Austria

Vertical text input is commonly encountered in various real-world applications, such as mathematical computations and word-based Sudoku puzzles. While current large language models (LLMs) have excelled in natural language tasks, they remain vulnerable to variations in text formatting.Recent research demonstrates that modifying input formats, such as vertically aligning words for encoder-based models, can substantially lower accuracy in text classification tasks. While easily understood by humans, these inputs can significantly mislead models, posing a potential risk of bypassing detection in real-world scenarios involving harmful or sensitive information. With the expanding application of LLMs, a crucial question arises: Do decoder-based LLMs exhibit similar vulnerabilities to vertically formatted text input? In this paper, we investigate the impact of vertical text input on the performance of various LLMs across multiple text classification datasets and analyze the underlying causes. Our findings are as follows: (i) Vertical text input significantly degrades the accuracy of LLMs in text classification tasks. (ii) Chain of Thought (CoT) reasoning does not help LLMs recognize vertical input or mitigate its vulnerability, but \textit{few-shot learning} with careful analysis does. (iii) We explore the underlying cause of the vulnerability by analyzing the inherent issues in tokenization and attention matrices.

ACL 2025

Vulnerability of LLMs to Vertically Aligned Text Manipulations

text format

llms

vulnerability

## 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.

technical paper

### 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**. 

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

This paper introduces Generalized Attention Flow (GAF), a novel feature attribution method for Transformer-based models to address the limitations of current approaches. By extending Attention Flow and replacing attention weights with the generalized Information Tensor, GAF integrates attention weights, their gradients, the maximum flow problem, and the barrier method to enhance the performance of feature attributions. The proposed method exhibits key theoretical properties and mitigates the shortcomings of prior techniques that rely solely on simple aggregation of attention weights. Our comprehensive benchmarking on sequence classification tasks demonstrates that a specific variant of GAF consistently outperforms state-of-the-art feature attribution methods in most evaluation settings, providing a more reliable interpretation of Transformer model outputs.

Generalized Attention Flow: Feature Attribution for Transformer Models via Maximum Flow

Current translation systems, despite being highly multilingual, cover only 5\% of the world's languages. Expanding language coverage to the long-tail of low-resource languages requires data-efficient methods that rely on cross-lingual and cross-modal knowledge transfer. To this end, we propose a character-based approach to improve adaptability to new languages and modalities. Our method leverages SONAR, a multilingual fixed-size embedding space with different modules for encoding and decoding. We use a teacher-student approach with parallel translation data to obtain a character-level encoder. Then, using ASR data, we train a lightweight adapter to connect a massively multilingual CTC ASR model (MMS), to the character-level encoder, potentially enabling speech translation from 1,000+ languages. Experimental results in text translation for 75 languages on FLORES+ demonstrate that our character-based approach can achieve better language transfer than traditional subword-based models, especially outperforming them in low-resource settings, and demonstrating better zero-shot generalizability to unseen languages. Our speech adaptation, maximizing knowledge transfer from the text modality, achieves state-of-the-art results in speech-to-text translation on the FLEURS benchmark on 33 languages, surpassing previous supervised and cascade models, albeit being a zero-shot model with minimal supervision from ASR data.

Improving Language and Modality Transfer in Translation by Character-level Modeling

Large Multimodal Models (LMMs) have demonstrated impressive performance across numerous academic benchmarks. However, fine-tuning still remains essential to achieve satisfactory performance on downstream tasks, while the task-specific tuning samples are usually not readily available or expensive and time-consuming to obtain. To address this, we propose an error-driven data-efficient tuning framework that aims to efficiently adapt generic LMMs to newly emerging tasks without requiring extensive task-specific training samples. In our approach, a generic LMM, acting as a student model, is first evaluated on a small validation set of the target task, and then a more powerful model, acting as a teacher model, identifies the erroneous steps within the student model's reasoning steps and analyzes its capability gaps from fully addressing the target task. Based on these gaps, targeted training samples are further retrieved from existing task-agnostic datasets to tune the student model and tailor it to the target task. We perform extensive experiments across three different training data scales and seven tasks, demonstrating that our training paradigm significantly and efficiently improves LMM's performance on downstream tasks, achieving an average performance boost of 7.01%

Error-driven Data-efficient Large Multimodal Model Tuning

Target-Oriented Dialogue (TOD) remains a significant challenge in the LLM era, where strategic dialogue planning is crucial for directing conversations toward specific targets. However, existing dialogue planning methods generate dialogue plans in a step-by-step sequential manner, and may suffer from compounding errors and myopic actions. To address these limitations, we introduce a novel dialogue planning framework, DiffTOD, which leverages diffusion models to enable non-sequential dialogue planning. DiffTOD formulates dialogue planning as a trajectory generation problem with conditional guidance, and leverages a diffusion language model to estimate the likelihood of the dialogue trajectory. To optimize the dialogue action strategies, DiffTOD introduces three tailored guidance mechanisms for different target types, offering flexible guidance toward diverse TOD targets at test time. Extensive experiments across three diverse TOD settings show that DiffTOD can effectively perform non-myopic lookahead exploration and optimize action strategies over a long horizon through non-sequential dialogue planning, and demonstrates strong flexibility across complex and diverse dialogue scenarios. Our code and data are accessible through https://github.com/ninglab/DiffTOD.

