Austria

The evaluation of text generated by LLMs remains a challenge for question answering, retrieval augmented generation (RAG), summarization, and many other natural language processing tasks. Evaluating the factuality of LLM generated responses is particularly important in medical question answering, where the stakes are high. One method of evaluating the factuality of text is through the use of information nuggets (answer keys). Nuggets are text representing atomic facts that may be used by an assessor to make a binary decision as to whether the fact represented by said nugget is contained in an answer. Although manual nugget extraction is expensive and time-consuming, recent RAG shared task evaluations have explored automating the nuggetization of text with LLMs. In this work, we explore several approaches to nugget generation for medical question answering and evaluate their alignment with expert human nugget generation. We find providing an example and extracting nuggets from an answer to be the best approach to nuggetization. While, overall, we found the capabilities of LLMs to distill atomic facts limited, Llama 3.3 performed the best out of the models we tested.

ACL 2025

Can Large Language Models Accurately Generate Answer Keys for Health-related Questions?

resources and evaluation

question answering

generation

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.

**Online Registration Form**: https://acl.swoogo.com/acl2026

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)

How well do modern long-context language models understand literary fiction? We explore this question via the task of literary evidence retrieval, repurposing the RELiC dataset of Thai et al. (2022) to construct a benchmark where the entire text of a primary source (e.g., The Great Gatsby) is provided to an LLM alongside literary criticism with a missing quotation from that work. This setting, in which the model must generate the missing quotation, mirrors the human process of literary analysis by requiring models to perform both global narrative reasoning and close textual examination. We curate a high-quality subset of 292 examples through extensive filtering and human verification. Our experiments show that recent reasoning models, such as Gemini 2.5 Pro can exceed human expert performance (62.5% vs. 50% accuracy). In contrast, the best open-weight model achieves only 29.1% accuracy, highlighting a wide gap in interpretive reasoning between open and closed-weight models. Despite their speed and apparent accuracy, even the strongest models struggle with nuanced literary signals and overgeneration, signaling open challenges for applying LLMs to literary analysis. We release our dataset and evaluation code to encourage future work in this direction.

Literary Evidence Retrieval via Long-Context Language Models

Retrieval from graph data is crucial for augmenting large language models (LLM) with both open-domain knowledge and private enterprise data, and it is also a key component in the recent GraphRAG system \cite{edge2024local}. Despite decades of research on knowledge graphs and knowledge base question answering, leading LLM frameworks (\eg Langchain and LlamaIndex) have only minimal support for retrieval from modern encyclopedic knowledge graphs like Wikidata. In this paper, we analyze the root cause and suggest that modern RDF knowledge graphs (\eg Wikidata, Freebase) are less efficient for LLMs due to overly large schemas that far exceed the typical LLM context window, use of resource identifiers, overlapping and ambiguous relation types and lack of normalization. As a solution, we propose \textit{property graph views} on top of the underlying RDF graph that can be efficiently queried by LLMs using \textit{Cypher}. We instantiated this idea on Wikidata and introduced {CypherBench}, the first benchmark with 11 large-scale, multi-domain property graphs with 7.8 million entities and over 10,000 questions. To achieve this, we tackled several key challenges, including developing an RDF-to-property graph conversion engine, creating a systematic pipeline for text-to-Cypher task generation, and designing new evaluation metrics.

CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Era

A person's perspective on a topic can influence their empathy towards a story. To investigate the use of personal perspective in empathy prediction, we collected a dataset, EmpathyFromPerspectives, where a user rates their empathy towards a story by a person with a different perspective on a prompted topic. We observed in the dataset that user perspective can be important for empathy prediction and developed a model, PPEP, that uses a rater's perspective as context for predicting the rater's empathy towards a story. Experiments comparing PPEP with baseline models show that use of personal perspective significantly improves performance. A user study indicated that human empathy ratings of stories generally agreed with PPEP's relative empathy rankings.

Empathy Prediction from Diverse Perspectives

This study provides the first comprehensive comparison of New York Times-style text generated by six large language models against real, human-authored NYT writing. The comparison is based on a formal syntactic theory. We use Head-driven Phrase Structure Grammar (HPSG) to analyze the grammatical structure of the texts. We then investigate and illustrate the differences in the distributions of HPSG grammar types, revealing systematic distinctions between human and LLM-generated writing. These findings contribute to a deeper understanding of the syntactic behavior of LLMs as well as humans, within the NYT genre.

