Austria

As large language models (LLMs) are increasingly deployed across diverse linguistic and cultural contexts, understanding their behavior in both factual and disputable scenarios is essential—especially when their outputs may shape public opinion or reinforce dominant narratives. This study investigates two types of bias in LLMs: model bias (bias stemming from model training) and inference bias (bias induced by the language of the query), through a two-phase evaluation. 
The first phase evaluates LLMs on factual questions where a single verifiable answer exists, assessing whether models maintain consistency across different query languages. The second phase expands the scope by probing geopolitically sensitive disputes, where responses may reflect culturally embedded or ideologically aligned perspectives. We construct a manually curated dataset spanning both factual and disputable QA, across four languages and question types. Our findings show that while Phase 1 reveals primarily language-induced alignment, Phase 2 reveals entangled effects of both language and model training. This study offers a structured framework for evaluating LLM behavior across neutral and sensitive topics, providing insights for future LLM deployment and culturally-aware evaluation practices in multilingual contexts.

ACL 2025

A Dual-Layered Evaluation of Geopolitical and Cultural Bias in LLMs

inference bias

geopolitical disputes

cultural

multilingual evaluation

model bias

large language models

bias

## 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.

workshop 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)

Search engines increasingly use large language models (LLMs) to generate direct answers, while AI chatbots retrieve updated information from the
Internet. As information curators for billions of users, LLMs must evaluate the accuracy and reliability of sources. This study audits nine LLMs
from OpenAI, Google, and Meta to assess their ability to evaluate the credibility and quality of the top 20 most popular Bangladeshi news outlets.
While LLMs rate most tested outlets, larger models more often refuse to rate sources due to insufficient information, while smaller models are
prone to hallucinations. When ratings are provided, LLMs show strong internal consistency with an average correlation coefficient (𝜌) of 0.72, but
their alignment with human expert evaluations is moderate, with an average 𝜌 of 0.45. We introduce a dataset of expert opinions (journalism and
media studies students) on the credibility and political bias of Bangladeshi news outlets to evaluate LLMs’ political bias and credibility assessments.
Our analysis reveals that LLMs in default configurations favor the Bangladesh Awami League-affiliated sources in credibility ratings. Assigning
partisan identities to LLMs further amplifies politically congruent biases in their assessments. These findings highlight the need to address political
bias and improve credibility evaluations as LLMs increasingly shape how news and political information are curated worldwide.

Evaluating Credibility and Political Bias in LLMs for News Outlets in Bangladesh

Chinese idioms (成语, Chengyu) are concise four-character expressions steeped in history and culture, whose literal translations often fail to capture their full meaning. This complexity makes them challenging for language models to interpret and use correctly. Existing benchmarks focus on narrow tasks—multiple-choice cloze tests, isolated translation, or simple paraphrasing. We introduce CHENGYU-BENCH, a comprehensive benchmark featuring three tasks: (1) Evaluative Connotation, classifying idioms as positive or negative; (2) Appropriateness, detecting incorrect idiom usage in context; and (3) Open Cloze, filling blanks in longer passages without options. CHENGYU-BENCH comprises 2,937 human-verified examples covering 1,765 common idioms sourced from diverse corpora. We evaluate leading LLMs and find they achieve over 95\% accuracy on Evaluative Connotation, but only ~85% on Appropriateness and ~40% top-1 accuracy in Open Cloze. Error analysis reveals that most mistakes arise from fundamental misunderstandings of idiom meanings. CHENGYU-BENCH demonstrates that while LLMs can reliably gauge idiom sentiment, they still struggle to grasp the cultural and contextual nuances essential for proper usage. The benchmark and code will be released upon paper acceptance.

CHENGYU-BENCH: Benchmarking Large Language Models for Chinese Idiom Understanding and Use

While large language models (LLMs) have demonstrated impressive capabilities across diverse tasks, their ability to generate valid graph structures remains underexplored. We evaluate fifteen state-of-the-art LLMs on five specialized graph generation tasks spanning delivery networks, social networks, quantum circuits, gene-disease networks, and transportation systems. We also test the LLMs using 3 different prompt types: direct, iterative feedback, and program-augmented. Models supported with explicit reasoning modules (o3-mini-high, o1, Claude 3.7 Sonnet, DeepSeek-R1) solve more than twice as many tasks as their general-purpose peers, independent of parameter count. Error forensics reveals two recurring failure modes: Llama-family models often violate basic structural constraints, whereas Claude models respect topology but mismanage higher-order logical rules. Allowing models to iteratively refine their answers yields uneven gains, underscoring fundamental differences in error-correction capacity. This work demonstrates that graph competence stems from specialized architectural design rather than scale, establishing a framework for developing truly graph-savvy language models. Results and verification scripts available at https://github.com/anonymized-for-the-blind-review.

