Austria

An extensive high-quality instruction dataset is crucial for the instruction tuning process of Large Language Models (LLMs). Recent instruction expansion methods have demonstrated their capability to improve the quality and quantity of existing datasets, by prompting high-performance LLM to generate multiple new instructions from the original ones. However, existing methods focus on constructing multi-perspective prompts (e.g., increasing complexity or difficulty) to expand instructions, overlooking the &quot;Fixed Thinking Pattern&quot; issue of LLMs. This issue arises when repeatedly using the same set of prompts, causing LLMs to rely on a limited set of certain expressions to expand all instructions, potentially compromising the diversity of the final expanded dataset. This paper theoretically analyzes the causes of the &quot;Fixed Thinking Pattern&quot;, and corroborates this phenomenon through multi-faceted empirical research. Furthermore, we propose a novel method based on dynamic prompt updating: Global Eye. Specifically, after a fixed number of instruction expansions, we analyze the statistical characteristics of newly generated instructions and then update the prompts. Experimental results show that our method enables Llama3-8B and Llama2-13B to surpass the performance of open-source LLMs and GPT3.5 across various metrics. Our code and data are submitted to the Software &amp; Data option.

ACL 2025

Global Eye: Breaking the &quot;Fixed Thinking Pattern&quot; during the Instruction Expansion Process

statistical testing for evaluation

nlp datasets

automatic creation and evaluation of language resources

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

An extensive high-quality instruction dataset is crucial for the instruction tuning process of Large Language Models (LLMs). Recent instruction expansion methods have demonstrated their capability to improve the quality and quantity of existing datasets, by prompting high-performance LLM to generate multiple new instructions from the original ones. However, existing methods focus on constructing multi-perspective prompts (e.g., increasing complexity or difficulty) to expand instructions, overlooking the "Fixed Thinking Pattern" issue of LLMs. This issue arises when repeatedly using the same set of prompts, causing LLMs to rely on a limited set of certain expressions to expand all instructions, potentially compromising the diversity of the final expanded dataset. This paper theoretically analyzes the causes of the "Fixed Thinking Pattern", and corroborates this phenomenon through multi-faceted empirical research. Furthermore, we propose a novel method based on dynamic prompt updating: Global Eye. Specifically, after a fixed number of instruction expansions, we analyze the statistical characteristics of newly generated instructions and then update the prompts. Experimental results show that our method enables Llama3-8B and Llama2-13B to surpass the performance of open-source LLMs and GPT3.5 across various metrics. Our code and data are submitted to the Software & Data option.

Global Eye: Breaking the "Fixed Thinking Pattern" during the Instruction Expansion Process

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)

As the demand for artificial intelligence (AI) grows to address complex real-world tasks, single models are often insufficient, requiring the integration of multiple models into pipelines. This paper introduces Bel Esprit, a conversational agent designed to construct AI model pipelines based on user requirements. Bel Esprit uses a multi-agent framework where subagents collaborate to clarify requirements, build, validate, and populate pipelines with appropriate models. We demonstrate its effectiveness in generating pipelines from ambiguous user queries, using both human-curated and synthetic data. A detailed error analysis highlights ongoing challenges in pipeline building.
Bel Esprit is available for a free trial at https://belesprit.aixplain.com.

Bel Esprit: Multi-Agent Framework for Building AI Model Pipelines

The rapid advancement of large language models (LLMs) has unlocked transformative potential for role-playing emotional companion products, enabling systems that address emotional well-being, educational goals, and therapeutic applications. However, existing approaches lack sustained personalization or contextual adaptability, limiting their real-world utility.
In this paper, we introduce iPET, an LLM-powered pet agent that enhances user engagement by offering rich pet lifestyles and user preference-oriented interactions.
The iPet consists of a dialogue module that instantiates virtual pet agents for emotionally interactive conversations, a memory module stores and synthesizes records of agent and user experiences, and a world simulation module generating diverse, preference-driven pet behaviors guided by high-level reflections. Deployed for over 200 days in a real-world non-commercial product, iPET has served millions of users, delivering emotional support to psychologically distressed individuals while validating its effectiveness in practical applications.

iPET: An Interactive Emotional Companion Dialogue System with LLM-Powered Virtual Pet World Simulation

