewer than 100 examples perform as well as large 70B parameter models used few-shot.

Efficient LLM Adaptation for Long Clinical Text Summarization

Augmenting large language models (LLMs) with external context significantly improves their performance in natural language processing (NLP) tasks. However, LLMs struggle to answer queries reliably when the provided context lacks information, often resorting to ungrounded speculation or internal knowledge. Groundedness, or the ability to generate responses strictly supported by the context, is essential for ensuring factual consistency and trustworthiness. This study focuses on detecting whether a given query is grounded in a document supplied in context before the computationally expensive answer generation by LLMs. This will potentially reduce both inference time and resource consumption. We show that lightweight, task-specific encoder models such as RoBERTa, fine-tuned on curated datasets, can achieve accuracy comparable to state-of-the-art LLMs such as Llama3 8B and GPT4 in groundedness detection while reducing inference latency by orders of magnitude.

Small Encoders Can Rival Large Decoders in Detecting Groundedness

Large language models (LLMs) demonstrate significant potential in advancing medical applications, yet their capabilities in addressing medical ethics challenges remain underexplored. This paper introduces MedEthicEval, a novel benchmark designed to systematically evaluate LLMs in the domain of medical ethics. Our framework encompasses two key components: knowledge, assessing the models' grasp of medical ethics principles, and application, focusing on their ability to apply these principles across diverse scenarios. To support this benchmark, we consulted with medical ethics researchers and developed three datasets addressing distinct ethical challenges: blatant violations of medical ethics, priority dilemmas with clear inclinations, and equilibrium dilemmas without obvious resolutions. MedEthicEval serves as a critical tool for understanding LLMs' ethical reasoning in healthcare, paving the way for their responsible and effective use in medical contexts.

MedEthicEval: Evaluating Large Language Models Based on Chinese Medical Ethics

Application of LLMs for complex causal question answering can be stymied by their opacity and propensity for hallucination. Although recent approaches such as Retrieval Augmented Generation and Chain of Thought prompting have improved reliability, we argue current approaches are insufficient and further fail to satisfy key criteria humans use to select and evaluate causal explanations. Inspired by findings from the social sciences, we present an implemented causal QA approach that combines iterative RAG with guidance from a formal model of causation. Our causal model is backed by the Cogent reasoning engine, allowing users to interactively perform counterfactual analysis and refine their answer. Our approach has been integrated into a deployed Collaborative Research Assistant (Cora) and we present an evaluation in the life sciences domain.

From Generating Answers to Building Explanations: Integrating Multi-Round RAG and Causal Modeling for Scientific QA

Multi-modal Large Language Models have shown remarkable progress in visual contexts, yet their ability to convert visual figures into executable code remains underexplored. To address this, we introduce Plot2Code, a comprehensive benchmark designed to assess MLLMs' visual coding capabilities. Plot2Code includes 132 high-quality matplotlib plots across six plot types, as well as an additional 150 and 86 plots from Python’s and R’s plotly libraries respectively, totaling 368 plots. Each plot is paired with its source code and a descriptive instruction generated by GPT-4, enabling thorough evaluation across diverse inputs. Furthermore, we propose three automatic evaluation metrics—code pass rate, text-match ratio, and GPT-4V rating judgement—to assess the quality of generated code and rendered images. Notably, the GPT-4V rating demonstrates strong reliability, as it correlates well with human evaluations, particularly for datasets of a certain size. Cross-validation across MLLMs (GPT-4V, Gemini-1.5-Pro, and Claude-3-Opus) also shows high consistency in ratings, which likely stems from the fact that ratings are based on rendered images rather than direct MLLM outputs, indicating minimal bias for this metric. Our evaluation of 14 MLLMs, including both proprietary and open-source models, highlights significant challenges in visual coding, particularly for text-dense plots, where MLLMs heavily rely on textual instructions. We believe these findings will advance future development of MLLMs.

Plot2Code: A Comprehensive Benchmark for Evaluating Multi-modal Large Language Models in Code Generation from Scientific Plots

Reward models (RMs) play a critical role in aligning language models through the process of reinforcement learning from human feedback. RMs are trained to predict a score reflecting human preference, which requires significant time and cost for human annotation. Additionally, RMs tend to quickly overfit on superficial features in the training set, hindering their generalization performance on unseen distributions. We propose a novel approach using synthetic natural language critiques generated by large language models to provide additional feedback, evaluating aspects such as instruction following, correctness, and style. This offers richer signals and more robust features for RMs to assess and score on. We demonstrate that high-quality critiques improve the performance and data efficiency of RMs initialized from different pretrained models, reducing the reliance on costly human annotations. Furthermore, incorporating critiques improves both the interpretability and robustness of RM training.

Downloads

Next from NAACL 2025

Prompt Compression for Large Language Models: A Survey

Similar lecture

Adaptive Linguistic Prompting (ALP) Enhances Phishing Webpage Detection in Multimodal Large Language Models