United States

Large language models (LLMs) have gained popularity in recent years for their utility in various applications. However, they are sensitive to non-semantic changes in prompt formats, where small changes in the prompt format can lead to significant performance fluctuations. In the literature, this problem is commonly referred to as prompt brittleness. Previous research on prompt engineering has focused mainly on developing techniques for identifying the optimal prompt for specific tasks. Some studies have also explored the issue of prompt brittleness and proposed methods to quantify performance variations; however, no simple solution has been found to address this challenge. We propose Mixture of Formats (MOF), a simple and efficient technique for addressing prompt brittleness in LLMs by diversifying the styles used in the prompt few-shot examples. MOF was inspired by computer vision techniques that utilize diverse style datasets to prevent models from associating specific styles with the target variable. Empirical results show that our proposed technique reduces style-induced prompt brittleness in various LLMs while also enhancing overall performance across prompt variations and different datasets.

NAACL 2025

Towards LLMs Robustness to Changes in Prompt Format Styles

prompt brittleness

few-shot generation

prompt engineering

### Welcome to IJCNLP-AACL 2025! 
 It is a great honor to host this joint conference in Mumbai, India, from December 20 to 24, 2025. The joint conferences of IJCNLP and AACL are organized with alternating leadership in the Asia-Pacific region. The event is run by the Asian Federation of Natural Language Processing (AFNLP) in odd years, and by AACL in even years, while it is organized solely by ACL when the annual ACL meeting is held in the region. This year, the conference is primarily organized by AFNLP. 
*Kentaro Inui
MBZUAI, UAE
General Chair, IJCNLP-AACL 2025* 
Read full message and download the Conference Handbook [**here**](https://drive.google.com/file/d/1UTwxkAqSqI-GAoJC3wE1zZt5VP1Y8GX0/view?usp=sharing).

IJCNLP-AACL 2025

The 14th IJCNLP & 4th AACL will be held in Mumbai, India from December 20th to December 24th, 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

We analyze contextual representations in neural autoregressive language models, emphasizing long-range contexts that span several thousand tokens. Our methodology employs a perturbation setup and the metric Anisotropy-Calibrated Cosine Similarity, to capture the degree of contextualization of long-range patterns from the perspective of representation geometry. We begin the analysis with a case study on standard decoder-only Transformers, demonstrating that similar perplexity can exhibit markedly different downstream task performance, which can be explained by the difference in contextualization of long-range content. Next, we extend the analysis to other models, covering recent novel architectural designs and various training configurations. The representation-level results illustrate a reduced capacity for high-complexity (i.e., less compressible) sequences across architectures, and that fully recurrent models rely heavily on local context, whereas hybrid models more effectively encode the entire sequence structure. Finally, preliminary analysis of model size and training configurations on the encoding of long-range context suggest potential directions for improving existing language models.

How much do contextualized representations encode long-range context?

Retrieval-Augmented Generation (RAG) models have drawn considerable attention in modern open-domain question answering. The effectiveness of RAG depends on the quality of the top retrieved documents. However, conventional retrieval methods sometimes fail to rank the most relevant documents at the top. In this paper, we introduce ASRANK, a new re-ranking method based on scoring retrieved documents using zero-shot answer scent which relies on a pre-trained large language model to compute the likelihood of the document-derived answers aligning with the answer scent. Our approach demonstrates marked improvements across several datasets, including NQ, TriviaQA, WebQA, ArchivalQA, HotpotQA, and Entity Questions. Notably, ASRANK increases Top-1 retrieval accuracy on NQ from 19.2% to 46.5% for MSS and 22.1% to 47.3% for BM25. It also shows strong retrieval performance on several datasets compared to state-of-the-art methods (47.3 Top-1 by ASRANK vs 35.4 by UPR by BM25).