Advertisement (Ad) video violation detection is critical for ensuring platform compliance, but existing methods struggle with precise temporal grounding, noisy annotations, and limited generalization. We propose RAVEN, a novel framework that integrates curriculum reinforcement learning with multimodal large language models (MLLMs) to enhance reasoning and cognitive capabilities for violation detection. RAVEN employs a progressive training strategy, combining precisely and coarsely annotated data, and leverages Group Relative Policy Optimization (GRPO) to develop emergent reasoning abilities without explicit reasoning annotations. Multiple hierarchical sophisticated reward mechanism ensures precise temporal grounding and consistent category prediction. Experiments on industrial datasets and public benchmarks show that RAVEN achieves superior performances in violation category accuracy and temporal interval localization. We also design a pipeline to deploy the RAVEN on the online Ad services, and online A/B testing further validates its practical applicability, with significant improvements in precision and recall. RAVEN also demonstrates strong generalization, mitigating the catastrophic forgetting issue associated with supervised fine-tuning.

RAVEN: Robust Advertisement Video Violation Temporal Grounding via Reinforcement Reasoning

Recommender systems play a central role in numerous real-life applications, yet evaluating their performance remains a significant challenge due to the gap between offline metrics and online behaviors. Given the scarcity and limits (e.g., privacy issues) of real user data, we introduce SimUSER, an agent framework that serves as believable and cost-effective human proxies. SimUSER first identifies self-consistent personas from historical data, enriching user profiles with unique backgrounds and personalities. Then, central to this evaluation are users equipped with persona, memory, perception, and brain modules, engaging in interactions with the recommender system. SimUSER exhibits closer alignment with genuine humans than prior work, both at micro and macro levels. Additionally, we conduct insightful experiments to explore the effects of thumbnails on click rates, the exposure effect, and the impact of reviews on user engagement. Finally, we refine recommender system parameters based on offline A/B test results, resulting in improved user engagement in the real world.

SimUSER: Simulating User Behavior with Large Language Models for Recommender System Evaluation

Despite advances in unsupervised log anomaly detection, current models require dataset-specific training, causing costly procedures, limited scalability, and performance bottlenecks. Furthermore, numerous models lack cognitive reasoning abilities, limiting their transferability to similar systems. Additionally, these models often encounter the **"identical shortcut"** predicament, erroneously predicting normal classes when confronted with rare anomaly logs due to reconstruction errors. To address these issues, we propose **MLAD**, a novel **M**ulti-system **L**og **A**nomaly **D**etection model incorporating semantic relational reasoning. Specifically, we extract cross-system semantic patterns and encode them as high-dimensional learnable vectors. Subsequently, we revamp attention formulas to discern keyword significance and model the overall distribution through vector space diffusion. Lastly, we employ a Gaussian mixture model to highlight rare word uncertainty, optimizing the vector space with maximum expectation. Experiments on real-world datasets demonstrate the superiority of MLAD.

Towards Multi-System Log Anomaly Detection

Referred to as LLM-as-judge, a generative large language model (LLM) has demonstrated considerable efficacy as an evaluator in various tasks, including Machine Translation (MT) by predicting scores or identifying error types for individual sentences. However, its dependability in practical application has yet to be demonstrated, as there is only an approximated match due to the task's open-ended nature. To address this problem, we introduce a straightforward and novel meta-evaluation strategy PromptCUE and evaluate cutting-edge LLM-as-judge models such as GEMBA-MQM. We identify their fundamental deficits, including certain label biases and the inability to assess near-perfect translations.

To improve reliability, we investigate more trustworthy and less biased models using multidimensional prompt engineering. Our findings indicate that the combination of span-level error quantification and a rubric-style prompt tailored to the characteristics of LLMs has efficiently addressed the majority of the challenges current LLM-as-judge models face. Furthermore, it demonstrates a considerably enhanced alignment with human values. Accordingly, we present Rubric-MQM, the LLM-as-judge for high-end models and an updated version of GEMBA-MQM.

