Austria

The growing use of large language models (LLMs) for text generation has led to widespread concerns about AI-generated content detection. However, an overlooked challenge is AI-polished text, where human-written content undergoes subtle refinements using AI tools. This raises a critical question: should minimally polished text be classified as AI-generated? Such classification can lead to false plagiarism accusations and misleading claims about AI prevalence in online content. In this study, we systematically evaluate eleven state-of-the-art AI-text detectors using our &#39;AI-Polished-Text Evaluation (APT-Eval)&#39; dataset, which contains 15K samples refined at varying AI-involvement levels. Our findings reveal that detectors frequently flag even minimally polished text as AI-generated, struggle to differentiate between degrees of AI involvement, and exhibit biases against older and smaller models. These limitations highlight the urgent need for more nuanced detection methodologies.

ACL 2025

Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writing

human-written-text

machine-text

ai-polishing

text-detection

### Welcome to IJCNLP-AACL 2025! 
 It is a great honor to host this joint conference in Mumbai, India, from December 20 to 24, 2025. The joint conferences of IJCNLP and AACL are organized with alternating leadership in the Asia-Pacific region. The event is run by the Asian Federation of Natural Language Processing (AFNLP) in odd years, and by AACL in even years, while it is organized solely by ACL when the annual ACL meeting is held in the region. This year, the conference is primarily organized by AFNLP. 
*Kentaro Inui
MBZUAI, UAE
General Chair, IJCNLP-AACL 2025* 
Read full message and download the Conference Handbook [**here**](https://drive.google.com/file/d/1UTwxkAqSqI-GAoJC3wE1zZt5VP1Y8GX0/view?usp=sharing).

IJCNLP-AACL 2025

The 14th IJCNLP & 4th AACL will be held in Mumbai, India from December 20th to December 24th, 2025.

The growing use of large language models (LLMs) for text generation has led to widespread concerns about AI-generated content detection. However, an overlooked challenge is AI-polished text, where human-written content undergoes subtle refinements using AI tools. This raises a critical question: should minimally polished text be classified as AI-generated? Such classification can lead to false plagiarism accusations and misleading claims about AI prevalence in online content. In this study, we systematically evaluate eleven state-of-the-art AI-text detectors using our 'AI-Polished-Text Evaluation (APT-Eval)' dataset, which contains 15K samples refined at varying AI-involvement levels. Our findings reveal that detectors frequently flag even minimally polished text as AI-generated, struggle to differentiate between degrees of AI involvement, and exhibit biases against older and smaller models. These limitations highlight the urgent need for more nuanced detection methodologies.

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)

The architectural industry produces extensive documents, including method statements—expository documents that integrate multi-source data into actionable guidance. Manual drafting however is labor-intensive and time-consuming. This paper introduces ArchiDocGen, a multi-agent framework automating method statement generation. Unlike traditional approaches relying on static templates or single-pass generation, ArchiDocGen decomposes the task into three steps: outline generation, section-based content generation, and polishing, each handled by specialized agents. To provide domain expertise, ArchiDocGen employs a section-based retriever to fetch and synthesize relevant documents from its custom knowledge base. Each section is generated through iterative reasoning of a section-based chain-of-thought (SeCoT) scheme, followed by refinement to meet professional standards. To evaluate the generated method statements, we partner with the industry to establish a multi-dimensional evaluation system by combining automatic and empirical methods. Experiments show that ArchiDocGen achieves 4.38 ContentScore, excelling in specialization, completeness, organization, and clarity. Additionally, a web-based application for ArchiDocGen is developed and deployed with industry partners.

ArchiDocGen: Multi-Agent Framework for Expository Document Generation in the Architectural Industry

Enhancing computational efficiency and reducing deployment costs for large language models (LLMs) have become critical challenges in various resource-constrained scenarios. In this work, we present DistilQwen2.5, a family of distilled, lightweight LLMs derived from the public Qwen2.5 models. These distilled models exhibit enhanced instruction-following capabilities compared to the original models based on a series of distillation techniques that incorporate knowledge from much larger LLMs. In our industrial practice, we first leverage powerful proprietary LLMs with varying capacities as multi-agent teachers to select, rewrite, and refine instruction-response pairs that are more suitable for student LLMs to learn. After standard fine-tuning, we further leverage a computationally efficient model fusion approach that enables student models to progressively integrate fine-grained hidden knowledge from their teachers. Experimental evaluations demonstrate that the distilled models possess significantly stronger capabilities than their original checkpoints. Additionally, we present use cases to illustrate the applications of our framework in real-world scenarios. To facilitate practical use, we have released all the DistilQwen2.5 models to the open-source community.

