Austria

Compositionality is a key aspect of human intelligence, essential for reasoning and generalization. While transformer-based models have become the de facto standard for many language modeling tasks, little is known about how they represent compound words, and whether these representations are compositional. In this study, we test compositionality in Mistral, OpenAI Large, and Google embedding models, and compare them with BERT. First, we evaluate compositionality in the representations by examining six diverse models of compositionality (addition, multiplication, dilation, regression, etc.). We find that ridge regression, albeit linear, best accounts for compositionality. Surprisingly, we find that the classic vector addition model performs almost as well as any other model. Next, we verify that most embedding models are highly compositional, while BERT shows much poorer compositionality. We verify and visualize our findings with a synthetic dataset consisting of fully transparent adjective-noun compositions. Overall, we present a thorough investigation of compositionality.

ACL 2025

How do Transformer Embeddings Represent Compositions? A Functional Analysis

phrase/sentence embedding

lexical relationships

lexical resources

lexical semantic change

multi-word expressions

word embeddings

compositionality

It is my great pleasure and honor to welcome you to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), held in San Diego, California, USA, July 2–7, 2026. ACL 2026 continues our fields 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.

It is exciting to see the many developments in the field reflected at our conference, such as the advancement of large language models (born out of our community) into many application directions. This is not without challenges, partly due to unsolved problems, and partly due to misuse of the technology. All this is reflected well at ACL 2026. The conference also reflects that the field is not only about advancing technology, but also the science of fundamentally understanding language and how it is use by many different speaker communities. 
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) 
<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing')">Conference Handbook</button></html>

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 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.aclweb.org/registration/) first.

Registration Required

ACL 2026

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

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 retriever, which retrieves relevant knowledge pieces from a knowledge base given a context, is an important component in many natural language processing (NLP) tasks. Recently, retrievers have been introduced in knowledge-grounded dialog systems to improve knowledge acquisition. In knowledge-grounded dialog systems, when conditioning on a given context, there may be multiple relevant and correlated knowledge pieces. However, knowledge pieces are usually assumed to be conditionally independent in current retriever models. To address this issue, we propose Entriever, an energy-based retriever. The Entriever directly models the candidate retrieval results as a whole instead of modeling the knowledge pieces separately, with the relevance score defined by an energy function. We explore various architectures of energy functions and different training methods for Entriever, and show that Entriever substantially outperforms the strong cross-encoder baseline in knowledge retrieval tasks. Furthermore, we show that in semi-supervised training of knowledge-grounded dialog systems, Entriever enables the effective scoring of retrieved knowledge pieces and leads to a significant improvement in the end-to-end performance of the dialog system.

Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems

Discourse particles are crucial elements that subtly shape the meaning of text. These words, often polyfunctional, give rise to nuanced and often quite disparate semantic/discourse effects,
as exemplified by the diverse uses of the particle *just* (e.g., exclusive, temporal, emphatic). 
This work investigates the capacity of LLMs to distinguish the fine-grained senses of English *just*, a well-studied example in formal semantics, using data meticulously created and labeled by expert linguists. Our findings reveal that while LLMs exhibit some ability to differentiate between broader categories, they struggle to fully capture more subtle nuances, highlighting a gap in their understanding of discourse particles.

Is It JUST Semantics? A Case Study of Discourse Particle Understanding in LLMs

Recent advances in table understanding have focused on instruction-tuning large language models (LLMs) for table-related tasks. However, existing research has overlooked the impact of hyperparameter choices and lacks a comprehensive evaluation of the out-of-domain table understanding ability and the general capabilities of these table LLMs. In this paper, we evaluate these abilities in existing table LLMs, and reveal significant declines in both out-of-domain table understanding and general capabilities compared to their base models. Through systematic analysis, we show that hyperparameters, such as learning rate, can significantly influence both table-specific and general capabilities. Contrary to the existing table instruction-tuning works, we demonstrate that smaller learning rates and fewer training instances can enhance table understanding while preserving general capabilities. Based on our findings, we introduce TAMA, a TAble LLM instruction-tuned from LLaMA 3.1 8B Instruct, which achieves performance on par with, or surpassing GPT-3.5 and GPT-4 on table tasks, while maintaining strong out-of-domain generalization and general capabilities. Our findings highlight the potential for reduced data annotation costs and more efficient model development through careful hyperparameter selection.

Rethinking Table Instruction Tuning

In clinical operations, teamwork can be the crucial factor that determines the final outcome. Prior studies have shown that sufficient collaboration is the key factor that determines the outcome of an operation. To understand how the team practices teamwork during the operation, we collected CliniDial from simulations of medical operations. CliniDial includes the audio data and its transcriptions, the simulated physiology signals of the patient manikins, and how the team operates from two camera angles. We annotate behavior codes following an existing framework to understand the teamwork process for CliniDial. We pinpoint three main characteristics of our dataset, including its label imbalances, rich and natural interactions, and multiple modalities, and conduct experiments to test existing LLMs' capabilities on handling data with these characteristics. Experimental results show that CliniDial poses significant challenges to the existing models, inviting future effort on developing domain-specific models that can deal with real-world clinical data.

