Austria

State-of-the-art automatic event detection struggles with interpretability and adaptability to evolving large-scale key events---unlike episodic structures, which excel in these areas. Often overlooked, episodes represent cohesive clusters of core entities performing actions at a specific time and location; a partially ordered sequence of episodes can represent a key event. This paper introduces a novel task, **episode detection**, which identifies episodes within a news corpus of key event articles. Detecting episodes poses unique challenges, as they lack explicit temporal or locational markers and cannot be merged using semantic similarity alone. While large language models (LLMs) can aid with these reasoning difficulties, they suffer with long contexts typical of news corpora. To address these challenges, we introduce **EpiMine**, an unsupervised framework that identifies a key event&#39;s candidate episodes by leveraging natural episodic partitions in articles, estimated through shifts in discriminative term combinations. These candidate episodes are more cohesive and representative of true episodes, synergizing with LLMs to better interpret and refine them into final episodes. We apply EpiMine to our three diverse, real-world event datasets annotated at the episode level, where it achieves a 59.2% average gain across all metrics compared to baselines.

ACL 2025

Synergizing Unsupervised Episode Detection with LLMs for Large-Scale News Events

episode detection

temporal reasoning

event extraction

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

ACL 2024

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

State-of-the-art automatic event detection struggles with interpretability and adaptability to evolving large-scale key events---unlike episodic structures, which excel in these areas. Often overlooked, episodes represent cohesive clusters of core entities performing actions at a specific time and location; a partially ordered sequence of episodes can represent a key event. This paper introduces a novel task, **episode detection**, which identifies episodes within a news corpus of key event articles. Detecting episodes poses unique challenges, as they lack explicit temporal or locational markers and cannot be merged using semantic similarity alone. While large language models (LLMs) can aid with these reasoning difficulties, they suffer with long contexts typical of news corpora. To address these challenges, we introduce **EpiMine**, an unsupervised framework that identifies a key event's candidate episodes by leveraging natural episodic partitions in articles, estimated through shifts in discriminative term combinations. These candidate episodes are more cohesive and representative of true episodes, synergizing with LLMs to better interpret and refine them into final episodes. We apply EpiMine to our three diverse, real-world event datasets annotated at the episode level, where it achieves a 59.2% average gain across all metrics compared to baselines.

technical 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)

Code LLMs have been widely used in various domains, including code generation, logical reasoning, and agent systems. However, open-access code LLMs mostly only release weights, lacking key features such as reproducible data pipelines and transparent training protocols, which are crucial for advancing deeper, more reliable investigations. To address the gap, we introduce OpenCoder, a top-tier code LLM that not only achieves performance comparable to leading models but also serves as an ``open cookbook'' for the research community. Unlike most prior efforts, we release not only model weights and inference code, but also the reproducible training data, complete data processing pipeline, rigorous experimental ablation results, and detailed training protocols for open scientific research. Our work identifies the key ingredients for building a top-tier code LLM: optimized heuristic rules for data cleaning and deduplication, effective recall of code-related text corpus, and high-quality synthetic data for both annealing and supervised fine-tuning stages. By offering this level of openness, we aim to broaden access to all aspects of a top-tier code LLM, with OpenCoder serving as both a powerful model and an open foundation to accelerate research and enable reproducible advancements in code intelligence. The released resource is available at https://opencoder-llm.github.io.

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models

Many sensitive domains — such as the clinical domain — lack widely available datasets due to privacy risks. The increasing generative capabilities of large language models (LLMs) have made synthetic datasets a viable path forward. In this study, we domain-adapt LLMs to the clinical domain and generate synthetic clinical texts that are machine-annotated with tags for personally identifiable information using capable encoder-based NER models. The synthetic corpora are then used to train synthetic NER models. The results show that training NER models using synthetic corpora incurs only a small drop in predictive performance. The limits of this process are investigated in a systematic ablation study — using both Swedish and Spanish data. Our analysis shows that smaller datasets can be sufficient for domain-adapting LLMs for data synthesis. Instead, the effectiveness of this process is almost entirely contingent on the performance of the machine-annotating NER models trained using the original data.