Are LLMs Truly Graph-Savvy? A Comprehensive Evaluation of Graph Generation

This paper quantifies the "embodiment gap" between disembodied language models and embodied agricultural knowledge communication through mixed-methods analysis with 78 farmers. Our key contributions include: (1) the Embodied Knowledge Representation Framework (EKRF), a novel computational architecture with specialized lexical mapping that incorporates embodied linguistic patterns from five identified domains of agricultural expertise; (2) the Embodied Prompt Engineering Protocol (EPEP), which reduced the embodiment gap by 47.3\% through systematic linguistic scaffolding techniques; and (3) the Embodied Knowledge Representation Index (EKRI), a new metric for evaluating embodied knowledge representation in language models. Implementation results show substantial improvements across agricultural domains, with particularly strong gains in tool usage discourse (58.7\%) and soil assessment terminology (67\% reduction in embodiment gap). This research advances both theoretical understanding of embodied cognition in AI and practical methodologies to enhance LLM performance in domains requiring embodied expertise.

Bridging the Embodiment Gap in Agricultural Knowledge Representation for Language Models

Effective communication of health information requires adapting complexity to match the target audience's literacy level. However, manually simplifying medical content is both time-consuming and difficult to scale. To address this challenge, we developed a new framework for automatically generating health answers at multiple complexity levels.

We began by collecting 166 linguistic features to quantify text complexity, including traditional readability metrics (e.g., Flesch-Kincaid, SMOG), medical terminology usage (e.g., UMLS coverage, medical entity recognition), syntactic complexity, semantic coherence, and LLM-based measures (e.g., masked language modeling, LLM-as-a-judge). Applying these features to a custom dataset of parallel health texts and external medical benchmarks, we used feature selection to identify 13 key metrics that reliably distinguish between simple and complex text pairs. From these, we derived a complexity scoring formula by combining the metrics with weights learned from a logistic regression model.

Using this formula, we created a large multi-level dataset of health question-answer pairs, ranging from elementary patient-friendly explanations to advanced technical summaries.
The initial QA pairs came from established datasets including LiveQA, MedicationQA, and MEDIQA-AnS. We then used LLaMA-based language models with carefully engineered prompts to transform the original answers into five different versions ordered by complexity.
Finally, we fine-tuned a large language model on this dataset, incorporating special tokens to control the complexity of the generated text. The resulting model can generate health answers at fine-grained complexity levels, allowing users to select the desired level of detail and technicality.

A Framework for Fine-Grained Complexity Control in Health Answer Generation

This paper represents an implementation of an approach rather similar to that of (Zhu et al., 2024), but for the Russian-language data. We introduce a RusConText Benchmark for evaluating short context understanding in Russian, comprising four distinct yet interrelated tasks: ellipsis resolution, coreference resolution, and idiom interpretation, and discourse understanding. Each task targets a specific aspect of linguistic processing, challenging large language model to recover omitted information, resolve referential dependencies, interpret idioms and discourse. RusConText Benchmark serves as an additional resource beyond standard benchmarks, designed to assess model performance from a specific perspective. In addition, we present the results of scoring 4 models on our benchmark.