Planning with Diffusion Models for Target-Oriented Dialogue Systems

Large Language Models (LLMs) demonstrate strong abilities in common-sense reasoning and interactive decision-making, but often struggle with complex, long-horizon planning tasks. Recent techniques have sought to structure LLM outputs using control flow and code to improve planning performance. However, code-based approaches can be error-prone and insufficient for handling ambiguous or unstructured data. To address these challenges, we propose REPL-Plan, an LLM planning approach that is fully code-expressive (it can utilize all the benefits of code) while also being dynamic (it can flexibly adapt from errors and use the LLM for soft reasoning). In REPL-Plan, an LLM solves tasks by interacting with a Read-Eval-Print Loop (REPL), which iteratively executes and evaluates code, similar to language shells or interactive code notebooks, allowing the model to flexibly correct errors and handle tasks dynamically. We demonstrate that REPL-Plan achieves strong results across various planning domains compared to previous methods.

Interactive and Expressive Code-Augmented Planning with Large Language Models

Human evaluation is crucial for assessing rapidly evolving language models but is influenced by annotator proficiency and task design. This study explores the integration of comparative judgment into human annotation for machine translation (MT) and evaluates three annotation setups—point-wise Multidimensional Quality Metrics (MQM), side-by-side (S×S) MQM, and its simplified version S×S relative ranking (RR). In MQM, annotators mark error spans with categories and severity levels. S×S MQM extends MQM to pairwise error annotation for two translations of the same input, while S×S RR focuses on selecting the better output without labeling errors.

Key findings are: (1) the S×S settings achieve higher inter-annotator agreement than MQM; (2) S×S MQM enhances inter-translation error marking consistency compared to MQM by, on average, 38.5% for explicitly compared MT systems and 19.5% for others; (3) all annotation settings return stable system rankings, with S×S RR offering a more efficient alternative to (S×S) MQM; (4) the S×S settings highlight subtle errors overlooked in MQM without altering absolute system evaluations.

To spur further research, we will release the triply annotated datasets comprising 377 ZhEn and 104 EnDe annotation examples, each covering 10 systems.

Enhancing Human Evaluation in Machine Translation with Comparative Judgement

As artificial intelligence surpasses human capabilities in text generation, the necessity to authenticate the origins of AI-generated content has become paramount. Unbiased watermarks offer a powerful solution by embedding statistical signals into language model-generated text without distorting the quality. In this paper, we introduce MCmark, a family of unbiased, Multi-Channel-based watermarks. MCmark works by partitioning the model's vocabulary into segments and promoting token probabilities within a selected segment based on a watermark key. We demonstrate that MCmark not only preserves the original distribution of the language model but also offers significant improvements in detectability and robustness over existing unbiased watermarks. Our experiments with widely-used language models demonstrate an improvement in detectability of over 10% using MCmark, compared to existing state-of-the-art unbiased watermarks. This advancement underscores MCmark's potential in enhancing the practical application of watermarking in AI-generated texts.

Improved Unbiased Watermark for Large Language Models

Recently, multimodal large language models (MLLMs) have been extensively explored in video question answering. However, most existing assessments focus on natural videos, overlooking synthetic videos (e.g., AI-generated content). Meanwhile, some works in video generation rely on MLLMs to evaluate the quality of generated videos, but the capabilities of MLLMs on AIGC videos remain largely underexplored. To address this, we propose a new benchmark, VQ-Eval, which introduces four tasks—coherence validation, error awareness, error type detection, and reasoning evaluation—to comprehensively evaluate the abilities of MLLMs on AIGC videos. We evaluate 13 frontier MLLMs on VQ-Eval and find that even the best-performing model, GPT-4.1, struggles to achieve consistently good performance across all tasks. This highlights the challenging nature of our benchmark. Additionally, to investigate the practical applications of VQ-Eval in improving video generation, we design a re-prompt pipeline, demonstrating that aligning MLLMs more closely with human feedback can benefit the video generation.

VQ-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC Videos

Multilingual models often treat language diversity as a problem of data imbalance, overlooking structural variation. We introduce the *Morphological Index* (MoI), a typologically grounded metric that quantifies how strongly a language relies on surface morphology for noun classification. Building on MoI, we propose *MoI-MoE*, a Mixture of Experts model that routes inputs based on morphological structure. Evaluated on 10 Bantu languages—a large, morphologically rich and underrepresented family—MoI-MoE outperforms strong baselines, improving Swahili accuracy by 14 points on noun class recognition while maintaining performance on morphology-rich languages like Zulu. These findings highlight typological structure as a practical and interpretable signal for multilingual model adaptation.

Typology-Guided Adaptation for African NLP

To create culturally inclusive vision-language models (VLMs), developing a benchmark that tests their ability to address culturally relevant questions is essential. Existing approaches typically rely on human annotators, making the process labor-intensive and creating a cognitive burden in generating diverse questions. To address this, we propose a semi-automated framework for constructing cultural VLM benchmarks, specifically targeting multiple-choice QA. This framework combines human-VLM collaboration, where VLMs generate questions based on guidelines, a small set of annotated examples, and relevant knowledge, followed by a verification process by native speakers. We demonstrate the effectiveness of this framework through the creation of K-Viscuit, a dataset focused on Korean culture. Our experiments on this dataset reveal that open-source models lag behind proprietary ones in understanding Korean culture, highlighting key areas for improvement. We also present a series of further analyses, including human evaluation, augmenting VLMs with external knowledge, and the evaluation beyond multiple-choice QA. Our dataset is available at https://huggingface.co/datasets/ddehun/k-viscuit.

Downloads

Next from ACL 2025

Generalized Attention Flow: Feature Attribution for Transformer Models via Maximum Flow

Similar lecture

Text or Pixels? Evaluating Efficiency and Understanding of LLMs with Visual Text Inputs