Data-Constrained Synthesis of Training Data for De-Identification

Despite the increasing use of large language models (LLMs) for context-grounded tasks like summarization and question-answering, understanding what makes an LLM produce a certain response is challenging. We propose Multi-Level Explanations for Generative Language Models (MExGen), a technique to provide explanations for context-grounded text generation. MExGen assigns scores to parts of the context to quantify their influence on the model's output. It extends attribution methods like LIME and SHAP to LLMs used in context-grounded tasks where (1) inference cost is high, (2) input text is long, and (3) the output is text. We conduct a systematic evaluation, both automated and human, of perturbation-based attribution methods for summarization and question answering. The results show that our framework can provide more faithful explanations of generated output than available alternatives, including LLM self-explanations. We open-source code for MExGen as part of the ICX360 toolkit: https://github.com/IBM/ICX360.

Multi-Level Explanations for Generative Language Models

Jailbreak attacks aim to bypass the LLMs' safeguards. While researchers have proposed different jailbreak attacks in depth, they have done so in isolation---either with unaligned settings or comparing a limited range of methods. To fill this gap, we present a large-scale evaluation of various jailbreak attacks. We collect 17 representative jailbreak attacks, summarize their features, and establish a novel jailbreak attack taxonomy. Then we conduct comprehensive measurement and ablation studies across nine aligned LLMs on 160 forbidden questions from 16 violation categories. Also, we test jailbreak attacks under eight advanced defenses. Based on our taxonomy and experiments, we identify some important patterns, such as heuristic-based attacks, which could achieve high attack success rates but are easy to mitigate by defenses. Our study offers valuable insights for future research on jailbreak attacks and defenses and serves as a benchmark tool for researchers and practitioners to evaluate them effectively.

JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs

The surge of interest in culture in NLP has inspired much recent research, but a shared understanding of "culture" remains unclear, making it difficult to evaluate progress in this emerging area. Drawing on prior research in NLP and related fields, we propose a fine-grained taxonomy of elements in culture that can provide a systematic framework for analyzing and understanding research progress. Using the taxonomy, we survey existing resources and methods for culturally aware and adapted NLP, providing an overview of the state of the art and the research gaps that still need to be filled.

Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art

Accurate mapping of queries to product categories is crucial for efficient retrieval and ranking of relevant products in e-commerce search. Conventionally, such query classification models rely on supervised learning using historical user interactions, but their effectiveness diminishes in cold-start scenarios, where new categories or products lack sufficient training data. This results in poor query-to-category mappings, negatively affecting retrieval and ranking. Synthetic query generation has emerged as a promising solution by augmenting training data; however, existing methods do not incorporate feedback from the query relevance model, limiting their ability to generate queries that enhance product retrieval. To address this, we propose an adversarial reinforcement learning framework that optimizes an LLM-based generator to expose weaknesses in query classification models. The generator produces synthetic queries to augment the classifier’s training set, ultimately improving its performance. Additionally, we introduce a structured reward signal to ensure stable training. Experiments on public datasets show an average PR-AUC improvement of +1.82\% on benchmarks and +3.26\% on a proprietary dataset, demonstrating the framework’s effectiveness in enhancing query classification and mitigating cold-start challenges.

Reinforcement Learning for Adversarial Query Generation to Enhance Relevance in Cold-Start Product Search

Building upon advancements in Large Language Models (LLMs), the field of audio processing has seen increased interest in training speech generation tasks with discrete speech token sequences. However, directly discretizing speech by neural audio codecs often results in sequences that fundamentally differ from text sequences. Unlike text, where text token sequences are deterministic, discrete speech tokens can exhibit significant variability based on contextual factors, while still producing perceptually identical audio segments. We refer to this phenomenon as Discrete Representation Inconsistency (DRI). This inconsistency can lead to a single speech segment being represented by multiple divergent sequences, which creates confusion in neural codec language models and results in poor generated speech. In this paper, we quantitatively analyze the DRI phenomenon within popular audio tokenizers such as EnCodec. Our approach effectively mitigates the DRI phenomenon of the neural audio codec. Furthermore, extensive experiments on the neural codec language model over LibriTTS and large-scale MLS dataset (44,000 hours) demonstrate the effectiveness and generality of our method. The demo of audio samples is available at https://consistencyinneuralcodec.github.io.