DistilQwen2.5: Industrial Practices of Training Distilled Open Lightweight Language Models

We present MegaBeam-Mistral-7B\footnote{\url{https://huggingface.co/aws-prototyping/MegaBeam-Mistral-7B-512k}}, a language model that supports 512K-token context length. Our work addresses practical limitations in long-context training, supporting real-world tasks such as compliance monitoring and verification. Evaluated on three long-context benchmarks, our 7B-parameter model demonstrates superior in-context learning performance on HELMET and robust retrieval and tracing capability on RULER. It is currently the only open model to achieve competitive long-range reasoning on BABILong at 512K context length without RAG or targeted fine-tuning. Released as fully open source under the Apache 2.0 license, the model has been downloaded over 100,000 times on Hugging Face.

Scaling Context, Not Parameters: Training a Compact 7B Language Model for Efficient Long-Context Processing

Large Action Models (LAMs) for AI Agents offer incredible potential but face challenges due to the need for high-quality training data, especially for multi-steps tasks that involve planning, executing tool calls, and responding to feedback. To address these issues, we present LAM SIMULATOR, a comprehensive framework designed for online exploration of agentic tasks with high-quality feedback. Our framework features a dynamic task query generator, an extensive collection of tools, and an interactive environment where Large Language Model (LLM) Agents can call tools and receive real-time feedback. This setup enables LLM Agents to explore and solve tasks independently and potentially come up with multiple approaches to tackle any given task. Generated data are then used to create high-quality training datasets for LAMs.

Our research shows that LAM SIMULATOR enables LLM Agents to autonomously solve tasks while automating the creation of high-quality training data. Models trained with these self-generated datasets demonstrated significant performance gains, showing up to a 49.3% improvement over their own baselines. This was especially evident in experiments conducted with the ToolBench and CRMArena environments. The process requires minimal human input during dataset creation, highlighting the LAM SIMULATOR's efficiency and effectiveness in speeding up AI agents' development.

LAM SIMULATOR: Advancing Data Generation for Large Action Models Trainings via Online Exploration and Feedback Simulation

Natural Question Answering (QA) datasets play a crucial role in evaluating the capabilities of large language models (LLMs), ensuring their effectiveness in real-world applications. Despite the numerous QA datasets that have been developed and some work has been done in parallel, there is a notable lack of a framework and large scale region-specific datasets queried by native users in their own languages. This gap hinders the effective benchmarking and the development of fine-tuned models for regional and cultural specificities. In this study, we propose a scalable, language-independent framework, NativQA, to seamlessly construct culturally and regionally aligned QA datasets in native languages, for LLM evaluation and tuning. We demonstrate the efficacy of the proposed framework by designing a multilingual natural QA dataset, MultiNativQA, consisting of ~64k manually annotated QA pairs in seven languages, ranging from high to extremely low resource, based on queries from native speakers from 9 regions covering 18 topics. We benchmark open- and closed-source LLMs with the MultiNativQA dataset. We made the framework NativQA, MultiNativQA dataset, and other experimental scripts publicly available for the community (https://anonymous.com/).

NativQA: Multilingual Culturally-Aligned Natural Query for LLMs

Continuous prompts, or "soft prompts", are a widely-adopted parameter-efficient tuning strategy for large language models, but are often less favorable due to their opaque nature. Prior attempts to interpret continuous prompts relied on projecting individual prompt tokens onto the vocabulary space. However, this approach is problematic as performant prompts can yield arbitrary or contradictory text, and it individually interprets each prompt token. In this work, we propose a new approach to interpret continuous prompts that elicits textual descriptions from their representations during model inference. Using a Patchscopes variant (Ghandeharioun et al., 2024) called InSPEcT over various tasks, we show our method often yields accurate task descriptions which become more faithful as task performance increases. Moreover, an elaborated version of InSPEcT reveals biased features in continuous prompts, whose presence correlates with biased model predictions. Providing an effective interpretability solution, InSPEcT can be leveraged to debug unwanted properties in continuous prompts and inform developers on ways to mitigate them.