CliniDial: A Naturally Emerged Multimodal Dialogue Dataset for Team Reflection During Clinical Operation

This study explores the potential of phonological reasoning within text-based large language models (LLMs). Utilizing the PhonologyBench benchmark, we assess tasks like rhyme generation, grapheme-to-phoneme conversion, and syllable counting. Our evaluations across 12 LLMs reveal that while few-shot learning offers inconsistent gains, the introduction of a novel Pedagogical Chain-of-Thought (P-CoT) prompts, which is anchored in educational theories like scaffolding and discovery learning consistently enhances performance. This method leverages structured guidance to activate latent phonological abilities, achieving up to 52% improvement and even surpassing human baselines in certain tasks. Future work could aim to optimize P-CoT prompts for specific models or explore their application across different linguistic domains.

P-CoT: A Pedagogically-motivated Participatory Chain-of-Thought Prompting for Phonological Reasoning in LLMs

Dialectal Arabic (DA) varieties are underserved by language technologies, particularly large language models (LLMs). This trend threatens to exacerbate existing social inequalities and limits language modeling applications, yet the research community lacks operationalized LLM performance measurements in DA. We present a method that comprehensively evaluates LLM fidelity, understanding, quality, and diglossia in modeling DA. We evaluate nine LLMs in eight DA varieties across these four dimensions and provide best practice recommendations. Our evaluation suggests that LLMs do not produce DA as well as they understand it, but does not suggest deterioration in quality when they do. Further analysis suggests that current post-training can degrade DA capabilities, that few-shot examples can overcome this and other LLM deficiencies, and that otherwise no measurable features of input text correlate well with LLM DA performance.

AL-QASIDA: Analyzing LLM Quality and Accuracy Systematically in Dialectal Arabic

As a cornerstone in language modeling, tokenization involves segmenting text inputs into pre-defined atomic units. Conventional statistical tokenizers often disrupt constituent boundaries within words, thereby corrupting semantic information. To address this drawback, we introduce morphological structure guidance to tokenization and propose a deep model to induce character-level structures of words. Specifically, the deep model jointly encodes internal structures and representations of words with a mechanism named MorphOverriding to ensure the indecomposability of morphemes. By training the model with self-supervised objectives, our method is capable of inducing character-level structures that align with morphological rules without annotated training data. Based on the induced structures, our algorithm tokenizes words through vocabulary matching in a top-down manner. Empirical results indicate that the proposed method effectively retains complete morphemes and outperforms widely adopted methods such as BPE and WordPiece on both morphological segmentation tasks and language modeling tasks. The code will be released upon acceptance.

Unsupervised Morphological Tree Tokenizer

Common subword tokenization algorithms like BPE and UnigramLM assume that text can be split into meaningful units by concatenative measures alone. This is not true for languages such as Hebrew and Arabic, where morphology is encoded in root-template patterns, or Malay and Georgian, where split affixes are common. We present SPLINTER, a pre-processing step which rearranges text into a linear form that better represents such nonconcatenative morphologies, enabling meaningful contiguous segments to be found by the tokenizer. We demonstrate SPLINTER's merit using both intrinsic measures evaluating token vocabularies in Hebrew, Arabic, and Malay; as well as on downstream tasks using BERT-architecture models trained for Hebrew.

Splintering Nonconcatenative Languages for Better Tokenization

Recent progress in developing general-purpose text embedders has been driven by training on synthetic LLM-generated data. Nonetheless, no publicly available synthetic data exists, posing a barrier to studying its role for the generalization of embedding models. To address this issue, we first reproduce and publicly release the synthetic data proposed by Wang et al. (2024) (Mistral-E5). Our synthetic data is high quality and leads to consistent improvements in performance. Next, we critically examine where exactly synthetic data improves model generalization. Our analysis reveals that benefits from synthetic data are sparse and highly localized to individual datasets. Moreover, we observe trade-offs between the performance on different categories and data that benefits one task, degrades performance on another. Our findings highlight the limitations of current synthetic data approaches for building general-purpose embedders and challenge the notion that training on synthetic data leads to more robust embedding models across tasks.

Understanding the Influence of Synthetic Data for Text Embedders

This paper investigates the role of dynamic external knowledge integration in improving counter-argument generation using Large Language Models (LLMs). While LLMs have shown promise in argumentative tasks, their tendency to generate lengthy, potentially unfactual responses highlights the need for more controlled and evidence-based approaches. We introduce a new manually curated dataset of argument and counter-argument pairs specifically designed to balance argumentative complexity with evaluative feasibility. We also propose a new LLM-as-a-Judge evaluation methodology that shows a stronger correlation with human judgments compared to traditional reference-based metrics. Our experimental results demonstrate that integrating dynamic external knowledge from the web significantly improves the quality of generated counter-arguments, particularly in terms of relatedness, persuasiveness, and factuality. The findings suggest that combining LLMs with real-time external knowledge retrieval offers a promising direction for developing more effective and reliable counter-argumentation systems. Data and code are publicly available.

Downloads

Next from ACL 2025

Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems

Similar lecture

Investigating More Explainable and Partition-Free Compositionality Estimation for LLMs: A Rule-Generation Perspective