Austria

In this paper, we evaluate the capacity of current language technologies to understand Basque and Spanish language varieties. We use NLI as a pivot task and introduce a novel, manually-curated parallel dataset in Basque and Spanish and their corresponding variants. Empirical analysis of comprehensive crosslingual and in-context learning experiments with respectively, encoder-only and decoder-based Large Language Models (LLMs), reveals a performance drop when processing linguistic variations, with more pronounced effects observed in Basque. Error analysis indicates that lexical overlap plays no role, suggesting that linguistic variation represents the primary reason for the lower results. All data and code are publicly available under Attribution-NonCommercial 4.0 International license.

ACL 2025

Lost in Variation? Evaluating NLI Performance in Basque and Spanish Geographical Variants

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING 2020

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

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)

In sentences such as John began the book, the complement noun, lexically denoting an entity, is interpreted as an event. This phenomenon is known in linguistics as complement coercion: the event associated with the verb is not overtly expressed but can be recovered from the meanings of other constituents, context and world knowledge. We investigate whether language models (LMs) can exploit sentence structure and compositional meaning to recover plausible events in complement coercion. For the first time, we tested different LMs in Norwegian, a low-resource language with high syntactic variation in coercion constructions across aspectual verbs. Results reveal that LMs struggle with retrieving plausible events and with ranking them above less plausible ones. Moreover, we found that LMs do not exploit the compositional properties of coercion sentences in their predictions.

Compositionality and Event Retrieval in Complement Coercion: A Study of Language Models in a Low-resource Setting

Knowing which words language learners struggle with is crucial for developing personalised education technologies. In this paper, we advocate for the novel task of "dictionary look-up predication" as a means for evaluating the complexity of words in reading tasks. We release the Dictionary Look-Up development dataset (DLU-dev) and the Dialogue Dictionary Look-Up dataset (D-DLU), which is based on chatbot dialogues. We demonstrate that dictionary look-up is a challenging task for LLMs (results are presented for LLaMA, Gemma and Longformer models). We explore finetuning with the ROC* loss function as a more appropriate loss for this task than the commonly used Binary Cross Entropy (BCE). We investigate the transfer between DLU and the related tasks of Complex Word Identification (CWI) and Semantic Error Prediction (SEP); establishing new state-of-the-art results for SEP.

DLU: Dictionary Look-Up Data and Prediction

Recent work has investigated whether extant neural language models (LMs) have an inbuilt inductive bias towards the acquisition of attested typologically-frequent grammatical patterns as opposed to infrequent, unattested, or impossible patterns using artificial languages (White and Cotterell, 2021; Kuribayashi et al., 2024). The use of artificial languages facilitates isolation of specific grammatical properties from other factors such as lexical or real-world knowledge, but also risks oversimplification of the problem.

In this paper, we examine the use of Generalized Categorial Grammars (GCGs) (Wood, 2014) as a general framework to create artificial languages with a wider range of attested word order patterns, including those where the subject intervenes between verb and object (VSO, OSV) and unbounded dependencies in object relative clauses. 
In our experiments, we exemplify our approach by extending White and Cotterell (2021) and report some significant differences from existing results.

GCG-Based Artificial Languages for Evaluating Inductive Biases of Neural Language Models

This study investigates the generalization abilities of discriminative transformers in Natural Language Inference (NLI) tasks, focusing on their tendency to rely on superficial features and dataset biases rather than genuine linguistic understanding. We argue that performance gaps between training and analysis datasets do not necessarily indicate a lack of knowledge but rather a misalignment between the decision boundaries of the classifier head and the representations learned by the encoder. By analyzing the representation space of NLI models on these datasets, we show that, despite poor accuracy based on final predictions, samples from opposing classes often remain linearly separable in the encoder's representation space. This suggests that the encoders possess sufficient knowledge to perform the NLI task effectively, despite the classifier head's challenges.

Beyond Accuracy: Revisiting Out-of-Distribution Generalization in NLI Models

Recent research has increasingly focused on the extent to which large language models (LLMs) exhibit human-like behavior. In this study, we investigate whether the mental lexicon in LLMs resembles that of humans in terms of lexical organization. Using a word association task—a direct and widely used method for probing word meaning and relationships in the human mind—we evaluated the lexical representations of GPT-4 and Llama-3.1. Our findings reveal that LLMs closely emulate human mental lexicons in capturing semantic relatedness but exhibit notable differences in other properties, such as association frequency and dominant lexical patterns (e.g., top associates). Specifically, LLM lexicons demonstrate greater clustering and reduced diversity compared to the human lexicon, with KL divergence analysis confirming significant deviations in word association patterns. Additionally, LLMs fail to fully capture word association responses patterns in different demographic human groups. Among the models, GPT-4 consistently exhibited a slightly higher degree of human-likeness than Llama-3.1. This study highlights both the potential and limitations of LLMs in replicating human mental lexicons, offering valuable insights for applications in natural language processing and cognitive science research involving LLMs.