Eliciting Textual Descriptions from Representations of Continuous Prompts

Assessing the reproducibility of social science papers is essential for promoting rigor in research processes, but manual assessment is costly. With advancements in AI agents, we seek to evaluate their capability to automate this process. However, existing benchmarks for reproducing research papers (1) focus solely on reproducing results using given code and data without assessing their consistency with the paper, (2) oversimplify real-world scenarios, and (3) lack necessary diversity in data formats and programming languages. To address these issues, we introduce REPRO-Bench, a collection of 112 task instances, each representing a social science paper with a publicly available reproduction report. The agents are tasked with assessing the reproducibility of the paper based on the original paper PDF and the corresponding reproduction package. REPRO-Bench features end-to-end evaluation tasks with complexity comparable to real-world assessments on the reproducibility of social science papers. We evaluate three representative AI agents on REPRO-Bench, with the best-performing agent achieving an accuracy of only 21.4%. Building on our empirical analysis, we develop REPRO-Agent, which improves the highest accuracy achieved by existing agents by 71%. We conclude that more advanced AI agents should be developed to automate real-world reproducibility assessment. REPRO-Bench is publicly available as an anonymous dataset: https://huggingface.co/datasets/anonymous-submission-acl2025/REPRO-Bench. The evaluation code is hosted anonymously: https://anonymous.4open.science/r/REPRO-Bench-Code-2E98/.

REPRO-Bench: Can AI Agents Assess the Reproducibility of Social Science Papers?

We present an interesting application of narrative understanding in the clinical assessment of aphasia, where story retelling tasks are used to evaluate a patient's communication abilities. This clinical setting provides a framework to help operationalize narrative discourse analysis and an application-focused evaluation method for narrative understanding systems. In particular, we highlight the use of main concepts---a list of statements that capture a story's gist---for aphasic discourse analysis and propose the task of automatically generating MCs from novel stories, that can be edited manually by experts thus enabling wider adaptation of current assessment tools. We then develop a prompt ensemble method using large language models (LLMs) to automatically generate MCs for a given story. We evaluate our proposed method on an existing narrative summarization dataset and apply it to a set of stories that have been annotated with main concepts through extensive analysis of retells from non-aphasic and aphasic participants (Kurland et al., 2021). Our results show that our method can generate most of the gold-standard MCs for stories from this dataset. Finally, we release this dataset of these stories and their annotated MCs, to spur more research in this area.

Automated main concept generation for narrative discourse assessment in aphasia

Text-to-SQL aims to translate natural language queries into SQL statements, which is practical as it enables anyone to easily retrieve the desired information from databases. Recently, many existing approaches tackle this problem with Large Language Models (LLMs), leveraging their strong capability in understanding user queries and generating corresponding SQL code. Yet, the parametric knowledge in LLMs might be limited to covering all the diverse and domain-specific queries that require grounding in various database schemas, which makes generated SQLs less accurate oftentimes. To tackle this, we propose constructing the knowledge base for text-to-SQL, a foundational source of knowledge, from which we retrieve and generate the necessary knowledge for given queries. In particular, unlike existing approaches that either manually annotate knowledge or generate only a few pieces of knowledge for each query, our knowledge base is comprehensive, which is constructed based on a combination of all the available questions and their associated database schemas along with their relevant knowledge, and can be reused for unseen databases from different datasets and domains. We validate our approach on multiple text-to-SQL datasets, considering both the overlapping and non-overlapping database scenarios, where it outperforms relevant baselines substantially.

Knowledge Base Construction for Knowledge-Augmented Text-to-SQL

Generating cell-level descriptions for Jupyter Notebooks, which is a major resource consisting of codes, tables, and descriptions, has been attracting increasing research attention. However, existing methods for Jupyter Notebooks mostly focus on generating descriptions from code snippets or table outputs independently. On the other side, descriptions should be personalized as users have different purposes in different scenarios while previous work ignored this situation during description generation. In this work, we formulate a new task, personalized description generation with code, tables,and user-written guidelines in Jupyter Notebooks. To evaluate this new task, we collect and propose a benchmark, namely NBDESCRIB, containing code, tables, and user-written guidelines as inputs and personalized descriptions as targets. Extensive experiments show that while existing models of text generation are able to generate fluent and readable descriptions, they still struggle to produce factually correct descriptions without user-written guidelines. CodeT5 achieved the highest scores in Orientation (1.27) and Correctness (-0.43) among foundation models in human evaluation, while the ground truth scored higher in Orientation (1.45) and Correctness (1.19). Common error patterns involve misalignment with guidelines, incorrect variable values, omission of im-031 portant code information, and reasoning errors.032 Moreover, ablation studies show that adding guidelines significantly enhances performance, both qualitatively and quantitatively.

Downloads

Next from ACL 2025

ArchiDocGen: Multi-Agent Framework for Expository Document Generation in the Architectural Industry

Similar lecture

Fine-Grained Detection of AI-Generated Text Using Sentence-Level Segmentation