Austria

We propose a method to optimize language model pre-training data mixtures through efficient approximation of the cross-entropy loss corresponding to each candidate mixture via a Mixture of Data Experts (MDE). We use this approximation as a source of additional features in a regression model, trained from observations of model loss for a small number of mixtures. Experiments with Transformer decoder-only language models in the range of 70M to 10B parameters on the SlimPajama dataset show that our method achieves significantly better performance than approaches that train regression models using only the mixture rates as input features. Combining this improved optimization method with an objective that takes into account cross-entropy on end task data leads to superior performance on few-shot downstream evaluations. We also provide theoretical insights on why aggregation of data expert predictions can provide good approximations to model losses for data mixtures.

ACL 2025

Optimizing Pre-Training Data Mixtures with Mixtures of Data Expert Models

data optimization

scaling laws

language model pre-training

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

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)

Automatic post-editing (APE) aims to correct errors in machine-translated text, enhancing translation quality, while reducing the need for human intervention. Despite advances in neural machine translation (NMT), the development of effective APE systems has been hindered by the lack of large-scale multilingual datasets specifically tailored to NMT outputs. To address this gap, we present and release LangMark, a new human-annotated multilingual APE dataset for English translation to seven languages: Brazilian Portuguese, French, German, Italian, Japanese, Russian, and Spanish. The dataset has 206,983 triplets, with each triplet consisting of a source segment, its NMT output, and a human post-edited translation. Annotated by expert human linguists, our dataset offers both linguistic diversity and scale. Leveraging this dataset, we empirically show that Large Language Models (LLMs) with few-shot prompting can effectively perform APE, improving upon leading commercial and even proprietary machine translation systems. We believe that this new resource will facilitate the future development and evaluation of APE systems.

LangMark: A Multilingual Dataset for Automatic Post-Editing

Each year, tens of millions of essays are written and graded in college-level English courses. Students are asked to analyze literary and cultural texts through a process known as close reading, where they gather textual details from which to formulate evidence-based arguments. Despite being viewed as a basis for critical thinking and widely adopted as a required element of university coursework, close reading has never been evaluated on large language models (LLMs), and multi-discipline benchmarks like MMLU do not include literature as a subject. To fill this gap, we present KRISTEVA, the first close reading benchmark for evaluating interpretive reasoning, consisting of 1331 multiple-choice questions adapted from classroom data. With KRISTEVA, we propose three progressively more difficult sets of tasks to approximate different elements of the close reading process, which we use to test how well LLMs understand and reason about literary works: 1) extracting stylistic features, 2) retrieving relevant contextual information from parametric knowledge, and 3) multi-hop reasoning between style and external contexts. Our baseline results find that while state-of-the-art LLMs possess some college-level close reading competency (accuracy 49.7% - 69.7%), their performances still trail those of experienced human evaluators on 10 out of our 11 tasks.

KRISTEVA: Close Reading as a Novel Task for Benchmarking Interpretive Reasoning

Multimodal Retrieval-Augmented Generation (MMRAG) has been introduced to enhance Multimodal Large Language Models by incorporating externally retrieved multimodal knowledge, but it introduces two challenges: Parametric-Retrieved Knowledge Inconsistency (PRKI), where discrepancies between parametric and retrieved knowledge create uncertainty in determining reliability, and Visual-Textual Knowledge Inconsistency (VTKI), where misalignment between visual and textual sources disrupts entity representation. To address these challenges, we propose $\textbf{C}$r$\textbf{o}$ss-source knowledge $\textbf{Re}$conciliation for $\textbf{M}$ulti$\textbf{M}$odal $\textbf{RAG}$ (CoRe-MMRAG), a novel end-to-end framework that effectively reconciles inconsistencies across knowledge sources. CoRe-MMRAG follows a four-stage pipeline: it first generates an internal response from parametric knowledge, then selects the most relevant multimodal evidence via joint similarity assessment, generates an external response, and finally integrates both to produce a reliable answer. Additionally, a specialized training paradigm enhances knowledge source discrimination, multimodal integration, and unified answer generation. Experiments on KB-VQA benchmarks show that CoRe-MMRAG achieves substantial improvements over baseline methods, achieving 5.6\% and 9.3\% performance gains on InfoSeek and Encyclopedic-VQA, respectively. We release code and data at \href{https://github.com/TyangJN/CoRe-MMRAG}{https://github.com/TyangJN/CoRe-MMRAG}.

CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAG

Large Language Models (LLMs) are increasingly deployed worldwide, yet their ability to navigate cultural nuances remains underexplored. Misinterpreting cultural content can lead to AI-generated responses that are offensive or inappropriate, limiting their usability in global applications such as customer service, diplomatic communication, and online education. While prior research has evaluated cultural knowledge of LLMs, existing benchmarks fail to assess dynamic cultural competence-the ability to apply cultural knowledge effectively in real-world interactions. To address this gap, we introduce SocialDuolingo, a novel benchmark designed to evaluate cultural competence through multi-turn interactive intercultural scenarios. It comprises 3,060 human-written scenarios spanning 60 countries across six continents. Through extensive experiments on eight prominent LLMs, our findings reveal a significant gap between the cultural knowledge stored in these models and their ability to apply it effectively in cross-cultural communication.