ASRank: Zero-Shot Re-Ranking with Answer Scent for Document Retrieval

As safety remains a crucial concern throughout the development lifecycle of Large Language Models (LLMs), researchers and industrial practitioners have increasingly focused on safeguarding and aligning LLM behaviors with human preferences and ethical standards. LLMs, trained on extensive multilingual corpora, exhibit powerful generalization abilities across diverse languages and domains. However, current safety alignment practices predominantly focus on single-language scenarios, which leaves their effectiveness in complex multilingual contexts, especially for those complex mixed-language formats, largely unexplored. In this study, we introduce Multilingual Blending, a mixed-language query-response scheme designed to evaluate the safety alignment of various state-of-the-art LLMs (e.g., GPT-4o, GPT 3.5, Llama3) under sophisticated, multilingual conditions. We further investigate language patterns such as language availability, morphology, and language family that could impact the effectiveness of Multilingual Blending in compromising the safeguards of LLMs. Our experimental results show that, without meticulously crafted prompt templates, Multilingual Blending significantly amplifies the detriment of malicious queries, leading to dramatically increased bypass rates in LLM safety alignment (67.23% on GPT-3.5 and 40.34% on GPT-4o), far exceeding those of single-language baselines. Moreover, the performance of Multilingual Blending varies notably based on intrinsic linguistic properties, with languages of different morphology and from diverse families being more prone to evading safety alignments. These findings underscore the necessity of evaluating LLMs and developing corresponding safety alignment strategies in a complex, multilingual context to align with their superior cross-language generalization capabilities.

Multilingual Blending: Large Language Model Safety Alignment Evaluation with Language Mixture

Large Language Models (LLMs) have recently demonstrated remarkable performance in Text-to-SQL tasks. However, existing research primarily focuses on the optimization of prompts and improvements in workflow, with few studies delving into the exploration of the questions. In this paper, we propose a Text-to-SQL framework based on question classification and multi-agent collaboration (QCMA-SQL). Specifically, we first employ multiple cross-attention mechanisms to train a schema selector to classify questions and select the most suitable database schema. Subsequently, we employ the appropriate agents based on the varying difficulty levels of the questions to generate preliminary SQL queries. Moreover, we implement syntax validation and execution optimization steps to generate final SQL queries. Experimental results on the Spider dataset show that the QCMA-SQL framework achieves an execution accuracy of 87.4%, outperforming state-of-the-art methods. Through ablation studies, we find that classifying the questions ultimately leads to a 2.8% increase in execution accuracy.

Enhancing Text-to-SQL with Question Classification and Multi-Agent Collaboration

Large language models (LLMs) have seen rapid development in recent years, revolutionizing various applications and significantly enhancing convenience and productivity. However, alongside their impressive capabilities, ethical concerns and new types of attacks, such as jailbreaking, have emerged. While most prompting techniques focus on optimizing adversarial inputs for individual cases, resulting in higher computational costs when dealing with large datasets. Less research has addressed the more general setting of training a universal attacker that can transfer to unseen tasks. In this paper, we introduce JUMP, a prompt-based method designed to jailbreak LLMs using universal multi-prompts. We also adapt our approach for defense, which we term DUMP. Experimental results demonstrate that our method for optimizing universal multi-prompts outperforms existing techniques.

Jailbreaking with Universal Multi-Prompts

Recent advancements in generative AI have suggested that by taking visual prompts, GPT-4V can demonstrate significant proficiency in visual recognition tasks. Despite its impressive capabilities, the financial cost associated with GPT-4V's inference presents a substantial barrier to its wide use. To address this challenge, we propose a budget-friendly collage prompting task that collages multiple images into a single visual prompt and makes GPT-4V perform visual recognition on several images simultaneously, thereby reducing the average cost of visual recognition. We present a comprehensive *dataset* of various collage prompts to assess its performance in GPT-4V's visual recognition. Our evaluations reveal several key findings: **1)** Recognition accuracy varies with different positions in the collage. **2)** Grouping images of the same category together leads to better visual recognition results. **3)** Incorrect labels often come from adjacent images. These findings highlight the importance of image arrangement within collage prompt. To this end, we construct a *benchmark* called **CollagePrompt**, which offers a platform for designing collage prompt to achieve more cost-effective visual recognition with GPT-4V. A *baseline* method derived from genetic algorithms to optimize collage layouts is proposed and two *metrics* are introduced to measure the efficiency of the optimized collage prompt. Our benchmark enables researchers to better optimize collage prompts, thus making GPT-4V more cost-effective in visual recognition. The code and data are available at this anonymous link <https://collageprompting.github.io/>.

