Austria

Mixture-of-experts (MoEs) have been adopted for reducing inference costs by sparsely activating experts in large language models (LLMs). Despite these reductions, the massive number of parameters in MoEs still makes them expensive to serve. Conventionally, unstructured or structured pruning has been considered to reduce number of parameters. Our key contribution is exploring the interpolation between structured and unstructured pruning, to propose a novel structured-then-unstructured (STUN) approach outperforming both of structured or unstructured pruning, especially for MoEs. In the first stage, we show a scalable expert pruning with O(1) forward pass, unlike existing work requiring $O(\frac{k^n}{\sqrt{n}})$ forward passes for $n$ experts that cannot scale for recent MoEs with hundreds of experts. We then show our expert-pruned MoEs are robust to unstructured pruning to follow. Experiments on Snowflake Arctic and Mixtral shows that our proposal is highly effective-- For Snowflake Arctic, a 480B-sized MoE with 128 experts, our method needs only one H100 and two hours to achieve nearly no loss in performance with 40% sparsity, even in generative tasks such as GSM8K, where state-of-the-art structured or unstructured pruning methods fail. The code is publicly available.

ACL 2025

STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning

nlp in resource-constrained settings

mixture of experts

sparsity

pruning

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

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)

This paper is concerned with phonetic reconstruction of the consonant system of Middle Chinese. We propose to cast the problem as a Mixed Integer Programming problem, which is able to automatically explore homophonic information from ancient rhyme dictionaries and phonetic information from modern Chinese dialects, the descendants of Middle Chinese. Numerical evaluation on a wide range of synthetic and real data demonstrates the effectiveness and robustness of the new method. We apply the method to information from Gu\v angy\`un (Author's note: The Gu\v angy\`un here is Chinese Pinyin in Latex, for HTML code, it should be Gu&#462;ngy&ugrave;n) and 20 modern Chinese dialects to obtain a new phonetic reconstruction result. A linguistically-motivated discussion of this result is also provided.

Phonetic Reconstruction of the Consonant System of Middle Chinese via Mixed Integer Optimization

Coreference resolution (CR) endeavors to match pronouns, noun phrases, etc. with their referent entities, acting as an important step for deep text understanding. Presently available CR datasets are either small in scale or restrict coreference resolution to a limited text span. In this paper, we present NovelCR, a large-scale bilingual benchmark designed for long-span coreference resolution. NovelCR features extensive annotations, including 148k mentions in NovelCR-en and 311k mentions in NovelCR-zh. Moreover, the dataset is notably rich in long-span coreference pairs, with 85% of pairs in NovelCR-en and 83% in NovelCR-zh spanning across three or more sentences. Experiments on NovelCR reveal a large gap between state-of-the-art baselines and human performance, highlighting that NovelCR remains an open issue.

NovelCR: A Large-Scale Bilingual Dataset Tailored for Long-Span Coreference Resolution

Hallucination occurs when large language models exhibit behavior that deviates from the boundaries of their knowledge during response generation. To address this critical issue, previous learning-based methods attempt to finetune models but are limited by off-policy sampling and coarse-grained feedback. In this paper, we present Reinforcement Learning for Hallucination (RLFH), an on-policy self-alignment approach that enables LLMs to actively explore their knowledge boundaries and self-correct generation behavior through fine-grained feedback signals. RLFH introduces a self-assessment framework where the policy serves as its own judge. Through this framework, responses are automatically decomposed into atomic facts and their truthfulness and informativeness are assessed against external knowledge sources. The resulting fine-grained feedback at the statement level are then converted into token-level dense reward signals. This enables online reinforcement learning to achieve precise and timely optimization without human intervention. Comprehensive evaluations on HotpotQA, SQuADv2, and Biography benchmarks validate RLFH’s effectiveness in hallucination mitigation.

On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation

Data visualizations, such as charts and histograms, are essential for analyzing and exploring data, enabling the effective communication of insights. While existing methods have been proposed to translate natural-language descriptions into visualization queries, they focus solely on spoken languages, overlooking sign languages, which comprise about 200 variants used by 70 million Deaf and Hard-of-Hearing (DHH) individuals. To fill this gap, this paper proposes Sign2Vis, a sign-language interface for data visualization, aimed at empowering the DHH community to engage with data analysis. We first construct a paired dataset that includes sign-language pose videos, paired with their corresponding visualization queries. Subsequently, we evaluate a variety of models, including both pipeline-based and end-to-end approaches, using the newly created dataset. Extensive experiments, coupled with a user study involving 15 participants, demonstrate the effectiveness of our proposed Sign2Vis. Finally, we share key insights from our evaluation and call for the development of more user-friendly techniques and tools to support the DHH community in conducting more effective interactive data analytics.

Sign2Vis: Automated Data Visualization from Sign Language

Role-Playing Agent (RPA) is an increasingly popular type of LLM Agent that simulates human-like behaviors in a variety of tasks. But how should we evaluate an RPA? It is hard because of the wide variety of task requirements and the different designs of RPA. This paper aims to propose an evidence-based, actionable, and generalizable evaluation design guideline for LLM-based RPA by systematically reviewing 1,676 papers published between Jan. 2021 and Dec. 2024. Our analysis synthesizes in total six agent attributes, seven task attributes, and seven evaluation metrics from existing literature. From this finding, we propose an RPA evaluation design guideline to support future researchers in designing their own evaluations in a more systematic and consistent manner.

Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agents

Conversational agents are increasingly woven into individuals' personal lives, yet users often underestimate the privacy risks involved. The moment users share information with these agents (e.g., LLMs), their private information becomes vulnerable to exposure. In this paper, we characterize the notion of contextual privacy for user interactions with LLMs. It aims to minimize privacy risks by ensuring that users (sender) disclose only information that is both relevant and necessary for achieving their intended goals when interacting with LLMs (untrusted receivers). Through a formative design user study, we observe how even "privacy-conscious" users inadvertently reveal sensitive information through indirect disclosures.

Based on insights from this study, we propose a locally-deployable framework that operates between users and LLMs, and identifies and reformulates out-of-context information in user prompts. Our evaluation using examples from ShareGPT shows that lightweight models can effectively implement this framework, achieving strong gains in contextual privacy while preserving the user's intended interaction goals through different approaches to classify information relevant to the intended goals.

Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents

Addressing gender bias and maintaining logical coherence in machine translation remains challenging, particularly when translating between natural gender languages, like English, and genderless languages, such as Persian, Indonesian, and Finnish. We introduce the Translate-with-Care (TWC) dataset, comprising 3,950 challenging scenarios across six low- to mid-resource languages, to assess translation systems' performance. Our analysis of diverse technologies, including GPT-4, mBART-50, NLLB-200, and Google Translate, reveals a universal struggle in translating genderless content, resulting in gender stereotyping and reasoning errors. All models preferred masculine pronouns when gender stereotypes could influence choices. Google Translate and GPT-4 showed particularly strong bias, favoring male pronouns 4-6 times more than feminine ones in leadership and professional success contexts. Fine-tuning mBART-50 on TWC substantially resolved these biases and errors, led to strong generalization, and surpassed proprietary LLMs while remaining open-source. This work emphasizes the need for targeted approaches to gender and semantic coherence in machine translation, particularly for genderless languages, contributing to more equitable and accurate translation systems.

Translate With Care: Addressing Gender Bias, Neutrality, and Reasoning in Large Language Model Translations

Cognitive tasks originally developed for humans are now increasingly used to study language models. While applying these tasks is often straightforward, interpreting their results can be challenging. In particular, when a model underperforms, it is often unclear whether this results from a limitation in the cognitive ability being tested or a failure to understand the task itself. A recent study argues that GPT 3.5’s declining performance on 2-back and 3-back tasks reflects a working memory capacity limit similar to humans (Gong et al., 2024). By analyzing a range of open-source language models of varying performance levels on these tasks, we show that the poor performance is due at least in part to a limitation in task comprehension and task set maintenance. We challenge the best-performing model with progressively harder versions of the task (up to 10-back) and experiment with alternative prompting strategies, before analyzing model attentions. Our larger aim is to contribute to the ongoing conversation around refining methodologies for the cognitive evaluation of language models.

Do Language Models Understand the Cognitive Tasks Given to Them? Investigations with the N-Back Paradigm

Recent advancements in Large Language Models (LLMs) have significantly propelled the development of Conversational Recommendation Agents (CRAs). However, these agents often generate short-sighted responses that fail to sustain user guidance and meet expectations. Although preference optimization has proven effective in aligning LLMs with user expectations, it remains costly and performs poorly in multi-turn dialogue. To address this challenge, we introduce a novel multi-turn preference optimization (MTPO) paradigm **ECPO**, which leverages Expectation Confirmation Theory to explicitly model the evolution of user satisfaction throughout multi-turn dialogues, uncovering the underlying causes of dissatisfaction. These causes can be utilized to support targeted optimization of unsatisfactory responses, thereby achieving turn-level preference optimization. ECPO eliminates the significant sampling overhead of existing MTPO methods while ensuring the optimization process drives meaningful improvements. To support ECPO, we also introduce an LLM-based user simulator, **AILO**, to simulate user feedback and expectation confirmation during conversational recommendations. Experimental results show that ECPO significantly enhances CRA's interaction capabilities, offering notable improvements in both efficiency and effectiveness over existing MTPO methods.

Expectation Confirmation Preference Optimization for Multi-Turn Conversational Recommendation Agent

Automated Essay Scoring (AES) plays a crucial role in educational assessment by providing scalable and consistent evaluations of writing tasks. However, traditional AES systems face three major challenges: (i) reliance on handcrafted features that limit generalizability, (ii) difficulty in capturing fine-grained traits like coherence and argumentation, and (iii) inability to handle multimodal contexts. In the era of Multimodal Large Language Models (MLLMs), we propose **EssayJudge**, the **first multimodal benchmark to evaluate AES capabilities across lexical-, sentence-, and discourse-level traits**. By leveraging MLLMs’ strengths in trait-specific scoring and multimodal context understanding, EssayJudge aims to offer precise, context-rich evaluations without manual feature engineering, addressing longstanding AES limitations. Our experiments with 18 representative MLLMs reveal gaps in AES performance compared to human evaluation, particularly in discourse-level traits, highlighting the need for further advancements in MLLM-based AES research. Our dataset and code will be available upon acceptance.

Downloads

Next from ACL 2025

Phonetic Reconstruction of the Consonant System of Middle Chinese via Mixed Integer Optimization

Similar lecture

Data Pruning for Efficient Model Pruning in Neural Machine Translation