SocialDuolingo: Interactive Evaluation for Cultural Competence in Language Agents

Large language models (LLMs) have demonstrated impressive translation capabilities even without being explicitly trained on parallel data. This remarkable property has led some to believe that parallel data is no longer necessary for building multilingual language models. While some attribute this to the emergent abilities of LLMs due to scale, recent work suggests that it is actually caused by incidental bilingual signals present in the training data. Various methods have been proposed to maximize the utility of parallel data to enhance the multilingual capabilities of multilingual encoder-based and encoder-decoder language models. However, some decoder-based LLMs opt to ignore parallel data instead. In this work, we conduct a systematic study on the impact of adding parallel data on LLMs' multilingual capabilities, focusing specifically on translation and multilingual common-sense reasoning. Through controlled experiments, we demonstrate that parallel data can significantly improve LLMs' multilingual capabilities.

Just Go Parallel: Improving the Multilingual Capabilities of Large Language Models

Curating datasets that span multiple languages is challenging. To make the collection more scalable, researchers often incorporate one or more imperfect classifiers in the process, like language identification models. These models, however, are prone to failure, resulting in some language partitions being unreliable for downstream tasks. We introduce a statistical test, the Preference Proportion Test, for identifying such unreliable partitions. By annotating only 20 samples for a language partition, we're able to identify systematic transcription errors for 10 language partitions in a recent large multilingual transcribed audio archive, X-IPAPACK (Zhu et al., 2024). We find that filtering these low-quality partitions out when training models for the downstream task of phonetic transcription brings substantial benefits, most notably a 25.7% relative improvement on transcribing recordings in out-of-distribution languages. Our work contributes an effective method for auditing multilingual audio archives.

A Comparative Approach for Auditing Multilingual Phonetic Transcript Archives

Character Coreference Resolution in Movie Screenplays (MovieCoref) is a newly emerging task for understanding complex movie plots and character relationships. This task poses greater challenges than traditional coreference resolution, due to the intricate narrative structures and character interactions unique to screenplays. In light of these challenges, we introduce a novel approach: a Structure-aware Triaffine Parser (STPar) for the MovieCoref task. The STPar combines discourse and syntactic structures in the feature encoding process, enabling comprehensive analysis of ternary relationships and complex interactions. During the pairing process, the STPar utilizes a triaffine scorer to consider high-order relations between candidate mention pairs, thus enhancing its ability to capture detailed narrative structures. In addition, the STPar incorporates multi-task learning, encompassing singleton and span detection tasks, to further improve coreference resolution performance. Our evaluations on the MovieCoref dataset demonstrate that the STPar significantly outperforms the best baseline by 6.9\%, 21.1\%, 6.7\% and 9.7\% in F1 scores of B$^3$, CEAF$_e$, LEA and CoNLL. Further analysis highlights the benefits of integrating structural discourse and syntactic information as well as the combined approaches of triaffine and multi-task learning.

STPar: A Structure-Aware Triaffine Parser for Screenplay Character Coreference Resolution

Language model users often issue queries that lack specification, where the context under which a query was issued---such as the user's identity, the query's intent, and the criteria for a response to be useful---is not explicit. For instance, a good response to a subjective query like “What book should I read next?” would depend on the user’s preferences, and a good response to an open-ended query like “How do antibiotics work against bacteria?” would depend on the user's expertise. This makes evaluation of responses to such queries an ill-posed task, as evaluators must make uninformed judgements about the quality of a response. To remedy this, we present contextualized evaluations, a protocol that synthetically constructs context surrounding an underspecified query and provides it during evaluation. We find that the presence of context can 1) change conclusions drawn from evaluation, even flipping win rates between model pairs, 2) nudge evaluators to make fewer judgments based on surface-level criteria of responses, like style, and 3) provide new insights about model behavior in different contexts. Specifically, we discover an implicit bias towards WEIRD contexts in default responses and find that models are not equally sensitive to following different contexts.

Contextualized Evaluations: Taking the Guesswork Out of Language Model Evaluations

Large-scale sense-annotated corpora are important for a range of tasks but are hard to come by. Dictionaries that record and describe the vocabulary of a language often offer a small set of real-world example sentences for each sense of a word. However, on their own, these sentences are too few to be used as diachronic sense-annotated corpora. We propose a targeted strategy for training and evaluating generative models producing historically and semantically accurate word usages given any word, sense definition, and year triple.

Our results demonstrate that the fine-tuned models can generate usages with the same properties as real-world example sentences from a reference dictionary. Thus the generated usages will be suitable for training and testing computational models where large-scale sense-annotated corpora are needed but currently unavailable.

Sense-Specific Historical Word Usage Generation

Digital education has gained popularity in the last decade, especially after the COVID-19 pandemic. With the improving capabilities of large language models to reason and communicate with users, envisioning intelligent tutoring systems (ITSs) that can facilitate self-learning is not very far-fetched. One integral component to fulfill this vision is the ability to give accurate and effective feedback via hints to scaffold the learning process. In this survey article, we present a comprehensive review of prior research on hint generation, aiming to bridge the gap between research in education and cognitive science, and research in AI and Natural Language Processing. Informed by our findings, we propose a formal definition of the hint generation task, and discuss the roadmap of building an effective hint generation system aligned with the formal definition, including open challenges, future directions and ethical considerations.

Downloads

Next from ACL 2025

LangMark: A Multilingual Dataset for Automatic Post-Editing

Similar lecture

Scalable Data Ablation Approximations for Language Models through Modular Training and Merging