Human-likeness of LLMs in the Mental Lexicon

Human lexicons contain many different words that speakers can use to refer to the same object, e.g., purple or magenta for the same shade of color. On the one hand, studies on language use have explored how speakers adapt their referring expressions to successfully commu- nicate in context, without focusing on proper- ties of the lexical system. On the other hand, studies in language evolution have discussed how competing pressures for informativeness and simplicity shape lexical systems, without tackling in-context communication. We aim at bridging the gap between these traditions, and explore why a soft mapping between referents and words is a good solution for communication, by taking into account both in-context communication and the structure of the lexicon. We propose a simple measure of informativeness for words and lexical systems, grounded in a visual space, and analyze color naming data for English and Mandarin Chinese. We conclude that optimal lexical systems are those where multiple words can apply to the same referent, conveying different amounts of information. Such systems allow speakers to maximize communication accuracy and minimize the amount of information they convey when communicating about referents in contexts.

Why do objects have many names? A study on word informativeness in language use and lexical systems

Retrieval Augmented Generation (RAG) complements the knowledge of Large Language Models (LLMs) by leveraging external information to enhance response accuracy for queries. This approach is widely applied in several fields by taking its advantage of injecting the most up-to-date information, and researchers are focusing on understanding and improving this aspect to unlock the full potential of RAG in such high-stakes applications. However, despite the potential of RAG to address these needs, the mechanisms behind the confidence levels of its outputs remain underexplored. Our study focuses on the impact of RAG, specifically examining whether RAG increases the confidence of LLM outputs in the medical domain. We conduct this analysis across various configurations and models. We evaluate confidence by treating the model's predicted probability as its output and calculating several evaluation metrics which include calibration error method, entropy, best probability, and accuracy. Experimental results across multiple datasets confirmed that certain models possess the capability to judge for themselves whether an inserted document relates to the correct answer. These results suggest that evaluating models based on their output probabilities determine whether they function as generators in the RAG framework. Our approach allows to evaluate whether the models handle retrieved documents. and improving this aspect to unlock the full potential of RAG in such high-stakes applications. However, despite the potential of RAG to address these needs, the mechanisms behind the confidence levels of its outputs remain underexplored. Our study focuses on the impact of RAG, specifically examining whether RAG increases the confidence of LLM outputs in the medical domain. We conduct this analysis across various configurations and models. We evaluate confidence by treating the model's predicted probability as its output and calculating several evaluation metrics which include calibration error method, entropy, best probability, and accuracy. Experimental results across multiple datasets confirmed that certain models possess the capability to judge for themselves whether an inserted document relates to the correct answer. These results suggest that evaluating models based on their output probabilities determine whether they function as generators in the RAG framework. Our approach allows to evaluate whether the models handle retrieved documents.

Understanding the Impact of Confidence in Retrieval Augmented Generation: A Case Study in the Medical Domain

Medical text summarization faces significant challenges due to the complexity and domain-specific nature of the language. Although large language models have achieved significant success in general domains, their effectiveness in the medical domain remains limited. This limitation stems from their insufficient understanding of domain-specific terminology and difficulty in interpreting complex medical relationships, which often results in suboptimal summarization quality. To address these challenges, we propose MedSummRAG, a novel retrieval-augmented generation (RAG) framework that integrates external knowledge to enhance summarization. Our approach employs a fine-tuned dense retriever, trained with contrastive learning, to retrieve relevant documents for medical summarization. The retrieved documents are then integrated with the input text to generate high-quality summaries. Experimental results show that MedSummRAG achieves significant improvements in ROUGE scores on both zero/few-shot and fine-tuned language models, outperforming baseline methods. These findings underscore the importance of RAG and domain adaptation of the retriever for medical text summarization. The source code of this paper can be obtained from: https://github.com/guantingluo98/MedSummRAG

MedSummRAG: Domain-Specific Retrieval for Medical Summarization

Social media platforms generate an enormous volume of multi-modal data, yet stress detection research has predominantly relied on text-based analysis. In this work, we propose a novel framework that integrates textual content with synthesized visual cues to enhance stress detection. Using the generative model DALL·E, we synthesize images from social media posts, which are then fused with text through the multi-modal capabilities of a pre-trained CLIP model. Our approach is evaluated on the Dreaddit dataset, where a classifier trained on frozen CLIP features achieves 94.90% accuracy, and full fine-tuning further improves performance to 98.41%. These results underscore the integration of synthesized visuals with textual data not only enhances stress detection but also offers a robust method over traditional text-only methods, paving the way for innovative approaches in mental health monitoring and social media analytics.

Enhancing Stress Detection on Social Media Through Multi-Modal Fusion of Text and Synthesized Visuals

We developed a new methodology of extracting the frequency of a patient's epilepsy seizures from unstructured, free-text outpatient clinic letters by: first, devising a singular unit of measurement for seizure frequency; and second, fine-tuning a generative Large Language Model (LLM) on our bespoke annotated dataset. We measured frequency by the number of seizures per month: one seizure or more requires an integer; and less than one a decimal. This approach enables us to track whether a patient's seizures are improving or not over time. We found fine-tuning improves the F1 score of our best-performing LLM, Ministral-8B-Instruct-2410, by around three times compared to an untrained model. We also found Ministral demonstrated an impressive ability for mathematical reasoning.

Downloads

Next from ACL 2025

Compositionality and Event Retrieval in Complement Coercion: A Study of Language Models in a Low-resource Setting

Similar lecture

Dealing with dialectal variation in the construction of the Basque historical corpus

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ACL 2025

Compositionality and Event Retrieval in Complement Coercion: A Study of Language Models in a Low-resource Setting

Similar lecture

Dealing with dialectal variation in the construction of the Basque historical corpus

Downloads