Austria

The paradigm of retrieval-augmented generated (RAG) helps mitigate hallucinations of large language models (LLMs). However, RAG also introduces biases contained within the retrieved documents. These biases can be amplified in scenarios which are multilingual and culturally-sensitive, such as territorial disputes. In this paper, we introduce BordIRLines, a benchmark consisting of 720 territorial dispute queries paired with 14k Wikipedia documents across 49 languages. To evaluate LLMs’ cross-lingual robustness for this task, we formalize several modes for multilingual retrieval. Our experiments on several LLMs reveal that retrieving multilingual documents best improves response consistency} and decreases geopolitical bias over using purely in-language documents, showing how incorporating diverse perspectives improves robustness. Also, querying in low-resource languages displays a much wider variance in the linguistic distribution of response citations. Our further experiments and case studies investigate how cross-lingual RAG is affected by aspects from IR to document contents. We release our benchmark and code to support further research towards ensuring equitable information access across languages.

ACL 2025

Multilingual Retrieval Augmented Generation for Culturally-Sensitive Tasks: A Benchmark for Cross-lingual Robustness

retrieval augmented generation

bias and fairness

multilingual nlp

large language models

information retrieval

benchmark

## 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)

The reranker and generator are two critical components in the Retrieval-Augmented Generation (i.e., RAG) pipeline, responsible for ranking relevant documents and generating responses. However, due to differences in pre-training data and objectives, there is an inevitable gap between the documents ranked as relevant by the reranker and those required by the generator to support answering the query. To address this gap, we propose RADIO, a novel and practical preference alignment framework with RAtionale DIstillatiOn. Specifically, We first propose a rationale extraction method that leverages the reasoning capabilities of large language models (LLMs) to extract the rationales necessary for answering the query. Subsequently, a rationale-based alignment process is designed to rerank the documents based on the extracted rationales, and fine-tune the reranker to align the preferences. We conduct extensive experiments on two tasks across three datasets to demonstrate the effectiveness of our approach compared to baseline methods. Our code is released online to ease reproduction.

Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation

We present a taxonomy-driven framework for constructing domain-specific knowledge graphs (KGs) that integrates structured taxonomies, Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). Although we focus on climate science to illustrate its effectiveness, our approach can potentially be adapted for other specialized domains. Existing methods often neglect curated taxonomies—hierarchies of verified entities and relationships—and LLMs frequently struggle to extract KGs in specialized domains. Our approach addresses these gaps by anchoring extraction to expert-curated taxonomies, aligning entities and relations with domain semantics, and validating LLM outputs using RAG against the domain taxonomy. Through a climate science case study using our annotated dataset of 25 publications (1,705 entity-publication links, 3,618 expert-validated relationships), we demonstrate that taxonomy-guided LLM prompting combined with RAG-based validation reduces hallucinations by 23.3\% while improving F1 scores by 13.9\% compared to baselines without the proposed techniques. Our contributions include: 1) a generalizable methodology for taxonomy-aligned KG construction; 2) a reproducible annotation pipeline, 3) the first benchmark dataset for climate science information retrieval; and 4) empirical insights into combining structured taxonomies with LLMs for specialized domains. The dataset, including expert annotations and taxonomy-aligned outputs, is publicly available at \url{https://github.com/Jo-Pan/ClimateIE}, and the accompanying framework can be accessed at \url{https://github.com/Jo-Pan/TaxoDrivenKG}.

Taxonomy-Driven Knowledge Graph Construction for Domain-Specific Scientific Applications

Human trafficking (HT) remains a critical issue, with traffickers increasingly leveraging online escort advertisements to advertise victims anonymously. Existing detection methods, including text-based Authorship Attribution (AA), overlook the multimodal nature of these ads, which combine text and images. To bridge this gap, we introduce MATCHED, a multimodal AA dataset comprising 27,619 unique text descriptions and 55,115 unique images sourced from Backpage across seven U.S. cities in four geographic regions. This study extensively benchmarks text-only, vision-only, and multimodal baselines for vendor identification and verification tasks, employing multitask (joint) training objectives that achieve superior classification and retrieval performance on in-sample and out-of-data distribution datasets. The results demonstrate that while text remains the dominant modality, integrating visual features adds stylistic cues that enrich model performance. Moreover, text-image alignment strategies like CLIP and BLIP2 struggle due to low semantic overlap and vague connections between the modalities of escort ads, with end-to-end multimodal training proving more robust. Our findings emphasize the potential of multimodal AA to combat HT, providing Law Enforcement Agencies with robust tools to link advertisements and disrupt trafficking networks.

MATCHED: Multimodal Authorship-Attribution To Combat Human Trafficking in Escort-Advertisement Data

With the increasing integration of large language models (LLMs) into real-world applications such as finance, e-commerce, and recommendation systems, their susceptibility to misinformation and adversarial manipulation poses significant risks. Existing fraud detection benchmarks primarily focus on single-turn classification tasks, failing to capture the dynamic nature of real-world fraud attempts. To address this gap, we introduce Fraud-R1, a challenging bilingual benchmark designed to assess LLMs' ability to resist fraud and phishing attacks across five key fraud categories: Fraudulent Services, Impersonation, Phishing Scams, Fake Job Postings, and Online Relationships, covering subclasses. Our dataset comprises manually curated fraud cases from social media, news, phishing scam records, and prior fraud datasets.

Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements

High-quality paraphrases are easy to produce using instruction-tuned language models or specialized paraphrasing models. Although this capability has a variety of benign applications, paraphrasing attacks---paraphrases applied to machine-generated texts---are known to significantly degrade the performance of machine-text detectors. This motivates us to consider the novel problem of paraphrase inversion, where, given paraphrased text, the objective is to recover an approximation of the original text. The closer the approximation is to the original text, the better machine-text detectors will perform. We propose an approach which frames the problem as translation from paraphrased text back to the original text, which requires examples of texts and corresponding paraphrases to train the inversion model. Fortunately, such training data can easily be generated, given a corpus of original texts and one or more paraphrasing models. We find that language models such as GPT-4 and Llama-3 exhibit biases when paraphrasing which an inversion model can learn with a modest amount of data. Perhaps surprisingly, we also find that such models generalize well, including to paraphrase models unseen at training time. Finally, we show that when combined with a paraphrased-text detector, our inversion models provide an effective defense against paraphrasing attacks, and overall our approach yields an average improvement of +22% AUROC across seven machine-text detectors and three different domains.

Mitigating Paraphrase Attacks on Machine-Text Detection via Paraphrase Inversion

Language models (LMs) are indispensable tools shaping modern workflows, but their global effectiveness depends on understanding local socio-cultural contexts. To address this, we introduce SANSKRITI, a benchmark designed to evaluate language models' comprehension of India's rich cultural diversity. Comprising of 21,853 meticulously curated question-answer pairs spanning 28 states and 8 union territories, SANSKRITI is the largest dataset for testing Indian cultural knowledge. It covers sixteen key attributes of Indian culture namely rituals and ceremonies, history, tourism, cuisine, dance and music, costume, language, art, festivals, religion, medicine, transport, sports, nightlife and personalities, providing a comprehensive representation of India’s cultural tapestry. We evaluate SANSKRITI on leading Large Language Models (LLMs), Indic Language Models (ILMs), and Small Language Models(SLMs), revealing significant disparities in their ability to handle culturally nuanced queries, with many models struggling in region-specific contexts. By offering an extensive, culturally rich, and diverse dataset, SANSKRITI sets a new standard for assessing and improving the cultural understanding of LMs. We will share the dataset and findings publicly to support research on inclusive and culturally aware AI systems.

SANSKRITI: A Comprehensive Benchmark for Evaluating Language Models’ Knowledge of Indian Culture

Over the past decade, various studies have addressed how speakers solve the so-called `The Paradigm Cell Filling Problem' (PCFP) \citep{ackerman2009parts} across different languages. The PCFP addresses a fundamental question in morphological processing: how do speakers accurately generate inflected forms of words when presented with incomplete paradigms? This problem is particularly salient when modeling complex inflectional systems. We focus on Spanish verbal paradigms, where certain verbs follow an irregular L-shaped pattern, where the first-person singular present indicative stem matches the stem used throughout the present subjunctive mood. We formulate the problem as a morphological reinflection task. Specifically, we investigate the role of input frequency in the acquisition of regular versus irregular L-shaped patterns in transformer models. By systematically manipulating the input distributions and analyzing model behavior, we reveal four key findings: 1) Models perform better on L-shaped verbs compared to regular verbs, especially in uneven frequency conditions; 2) Robust primacy effects are observed, but no consistent recency effects; 3) Memorization becomes more prominent as the proportion of L-shaped verbs increases; 4) There is a tendency to regularize L-shaped verbs when their consonant alternation pairs are rare or absent in the training data.

Frequency matters: Modeling irregular morphological patterns in Spanish with Transformers

Although generically expressing empathy is straightforward, effectively conveying empathy in specialized settings presents nuanced challenges. We present a conceptually motivated investigation into the use of figurative language and causal semantic context to facilitate targeted empathetic response generation within a specific mental health support domain, studying how these factors may be leveraged to promote improved response quality. Our approach achieves a 7.6% improvement in BLEU, a 36.7% reduction in Perplexity, and a 7.6% increase in lexical diversity (D-1 and D-2) compared to models without these signals, and human assessments show a 24.2% increase in empathy ratings. These findings provide deeper insights into grounded empathy understanding and response generation, offering a foundation for future research in this area.

From Heart to Words: Generating Empathetic Responses via Integrated Figurative Language and Semantic Context Signals

Large Language Models (LLMs) have been widely found to struggle with logical reasoning, where even fine-tuned models fail dramatically on out-of-distribution problems. However, existing work has focused on relatively complex ``many-hop'' reasoning problems. In this paper, we analyse the performance of fine-tuned LLMs on simple reasoning problems, all of which can be solved in at most three inference steps. Due to the simplicity of these problems, the model cannot encounter test problems that are fundamentally different from those it has seen during training. Unfortunately, however, we find that the models remain highly brittle, being susceptible to seemingly innocent perturbations, such as the addition of duplicates to the set of premises and shuffling the order in which the premises are presented.

There's No Such Thing as Simple Reasoning for LLMs

Automated definition generation systems have been proposed to support vocabulary expansion for language learners. The main barrier to the success of these systems is that learners often struggle to understand definitions due to the presence of potentially unfamiliar words and grammar, particularly when non-standard language is involved. To address these challenges, we propose CLIX, the task of Cross-Lingual explanations of Idiomatic eXpressions. We explore the capabilities of current NLP models for this task, and observe that while it remains challenging, large language models show promise. Finally, we perform a detailed error analysis to highlight the key challenges that need to be addressed before we can reliably incorporate these systems into educational tools.

Downloads

Next from ACL 2025

Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation

Similar lecture

The Cross-Lingual Cost: Retrieval Biases in RAG over Arabic-English Corpora