Austria

The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined — such attacks can be achieved by embedding malicious behaviors during training and activated under specific conditions that trigger malicious outputs. Despite the increasing support for multilingual capabilities in open-source and proprietary LLMs, the impact of backdoor attacks on these systems remains largely under-explored. Our research focuses on crosslingual backdoor attacks against multilingual LLMs, particularly investigating how poisoning the instruction-tuning data for one or two languages can affect the outputs for languages whose instruction-tuning data was not poisoned. Despite its simplicity, our empirical analysis reveals that our method exhibits remarkable efficacy in models like BLOOM and GPT-4o, with high attack success rates, surpassing 90% in more than 7 out of 12 languages across various scenarios. Our findings also indicate that more powerful models show increased susceptibility to transferable cross-lingual backdoor attacks, which also applies to LLMs predominantly pre-trained on English data, such as Llama2, Llama3, and Gemma. Moreover, our experiments demonstrate the high transferability of the proposed attack: 1) the backdoor mechanism successfully operates in cross-lingual response scenarios across 26 languages, achieving an average attack success rate of 99%, and 2) the proposed attack remains effective even after defenses are applied. These findings expose critical security vulnerabilities in multilingual LLMs and highlight the urgent need for more robust, targeted defense strategies to address the unique challenges posed by cross-lingual backdoor transfer.

ACL 2025

TUBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning

instruction tuning

backdoor attacks

cross-lingual transfer

## 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 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)

Retrieval-augmented generation (RAG) in Knowledge Graph Question Answering (KGQA) enhances the context of Large Language Models (LLMs) by incorporating information retrieved from the Knowledge Graph (KG). Most recent approaches rely on costly LLM calls to generate executable relation paths or traverse the KG, which is inefficient in complex KGQA tasks, such as those involving multi-hop or multi-entity questions. We introduce the GNN-RAG framework, which utilizes lightweight Graph Neural Networks (GNNs) for effective and efficient graph retrieval. The GNN learns to assign importance weights to nodes based on their relevance to the question, as well as the relevance of their neighboring nodes. This enables the framework to effectively handle context from deeper parts of the graph, improving retrieval performance. GNN-RAG retrieves the shortest paths connecting question entities to GNN answer candidates, providing this information as context for the LLM. Experimental results show that GNN-RAG achieves effective retrieval on two widely used KGQA benchmarks (WebQSP and CWQ), outperforming or matching GPT-4 performance with a 7B tuned LLM. Additionally, GNN-RAG excels on multi-hop and multi-entity questions outperforming LLM-based retrieval approaches by 8.9--15.5% points at answer F1. Furthermore, it surpasses long-context inference while using 9x fewer KG tokens.

GNN-RAG: Graph Neural Retrieval for Efficient Large Language Model Reasoning on Knowledge Graphs

Large Language Models (LLMs) suffer from hallucinations and outdated knowledge due to their reliance on static training data. Retrieval-Augmented Generation (RAG) mitigates these issues by integrating external dynamic information for improved factual grounding. With advances in multimodal learning, Multimodal RAG extends this approach by incorporating multiple modalities such as text, images, audio, and video to enhance the generated outputs. However, cross-modal alignment and reasoning introduce challenges beyond those in unimodal RAG. This survey offers a structured and comprehensive analysis of Multimodal RAG systems, covering datasets, benchmarks, metrics, evaluation, methodologies, and innovations in retrieval, fusion, augmentation, and generation. We precisely review training strategies, robustness enhancements, and loss functions, while also exploring the diverse Multimodal RAG scenarios. In addition, we outline open challenges and future directions to guide research in this evolving field. This survey lays the foundation for developing more reliable AI systems that effectively leverage multimodal dynamic external knowledge bases. To support further research, all resources are publicly available.

Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation

The remarkable understanding and generation capabilities of large language models (LLMs) have greatly improved translation performance. However, incorrect understanding of the sentence to be translated can degrade translation quality. To address this issue, we proposed a novel Iterative Bilingual Understanding Translation (IBUT) method based on the cross-lingual capabilities of LLMs and the dual characteristics of translation tasks. The cross-lingual capability of LLMs enables the generation of contextual understanding for both the source and target languages separately. Furthermore, the dual characteristics allow IBUT to generate effective cross-lingual feedback, iteratively refining contextual understanding, thereby reducing errors and improving translation performance. Experimental results showed that the proposed IBUT outperforms several strong comparison methods, especially being generalized to multiple domains (e.g., news, commonsense, and cultural translation benchmarks).

LLM-based Translation Inference with Iterative Bilingual Understanding

Word Sense Induction is beneficial for linguistic studies, and for semantic-intensive NLP applications in low computation resources scenarios, not benefiting of LLMs. In this paper, we emphasize methodological problems in current WSI evaluation. We propose an evaluation on a SemCor-derived dataset, respecting the original corpus polysemy and frequency distributions. We assess pre-trained embeddings and clustering algorithms across parts of speech, and propose and evaluate an LLM-based WSI method for English. We evaluate data augmentation sources (LLM-generated, corpus and lexicon), and semi-supervised scenarios using Wiktionary for data augmentation, must-link constraints, number of clusters per lemma.

We find that no unsupervised method (whether ours or previous) surpasses the strong "one cluster per lemma" heuristic (1cpl). We also show that (i) results and best systems may vary across POS, (ii) LLMs have troubles performing this task, (iii) data augmentation is beneficial and (iv) capitalizing on Wiktionary does help. It surpasses previous SoTA system on our test set by 3.3%. WSI is not solved, and calls for a better articulation of lexicons and LLMs' lexical semantics capabilities.