Analyzing and Mitigating Inconsistency in Discrete Speech Tokens for Neural Codec Language Models

Large Language Models (LLMs) are increasingly used in everyday life and research. One of the most common use cases is conversational interactions, enabled by the language generation capabilities of LLMs. Just as between two humans, a conversation between an LLM-powered entity and a human depends on the personality of the conversants. However, measuring the personality of a given LLM is currently a challenge. This article introduces the Language Model Linguistic Personality Assessment (LMLPA), a system designed to evaluate the linguistic personalities of LLMs. Our system helps to understand LLMs' language generation capabilities by quantitatively assessing the distinct personality traits reflected in their linguistic outputs. Unlike traditional human-centric psychometrics, the LMLPA adapts a personality assessment questionnaire, specifically the Big Five Inventory, to align with the operational capabilities of LLMs, and also incorporates the findings from previous language-based personality measurement literature. To mitigate sensitivity to the order of options, our questionnaire is designed to be open-ended, resulting in textual answers. Thus, the Artificial Intelligence (AI) rater is needed to transform ambiguous personality information from text responses into clear numerical indicators of personality traits. Utilising Principal Component Analysis and reliability validation methods, our findings demonstrate that LLMs possess distinct personality traits that can be effectively quantified by the LMLPA. This research contributes to Human-Centered AI and Computational Linguistics, providing a robust framework for future studies to refine AI personality assessments and expand their applications in multiple areas, including education and manufacturing

LMLPA: Language Model Linguistic Personality Assessment

Transforming dense, unstructured text into interpretable tables—commonly referred to as Text-to-Table generation—is a key task in information extraction. Existing methods often overlook what complex information to extract and how to infer it from text. We present Map&Make, a versatile approach that decomposes text into atomic propositions to infer latent schemas, which are then used to generate tables capturing both qualitative nuances and quantitative facts. We evaluate our method on three challenging datasets: Rotowire, known for its complex, multi-table schema; Livesum which requires numerical aggregation; and Wiki40 which require open text extraction from mulitple domains. By correcting hallucination errors in Rotowire, we also provide a cleaner benchmark. Our method shows significant gains in both accuracy and interpretability across comprehensive comparative and referenceless metrics. Finally, ablation studies highlight the key factors driving performance and validate the utility of our approach in structured summarization. Code and data are available at: https://coral-lab-asu.github.io/map-make.

Map&Make: Schema Guided Text to Table Generation

Automatic language identification is a core problem of many Natural Language
Processing (NLP) pipelines. A wide variety of architectures and benchmarks have
been proposed with often near-perfect performance. Although previous
studies have focused on certain challenging setups (i.e. cross-domain, short
inputs), a systematic comparison is missing. We propose a benchmark that 
allows us to test for the effect of input size, training data size, domain, number of
languages, scripts, and language families on performance. We evaluate
five popular models on this benchmark and identify which open challenges
remain for this task as well as which architectures achieve robust performance. We
find that cross-domain setups are the most challenging (although arguably most
relevant), and that number of languages, variety in scripts, and variety in
language families have only a small impact on performance. We also contribute
practical takeaways: training with 1,000 instances per language and a maximum
input length of 100 characters is enough for robust language identification.
Based on our findings, we train an accurate (94.41%) multi-domain language
identification model on 2,034 languages, for which we also provide an analysis
of the remaining errors.

Downloads

Next from ACL 2025

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models

Similar lecture

EVIT: Event-Oriented Instruction Tuning for Event Reasoning