Austria

Post-training is essential for enabling large language models (LLMs) to follow human instructions. However, its effectiveness depends on high-quality instruction data, which is challenging to obtain in the real world due to privacy concerns, data scarcity, and high annotation costs. To fill this gap, inspired by the recent success of using LLMs to simulate human society, we propose MATRIX, a multi-agent simulator that automatically generates diverse text-based scenarios, capturing a wide range of real-world human needs in a realistic and scalable manner. Leveraging these outputs, we introduce a novel scenario-driven instruction generator MATRIX-Gen for controllable and highly realistic data synthesis. Extensive experiments demonstrate that our framework effectively generates both general and domain-specific data. On AlpacaEval 2 and Arena-Hard benchmarks, Llama-3-8B-Base, post-trained on datasets synthesized by MATRIX-Gen with just 20K instruction-response pairs, outperforms Meta&#39;s Llama-3-8B-Instruct model, which was trained on over 10M pairs.

ACL 2025

Synthesizing Post-Training Data for LLMs through Multi-Agent Simulation

synthetic data

language modeling

fine-tuning

#### *Message from the General Chair, Aline Villavicencio*
I’m delighted and honoured to welcome you to the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026), taking place in the beautiful city of Rabat, in Morocco, in March 24-29, 2026. EACL is the flagship European conference of the Association and EACL 2026 proudly continues our field’s tradition of excellence in scholarship, innovation, and inclusivity. I am deeply grateful to the many volunteers whose dedication, generosity, and tireless efforts have made this conference possible.
For the first time EACL is being hosted in the African continent. This is an important milestone for our community, and we are grateful to our Moroccan hosts for enabling this historic moment by bringing this edition of EACL to Rabat. We are also delighted that the Second Arabic NLP School is co-located with EACL. We hope attendees enjoy this wonderful opportunity to strengthen ties with the Computational Linguistics communities across the African continent. *[Read full message](https://drive.google.com/file/d/14NlmHvwM6fPJuMmOvVh7K0vtQbEyv3SZ/view?usp=sharing)* 

<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://underline.io/events/522/reception','_blank')">Go to Workshops and Tutorials Program</button></html>

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 EACL 2026". 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 are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.eacl.org/registration/) first.

**Online Registration Form**: https://acl.swoogo.com/eacl2026

Registration Required

EACL 2026

Welcome to the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL). EACL 2026 will be held in Rabat, Morocco, from March 24–29, 2026. 

Post-training is essential for enabling large language models (LLMs) to follow human instructions. However, its effectiveness depends on high-quality instruction data, which is challenging to obtain in the real world due to privacy concerns, data scarcity, and high annotation costs. To fill this gap, inspired by the recent success of using LLMs to simulate human society, we propose MATRIX, a multi-agent simulator that automatically generates diverse text-based scenarios, capturing a wide range of real-world human needs in a realistic and scalable manner. Leveraging these outputs, we introduce a novel scenario-driven instruction generator MATRIX-Gen for controllable and highly realistic data synthesis. Extensive experiments demonstrate that our framework effectively generates both general and domain-specific data. On AlpacaEval 2 and Arena-Hard benchmarks, Llama-3-8B-Base, post-trained on datasets synthesized by MATRIX-Gen with just 20K instruction-response pairs, outperforms Meta's Llama-3-8B-Instruct model, which was trained on over 10M pairs.

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.

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)

Recent advancements in large language models (LLMs) have significantly improved the performance of multi-hop question answering (MHQA) systems. Despite the success of MHQA systems, the evaluation of MHQA is not deeply investigated. Existing evaluations mainly focus on comparing the final answers of the reasoning method and given ground-truths. We argue that the reasoning process should also be evaluated because wrong reasoning process can also lead to the correct final answers. Motivated by this, we propose a "Planner-Executor-Reasoner" (PER) architecture, which forms the core of the Plan-anchored Data Preprocessing (PER-DP) and the Plan-guided Multi-Hop QA (PER-QA).
The former provides the ground-truth of intermediate reasoning steps and final answers, and the latter offers them of a reasoning method. Moreover, we design a fine-grained evaluation metric called Plan-aligned Stepwise Evaluation (PSE), which evaluates the intermediate reasoning steps from two aspects: planning and solving. Extensive experiments on ten types of questions demonstrate competitive reasoning performance, improved explainability of the MHQA system, and uncover issues such as "fortuitous reasoning continuance" and "latent reasoning suspension" in RAG-based MHQA systems. Besides, we also demonstrate the potential of our approach in data contamination scenarios.