Comparing LLM-generated and human-authored news text using formal syntactic theory

Modern Slavery Acts mandate that corporations disclose their efforts to combat modern slavery, aiming to enhance transparency and strengthen practices for its eradication. However, verifying these statements remains challenging due to their complex, diversified language and the sheer number of statements that must be reviewed. The development of NLP tools to assist in this task is also difficult due to a scarcity of annotated data. Furthermore, as modern slavery transparency legislation has been introduced in several countries, the generalizability of such tools across legal jurisdictions must be studied. To address these challenges, we work with domain experts to make two key contributions. First, we present AIMS.uk and AIMS.ca, newly annotated datasets from the UK and Canada to enable cross-jurisdictional evaluation. Second, we introduce AIMSCheck, an end-to-end framework for compliance validation. AIMSCheck decomposes the compliance assessment task into three levels, enhancing interpretability and practical applicability. Our experiments show that models trained on an Australian dataset generalize well across UK and Canadian jurisdictions, demonstrating the potential for broader application in compliance monitoring. We release the benchmark datasets and AIMSCheck to the public to advance AI-adoption in compliance assessment and drive further research in this field.

AIMSCheck: Leveraging LLMs for AI-Assisted Review of Modern Slavery Statements Across Jurisdictions

Dense retrieval models are commonly used in Information Retrieval (IR) applications, such as Retrieval-Augmented Generation (RAG). Since they often serve as the first step in these systems, their robustness is critical to avoid downstream failures. In this work, we repurpose a relation extraction dataset (e.g., Re-DocRED) to design controlled experiments that quantify the impact of heuristic biases, such as a preference for shorter documents, on retrievers like Dragon+ and Contriever. We uncover major vulnerabilities, showing retrievers favor shorter documents, early positions, repeated entities, and literal matches, all while ignoring the answer's presence! Notably, when multiple biases combine, models exhibit catastrophic performance degradation, selecting the answer-containing document in less than 10% of cases over a synthetic biased document without the answer. Furthermore, we show that these biases have direct consequences for downstream applications like RAG, where retrieval-preferred documents can mislead LLMs, resulting in a 34% performance drop than providing no documents at all.
https://huggingface.co/datasets/mohsenfayyaz/ColDeR

Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence

Toxic language detection is crucial for creating safer online environments and limiting the spread of harmful content. While toxic language detection has been under-explored in Persian, the current work compares different methods for this task, including fine-tuning, data enrichment, zero-shot and few-shot learning, and cross-lingual transfer learning. What is especially compelling is the impact of cultural context on transfer learning for this task: We show that the language of a country with cultural similarities to Persian yields better results in transfer learning. Conversely, the improvement is lower when the language comes from a culturally distinct country.

Culture Matters in Toxic Language Detection in Persian

Personalization plays a critical role in numerous language tasks and applications, since users with the same requirements may prefer diverse outputs based on their interests. This has led to the development of various personalized approaches aimed at adapting large language models (LLMs) to generate customized outputs aligned with user preferences. Some of them involve fine-tuning a unique personalized LLM for each user, which is too expensive for widespread application. Alternative approaches introduce personalization information in a plug-and-play manner by retrieving the user's relevant historical texts as demonstrations. However, this retrieval-based strategy may break the continuity of the user history and fail to capture the user's overall styles and patterns, hence leading to sub-optimal performance. To address these challenges, we propose a novel personalized LLM model, PPlug. It constructs a user-specific embedding for each individual by modeling all her historical contexts through a lightweight plug-in user embedder module. By attaching this embedding to the task input, LLMs can better understand and capture user habits and preferences, thereby producing more personalized outputs without tuning their parameters. Extensive experiments on various tasks in the language model personalization (LaMP) benchmark demonstrate that the proposed model significantly outperforms existing personalized LLM approaches.

LLMs + Persona-Plug = Personalized LLMs

Large language models possess general linguistic abilities but acquire language less efficiently than humans. This study proposes a method for integrating the developmental characteristics of working memory during the critical period, a stage when human language acquisition is particularly efficient, into the training process of language models. The proposed method introduces a mechanism that initially constrains working memory during the early stages of training and gradually relaxes this constraint in an exponential manner as learning progresses. Targeted syntactic evaluation shows that the proposed method outperforms conventional methods without memory constraints or with static memory constraints. These findings not only provide new directions for designing data-efficient language models but also offer indirect evidence supporting the role of the developmental characteristics of working memory as the underlying mechanism of the critical period in language acquisition.

Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition

Temporal knowledge graph completion aims to predict missing facts in a knowledge graph by leveraging temporal information. Existing methods often struggle to capture both the long-term changes and short-term variability of relations, which are crucial for accurate prediction. In this paper, we propose a novel method called TeRDy for temporal knowledge graph completion. TeRDy captures temporal relational dynamics by utilizing time-invariant embeddings, along with long-term temporally dynamic embeddings (e.g., enduring political alliances) and short-term temporally dynamic embeddings (e.g., transient political events). These two types of embeddings are derived from low- and high-frequency components via frequency decomposition. Also, we design temporal smoothing and temporal gradient to seamlessly incorporate timestamp embeddings into relation embeddings. Extensive experiments on benchmark datasets demonstrate that TeRDy outperforms state-of-the-art temporal knowledge graph embedding methods.

Downloads

Next from ACL 2025

Literary Evidence Retrieval via Long-Context Language Models

Similar lecture

Do Nugget-Based Evaluation Patterns Generalize to List-QA?