CollagePrompt: A Benchmark for Budget-Friendly Visual Recognition with GPT-4V

Since the release of ChatGPT, large language models (LLMs) have demonstrated remarkable capabilities across various domains. A key challenge in developing these general capabilities is efficiently sourcing diverse, high-quality data. This becomes especially critical in reasoning-related tasks with sandbox checkers, such as math or code, where the goal is to generate correct solutions to specific problems with higher probability. In this work, we introduce Flaming-hot Initiation with Regular Execution (FIRE) sampling, a simple yet highly effective method to efficiently find good responses. Our empirical findings show that FIRE sampling enhances inference-time generation quality and also benefits training in the alignment stage. Furthermore, we explore how FIRE sampling improves performance by promoting diversity and analyze the impact of employing FIRE at different positions within a response.

Flaming-hot Initiation with Regular Execution Sampling for Large Language Models

Entity matching (EM), which identifies whether two data records refer to the same real-world entity, is crucial for knowledge base construction and enhancing data-driven AI systems. Recent advances in language models (LMs) have shown great potential in resolving entities with rich textual attributes. However, their performance heavily depends on how structured entities are ''talked'' through serialized text. The impact of this serialization process remains underexplored, particularly for entities with complex relations in knowledge graphs (KGs). In this work, we systematically study entity serialization by benchmarking the effect of common schemes with LMs of different sizes on diverse tabular matching datasets. We apply our findings to propose a novel serialization scheme for KG entities based on random walks and utilize LLMs to encode sampled semantic walks for matching. Using this lightweight approach with open-source LLMs, we achieve a leading performance on EM in canonical and highly heterogeneous KGs, demonstrating significant throughput increases and superior robustness compared to GPT-4-based methods. Our study on serialization provides valuable insights for the deployment of LMs in real-world EM tasks.

How to Talk to Language Models: Serialization Strategies for Structured Entity Matching

We present OpenReviewer, an open-source system for generating high-quality peer reviews of machine learning and AI conference papers. At its core is Llama-OpenReviewer-8B, an 8B parameter language model specifically fine-tuned on 79,000 expert reviews from top conferences. Given a PDF paper submission and review template as input, OpenReviewer extracts the full text, including technical content like equations and tables, and generates a structured review following conference-specific guidelines. Our evaluation on 400 test papers shows that OpenReviewer produces considerably more critical and realistic reviews compared to general-purpose LLMs like GPT-4 and Claude-3.5. While other LLMs tend toward overly positive assessments, OpenReviewer's recommendations closely match the distribution of human reviewer ratings. The system provides authors with rapid, constructive feedback to improve their manuscripts before submission, though it is not intended to replace human peer review. OpenReviewer is available as an online demo and open-source tool.

OpenReviewer: A Specialized Large Language Model for Generating Critical Scientific Paper Reviews

Large Language Models (LLMs) have recently demonstrated impressive few-shot learning capabilities through in-context learning (ICL). However, ICL performance is highly dependent on the choice of few-shot demonstrations, making the selection of the most optimal examples a persistent research challenge. This issue is further amplified in low-resource Indic languages, where the scarcity of ground-truth data complicates the selection process. In this work, we propose PromptRefine, a novel Alternating Minimization approach for example selection that improves ICL performance on low-resource Indic languages. PromptRefine leverages auxiliary example banks from related high-resource Indic languages and employs multi-task learning techniques to align language-specific retrievers, enabling effective cross-language retrieval. Additionally, we incorporate diversity in the selected examples to enhance generalization and reduce bias. Through comprehensive evaluations on four text generation tasks—Cross-Lingual Question Answering, Multilingual Question Answering, Machine Translation, and Cross-Lingual Summarization using state-of-the-art LLMs such as LLAMA-3.1-8B, LLAMA-2-7B, Qwen-2-7B, and Qwen-2.5-7B, we demonstrate that PromptRefine significantly outperforms existing frameworks for retrieving examples.

Downloads

Next from NAACL 2025

How much do contextualized representations encode long-range context?

Similar lecture

Are Humans as Brittle as Large Language Models?