Beyond the Answer: Advancing Multi-Hop QA with Fine-Grained Graph Reasoning and Evaluation

This paper investigates the flow of factual information in Mamba State-Space Model (SSM)-based language models. We rely on theoretical and empirical connections to Transformer-based architectures and their attention mechanisms. Exploiting this relationship, we adapt attentional interpretability techniques originally developed for Transformers—specifically, the Attention Knockout methodology—to both Mamba-1 and Mamba-2. Using them we trace how information is transmitted and localized across tokens and layers, revealing patterns of subject-token information emergence and layer-wise dynamics. Notably, some phenomena vary between mamba models and Transformer based models, while others appear universally across all models inspected—hinting that these may be inherent to LLMs in general. By further leveraging Mamba’s structured factorization, we disentangle how distinct “features” either enable token-to-token information exchange or enrich individual tokens, thus offering a unified lens to understand Mamba internal operations.

Mamba Knockout for Unraveling Factual Information Flow

Recent remarkable advances in Large Language Models (LLMs) have led to innovations in various domains such as education, healthcare, and finance, while also raising serious concerns that they can be easily misused for malicious purposes. Most previous research has focused primarily on observing how jailbreak attack techniques bypass safety mechanisms like Reinforcement Learning through Human Feedback (RLHF). However, whether there are neurons within LLMs that directly govern aggression has not been sufficiently investigated. To fill this gap, this study identifies specific neurons (“aggression neurons”) closely related to the expression of aggression and systematically analyzes how manipulating them affects the model’s overall aggression. Specifically, using a large-scale synthetic text corpus (aggressive and non-aggressive), we measure the activation frequency of each neuron, then apply masking and activation techniques to quantitatively evaluate changes in aggression by layer and by manipulation ratio. Experimental results show that, in all models, manipulating only a small number of neurons can increase aggression by up to 33%, and the effect is even more extreme when aggression neurons are concentrated in certain layers. Moreover, even models of the same scale exhibit nonlinear changes in aggression patterns, suggesting that simple external safety measures alone may not be sufficient for complete defense.

Small Changes, Big Impact: How Manipulating a Few Neurons Can Drastically Alter LLM Aggression

This paper explores a novel perspective to speech quality assessment by leveraging natural language descriptions, offering richer, more nuanced insights than traditional numerical scoring methods. Natural language feedback provides instructive recommendations and detailed evaluations, yet existing datasets lack the comprehensive annotations needed for this approach. To bridge this gap, we introduce QualiSpeech, a comprehensive low-level speech quality assessment dataset encompassing 11 key aspects and detailed natural language comments that include reasoning and contextual insights. Additionally, we propose the QualiSpeech Benchmark to evaluate the low-level speech understanding capabilities of auditory large language models (LLMs). Experimental results demonstrate that finetuned auditory LLMs can reliably generate detailed descriptions of noise and distortion, effectively identifying their types and temporal characteristics. The results further highlight the potential for incorporating reasoning to enhance the accuracy and reliability of quality assessments. The dataset can be found at https://huggingface.co/datasets/tsinghua-ee/QualiSpeech.

QualiSpeech: A Speech Quality Assessment Dataset with Natural Language Reasoning and Descriptions

Instruction tuning for large language models (LLMs) can drive them to produce results consistent with human goals in specific downstream tasks. However, the process of continual instruction tuning (CIT) for LLMs may bring about the catastrophic forgetting (CF) problem, where previously learned abilities are degraded. Recent methods try to alleviate the CF problem by modifying models or replaying data, which may only remember the surface-level pattern of instructions and get confused on held-out tasks. In this paper, we propose a novel continual instruction tuning method based on Key-part Information Gain (KPIG). Our method computes the information gain on masked parts to dynamically replay data and refine the training objective, which enables LLMs to capture task-aware information relevant to the correct response and alleviate overfitting to general descriptions in instructions. In addition, we propose two metrics, P-score and V-score, to measure the generalization and instruction-following abilities of LLMs. Experiments demonstrate our method achieves superior performance on both seen and held-out tasks.

Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuning

Retrieval-augmented generation (RAG) has revitalized Large Language Models (LLMs) by injecting non-parametric factual knowledge. Compared with long-context LLMs, RAG is considered an effective summarization tool in a more concise and lightweight manner, which can interact with LLMs multiple times using diverse queries to get comprehensive responses. However, the LLM-generated historical responses, which contain potentially insightful information, are largely neglected and discarded by existing approaches, leading to suboptimal results. In this paper, we propose $\textit{graph of records}$ ($\textbf{GoR}$), which leverages historical responses generated by LLMs to enhance RAG for long-context global summarization. Inspired by the $\textit{retrieve-then-generate}$ paradigm of RAG, we construct a graph by establishing an edge between the retrieved text chunks and the corresponding LLM-generated response. To further uncover the intricate correlations between them, GoR features a $\textit{graph neural network}$ and an elaborately designed $\textit{BERTScore}$-based objective for self-supervised model training, enabling seamless supervision signal backpropagation between reference summaries and node embeddings. We comprehensively compare GoR with 12 baselines across four long-context summarization datasets, and the results indicate that our proposed method reaches the best performance ($\textit{e.g.}$, 15%, 8%, and 19% improvement over retrievers w.r.t. Rouge-L, Rouge-1, and Rouge-2 on the WCEP dataset). Extensive experiments further demonstrate the effectiveness of GoR.

Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs

The performance and usability of Large-Language Models (LLMs) are driving their use in explanation generation tasks. However, despite their widespread adoption, LLM explanations have been found to be unreliable, making it difficult for users to distinguish good from bad explanations. To address this issue, we present Rubrik’s CUBE--an education-inspired rubric and a dataset of 26k explanations, written and later quality-annotated using the rubric by both humans and six open- and closed-source LLMs. The CUBE dataset focuses on two reasoning and two language tasks, providing the necessary diversity for us to effectively test our proposed rubric. Using Rubrik, we find that explanations are influenced by both task and perceived difficulty. Low quality stems primarily from a lack of conciseness in LLM-generated explanations, rather than cohesion and word choice. The full dataset, rubric, and code are available at https://github.com/RubriksCube/rubriks_cube.

Rubrik's Cube: Testing a New Rubric for Evaluating Explanations on the CUBE dataset

While understanding the knowledge boundaries of LLMs is crucial to prevent hallucination, research on the knowledge boundaries of LLMs has predominantly focused on English. In this work, we present the first study to analyze how LLMs recognize knowledge boundaries across different languages by probing their internal representations when processing known and unknown questions in multiple languages. Our empirical studies reveal three key findings: 1) LLMs' perceptions of knowledge boundaries are encoded in the middle to middle-upper layers across different languages. 2) Language differences in knowledge boundary perception follow a linear structure, which motivates our proposal of a training-free alignment method that effectively transfers knowledge boundary perception ability across languages, thereby helping reduce hallucination risk in low-resource languages; 3) Fine-tuning on bilingual question pair translation further enhances LLMs' recognition of knowledge boundaries across languages. Given the absence of standard testbeds for cross-lingual knowledge boundary analysis, we construct a multilingual evaluation suite comprising three representative types of knowledge boundary data. Our code and datasets are publicly available at \url{https://github.com/DAMO-NLP-SG/LLM-Multilingual-Knowledge-Boundaries}.

Analyzing LLMs' Cognition of Knowledge Boundary Across Languages Through the Lens of Internal Representation

With the increasing interest in robotic synthesis in the context of organic chemistry, the automated extraction of chemical procedures from literature is critical. However, this task remains challenging due to the inherent ambiguity of chemical language and the high cost of human annotation required for developing reliable computer-aided extraction protocols. Here, we present \textbf{ChemActor}, a fully fine-tuned large language model (LLM), as a chemical executor to convert between unstructured experimental procedures and structured action sequences. We propose a sequential LLM-generated data framework to address the challenges of insufficient and low-quality annotated data. This framework integrates a data selection module that selects data based on distribution divergence, with a general-purpose LLM, to generate machine-executable actions from a single molecule input. Additionally, we introduce a novel multi-round LLMs circle review metric, which reflects the model's advanced understanding of chemical experimental procedures. Extensive experiments on reaction-to-description (R2D) and description-to-action (D2A) tasks demonstrate that ChemActor, augmented by LLM-generated data, achieves state-of-the-art performance, outperforming the baseline model by 10\%. The code is available at: https://github.com/Zhanghahah/ChemActor.

ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data

With the growing popularity of Large Language Models (LLMs) and vector databases, private textual data is increasingly processed and stored as numerical embeddings. However, recent studies have proven that such embeddings are vulnerable to inversion attacks, where original text is reconstructed to reveal sensitive information. Previous research has largely assumed access to millions of sentences to train attack models, e.g., through data leakage or nearly unrestricted API access. With our method, a single data point is sufficient for a partially successful inversion attack. With as little as 1k data samples, performance reaches an optimum across a range of black-box encoders, without training on leaked data. We present a Few-shot Textual Embedding Inversion Attack using Cross-Model **AL**ignment and **GEN**eration (__ALGEN__), by aligning victim embeddings to the attack space and using a generative model to reconstruct text. We find that __ALGEN__ attacks can be effectively transferred across domains and languages, revealing key information. We further examine a variety of defense mechanisms against **ALGEN**, and find that none are effective, highlighting the vulnerabilities posed by inversion attacks. By significantly lowering the cost of inversion and proving that embedding spaces can be aligned through one-step optimization, we establish a new textual embedding inversion paradigm with broader applications for embedding alignment in NLP.

Downloads

Next from ACL 2025

Beyond the Answer: Advancing Multi-Hop QA with Fine-Grained Graph Reasoning and Evaluation

Similar lecture

Beyond Sample-Level Feedback: Using Reference-Level Feedback to Guide Data Synthesis