RusConText Benchmark: A Russian Language Evaluation Benchmark for Understanding Context

Neural topic modeling is a scalable automated technique for text data mining. In various downstream tasks of topic modeling, it is prefered that the discovered topics well align with labels. However, due to the lack of guidance from labels, unsupervised neural topic models are less powerful in this situation. Existing supervised neural topic models often adopt a label-free prior to generate the latent document-topic distributions and use them to predict the labels and thus achieve label-topic alignment indirectly. Such a mechanism faces the following issues: 1) The label-free prior leads to topics blending the latent patterns of multiple labels; 2) One is unable to intuitively identify the explicit relationships between labels and the discovered topics. To tackle these problems, we develop a novel supervised neural topic model which utilizes a chain-structured graphical model that emphasizes direct constraints of labels on topics. Soft indicators are introduced to explicitly construct the label-topic relationships. To obtain well-organized label-topic relationships, we formalize an entropy-regularized optimal transport problem on the embedding space and model them as the transport plan. Moreover, our proposed method can be seamlessly integrated with most existing unsupervised neural topic models in a flexible manner. Experiment results on multiple datasets demonstrate that our model can greatly enhance the alignment between labels and topics while maintaining good topic quality.

Supervised Neural Topic Modeling with Label Alignment

Amidst the rapid advancement of artificial intelligence, research on large vision-language models (LVLMs) has emerged as a pivotal area. However, understanding their internal mechanisms remains challenging due to the limitations of existing interpretability methods, especially regarding faithfulness and plausibility. To address this, we first construct a human response interpretability dataset that evaluates the plausibility of model explanations by comparing the attention regions between the model and humans when answering the same questions. We then propose a patchwise cooperative game-based interpretability method for LVLMs, which employs Shapley values to quantify the impact of individual image patches on generation likelihood and enhances computational efficiency through a single input approximation approach. Experimental results demonstrate our method's faithfulness, plausibility, and robustness. Our method provides researchers with deeper insights into model behavior, allowing for an examination of the specific image regions each layer relies on during response generation, ultimately enhancing model reliability. Our codes are available at https://github.com/ZY123-GOOD/Patchwise_Cooperative.

Patchwise Cooperative Game-based Interpretability Method for Large Vision-Language Models

We propose the Data Contamination Quiz (DCQ), a simple and effective approach to detect data contamination in large language models (LLMs) and estimate the amount of it. Specifically, we frame data contamination detection as a series of multiple-choice questions, devising a quiz format wherein three perturbed versions of each instance, subsampled from a specific dataset partition, are created. These changes only include word-level perturbations. The generated perturbations, along with the original dataset instance, form the options in the DCQ, with an extra option accommodating the selection of none of the provided options. Given that the only distinguishing signal among the options is the exact wording with respect to the original dataset instance, an LLM, when tasked with identifying the original dataset instance, gravitates towards selecting the original one if it has been exposed to it. While accounting for positional biases in LLMs, the quiz performance reveals the contamination level for the tested model with the dataset partition to which the quiz pertains. Applied to various datasets and LLMs, under controlled and uncontrolled contamination, our findings—while fully lacking access to training data and model parameters—suggest that DCQ achieves state-of-the-art results and uncovers greater contamination/memorization levels compared to existing methods. Also, it proficiently bypasses more safety filters, especially those set to avoid generating copyrighted content.

Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models

Adversarial examples pose a significant challenge to deep neural networks across both image and text domains, with the intent to degrade model performance through carefully altered inputs. Adversarial texts, however, are distinct from adversarial images due to their requirement for semantic similarity and the discrete nature of the textual contents. This study delves into the concept of human suspiciousness, a quality distinct from the traditional focus on imperceptibility found in image-based adversarial examples, where adversarial changes are often desired to be indistinguishable to the human eye even when placed side by side with originals. Although this is generally not possible with text, textual adversarial content must still often remain undetected or non-suspicious to human readers. Even when the text’s purpose is to deceive NLP systems or bypass filters, the text is often expected to be natural to read. In this research, we expand the study of human suspiciousness by analyzing how individuals perceive adversarial texts. We gather and publish a novel dataset of Likert-scale human evaluations on the suspiciousness of adversarial sentences, crafted by four widely used adversarial attack methods and assess their correlation with the human ability to detect machine-generated alterations. Additionally, we develop a regression-based model to predict levels of suspiciousness and establish a baseline for future research in reducing the suspiciousness in adversarial text generation. We also demonstrate how the regressor-generated suspicious scores can be incorporated into adversarial generation methods to produce texts that are less likely to be perceived as computer-generated.

Downloads

Next from ACL 2025

Evaluating Credibility and Political Bias in LLMs for News Outlets in Bangladesh

Similar lecture

Social Bias in Multilingual Language Models: A Survey