RUBRIC-MQM : Span-Level LLM-as-judge in Machine Translation For High-End Models

Retrieval Augmented Generation (RAG) has emerged as a powerful application of Large Language Models (LLMs), revolutionizing information search and consumption. RAG systems combine traditional search capabilities with LLMs to generate comprehensive answers to user queries, ideally with accurate citations. However, in our experience of developing a RAG product, LLMs often struggle with source attribution, aligning with other industry studies reporting citation accuracy rates of only about 74\% for popular generative search engines. To address this, we present efficient post-processing algorithms to improve citation accuracy in LLM-generated responses, with minimal impact on latency and cost. Our approaches cross-check generated citations against retrieved articles using methods including keyword + semantic matching, fine tuned model with BERTScore, and a lightweight LLM-based technique. Our experimental results demonstrate a relative improvement of 15.46\% in the overall accuracy metrics of our RAG system. This significant enhancement potentially enables a shift from our current larger language model to a relatively smaller model that is approximately 12x more cost-effective and 3x faster in inference time, while maintaining comparable performance. This research contributes to enhancing the reliability and trustworthiness of AI-generated content in information retrieval and summarization tasks which is critical to gain customer trust especially in commercial products.

CiteFix: Enhancing RAG Accuracy Through Post-Processing Citation Correction

This paper introduces Light-R1, an opensource suite for training long reasoning modelsusing reproducible and cost-effective methodology. Given the proprietary nature of data usedin the DeepSeek-R1 series, we develop an alternative approach leveraging exclusively publicdata and models. Our curriculum training progressively increases data difficulty, combinedwith multi-staged post-training. Our LightR1-32B model, trained from Qwen2.5-32BInstruct, outperforms DeepSeek-R1-DistillQwen-32B in math reasoning. Experimental results show that this curriculum approachbecomes more effective when distinct, diverse datasets are available for different training stages: fine-tuning DeepSeek-R1-Distilledmodels (pre-tuned by DeepSeek team on proprietary data) with 3,000 challenging examplesfrom our curriculum dataset yielded state-ofthe-art 7B and 14B models, while the 32Bmodel, Light-R1-32B-DS performed comparably to QwQ-32B and DeepSeek-R1. Furthermore, we extend our work by applying GRPOon long reasoning models. Our final Light-R1-14B-DS achieves SOTA performance among14B models in math, with AIME24 & 25 scoresof 74.0 and 60.2 respectively, surpassing many32B models and DeepSeek-R1-Distill-Llama70B. Despite math-focused training, Light-R1-14B-DS demonstrates strong cross-domain generalization. Light-R1 represents a significantadvancement in making sophisticated reasoning models more accessible and implementablein real-world applications. Our models, training data and code have been made available.

Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Discovering and evaluating long-form talk content such as videos and podcasts poses a significant challenge for users, as it requires a considerable time investment. Previews offer a practical solution by providing concise snippets that showcase key moments of the content, enabling users to make more informed and confident choices. We propose an LLM-based approach for generating podcast episode previews and deploy the solution at scale, serving hundreds of thousands of podcast previews in a real-world application. Comprehensive offline evaluations and online A/B testing demonstrate that LLM-generated previews consistently outperform a strong baseline built on top of various ML expert models, showcasing a significant reduction in the need for meticulous feature engineering. The offline results indicate notable enhancements in understandability, contextual clarity, and interest level, and the online A/B test shows a 4.6% increase in user engagement with preview content, along with a 5x boost in processing efficiency, offering a more streamlined and performant solution compared to the strong baseline of feature-engineered expert models.

Transforming Podcast Preview Generation: From Expert Models to LLM-Based Systems

Transformer-based large language models (LLMs) encounter challenges in processing long sequences on edge devices due to the quadratic complexity of attention mechanisms and growing memory demands from Key-Value (KV) cache. Existing KV cache optimizations struggle with irreversible token eviction in long-output tasks, while alternative sequence modeling architectures prove costly to adopt within established Transformer infrastructure. We present EdgeInfinite, a memory-efficient solution for infinite contexts that integrates compressed memory into Transformer-based LLMs through a trainable memory-gating module. This approach maintains full compatibility with standard Transformer architectures, requiring fine-tuning only a small part of parameters, and enables selective activation of the memory-gating module for long and short context task routing. The experimental result shows that EdgeInfinite achieves comparable performance to baseline Transformer-based LLM on long context benchmarks while optimizing memory consumption and time to first token.

Downloads

Next from ACL 2025

Bel Esprit: Multi-Agent Framework for Building AI Model Pipelines

Similar lecture

Priority on High-Quality: Selecting Instruction Data via Consistency Verification of Noise Injection