In the LLM era, Word Sense Induction remains unsolved

This paper investigates the effect of dialectal prompting, variations in prompting scrip t and model fine-tuning on subjective classification in Arabic dialects. To this end, we evaluate the performances of 12 widely used open LLMs across four tasks and eight benchmark datasets. Our results reveal that specialized fine-tuned models with Arabic and Arabizi scripts dialectal prompts achieve the best results, which constitutes a novel state of the art in the field.

Are Dialects Better Prompters? A Case Study on Arabic Subjective Text Classification

Though online medical literature has made health information more available than ever, the barrier of complex medical jargon prevents the general public from understanding it. Though parallel and comparable corpora for Biomedical Text Simplification have been introduced, these conflate the many syntactic and lexical operations involved in simplification. To enable more targeted development and evaluation, we present a fine-grained lexical simplification task and dataset, Jargon Explanations for Biomedical Simplification (JEBS). The JEBS task involves identifying complex terms, classifying how to replace them, and generating replacement text. The JEBS dataset contains 21,595 replacements for 10,314 terms across 400 biomedical abstracts and their manually simplified versions. Additionally, we provide baseline results for a variety of rule-based and transformer-based systems for the three subtasks. The JEBS task, data, and baseline results pave the way for development and rigorous evaluation of systems for replacing or explaining complex biomedical terms.

JEBS: A Fine-grained Biomedical Lexical Simplification Task

Translation-based strategies for cross-lingual transfer XLT such as translate-train---training on noisy target language data translated from the source language---and translate-test---evaluating on noisy source language data translated from the target language---are competitive XLT baselines. In XLT for token classification tasks, however, these strategies include label projection, the challenging step of mapping the labels from each token in the original sentence to its counterpart(s) in the translation. Although word aligners (WAs) are commonly used for label projection, the low-level design decisions for applying them to translation-based XLT have not been systematically investigated. Moreover, recent marker-based methods, which project labeled spans by inserting tags around them before (or after) translation, claim to outperform WAs in label projection for XLT. In this work, we revisit WAs for label projection, systematically investigating the effects of low-level design decisions on token-level XLT: (i) the algorithm for projecting labels between (multi-)token spans, (ii) filtering strategies to reduce the number of noisily mapped labels, and (iii) the pre-tokenization of the translated sentences. We find that all of these substantially impact translation-based XLT performance and show that, with optimized choices, XLT with WA offers performance at least comparable to that of marker-based methods. We then introduce a new projection strategy that ensembles translate-train and translate-test predictions and demonstrate that it substantially outperforms the marker-based projection. Crucially, we show that our proposed ensembling also reduces sensitivity to low-level WA design choices, resulting in more robust XLT for token classification tasks.

The Devil Is in the Word Alignment Details: On Translation-Based Cross-Lingual Transfer for Token Classification Tasks

Russenorsk, a pidgin language historically used in trade interactions between Russian and Norwegian speakers, represents a unique linguistic phenomenon. In this article, we attempt to analyze its lexicon using modern large language models (LLMs), based on surviving literary sources. We construct a structured dictionary of the language, grouped by synonyms and word origins. Subsequently, we use this dictionary to formulate hypotheses about the core principles of word formation in Russenorsk and show which the hypotheses generated by large language model correspond with the hypotheses previously proposed in the academic literature. We also develop a "reconstruction" translation agent that generates plausible translations into Russenorsk.

Smotrom tvoja på ander drogoj verden! Resurrecting Dead Pidgin with Generative Models: Russenorsk Case Study

Despite recent advancements in automatic summarization, state-of-the-art models do not summarize all documents equally well, raising the question: why? While prior research has extensively analyzed summarization models, little attention has been given to the role of document characteristics in influencing summarization performance.
In this work, we explore two key research questions. First, do documents exhibit consistent summarization quality across multiple systems? If so, can we predict a document's summarization performance without generating a summary? We answer both questions affirmatively and introduce PreSumm, a novel task in which a system predicts summarization performance based solely on the source document. Our analysis sheds light on common properties of documents with low PreSumm scores, revealing that they often suffer from coherence issues, complex content, or a lack of a clear main theme.
In addition, we demonstrate PreSumm's practical utility in two key applications: improving hybrid summarization workflows by identifying documents that require manual summarization and enhancing dataset quality by filtering outliers and noisy documents.
Overall, our findings highlight the critical role of document properties in summarization performance and offer insights into the limitations of current systems that could serve as the basis for future improvements.

PreSumm: Predicting Summarization Performance Without Summarizing

One of the most widely used tasks to evaluate Large Language Models (LLMs) is Multiple-Choice Question Answering (MCQA). While open-ended question answering tasks are more challenging to evaluate, MCQA tasks are, in principle, easier to assess, as the model's answer is thought to be simple to extract and is directly compared to a set of predefined choices. However, recent studies have started to question the reliability of MCQA evaluation, showing that multiple factors can significantly impact the reported performance of LLMs, especially when the model generates free-form text before selecting one of the answer choices. In this work, we shed light on the inconsistencies of MCQA evaluation strategies, which can lead to inaccurate and misleading model comparisons. We systematically analyze whether existing answer extraction methods are aligned with human judgment, and how they are influenced by answer constraints in the prompt across different domains. Our experiments demonstrate that traditional evaluation strategies often underestimate LLM capabilities, while LLM-based answer extractors are prone to systematic errors. Moreover, we reveal a fundamental trade-off between including format constraints in the prompt to simplify answer extraction and allowing models to generate free-form text to improve reasoning. Our findings call for standardized evaluation methodologies and highlight the need for more reliable and consistent MCQA evaluation practices.

Downloads

Next from ACL 2025

GNN-RAG: Graph Neural Retrieval for Efficient Large Language Model Reasoning on Knowledge Graphs

Similar lecture

Forget the Unneeded: Backdooring Large Language Models via Contrastive-enhanced Machine Unlearning