China

We introduce HYDRA, a simple yet effective multi-head encoder-only architecture for hierarchical text classification that treats each level in the hierarchy as a separate classification task with its own label space. State-of-the-art approaches rely on complex components like graph encoders, label semantics, and autoregressive decoders. We demonstrate that such complexity is often unnecessary. Through parameter sharing and level-specific parameterization, HYDRA enables flat models to incorporate hierarchical awareness without architectural complexity. Experiments on four benchmarks (NYT, RCV1-V2, BGC, and WOS) demonstrate that HYDRA always increases the performance over flat models and matches or exceeds the performance of complex state-of-the-art methods.

EMNLP 2025

HYDRA: A Multi-Head Encoder-only Architecture for Hierarchical Text Classification

representation learning

hierarchical text classification

multi-task learning

## 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."<br>

*Message from the General Chair, Dirk Hovy*





<br>

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

poster

Simplifying complex texts is essential for ensuring equitable access to information, especially for individuals with cognitive impairments. The Easy-to-Read (ETR) initiative offers a framework for making content accessible to the neurodivergent population, but the manual creation of such texts remains time-consuming and resource-intensive. In this work, we investigate the potential of large language models (LLMs) to automate the generation of ETR content. To address the scarcity of aligned corpora and the specificity of ETR constraints, we propose a multi-task learning (MTL) approach that trains models jointly on text summarization, text simplification, and ETR generation. We explore two different strategies: multi-task retrieval-augmented generation (RAG) for in-context learning, and MTL-LoRA for parameter-efficient fine-tuning. Our experiments with Mistral-7B and LLaMA-3-8B, based on ETR-fr, a new high-quality dataset, demonstrate the benefits of multi-task setups over single-task baselines across all configurations. Moreover, results show that the RAG-based strategy enables generalization in out-of-domain settings, while MTL-LoRA outperforms all learning strategies within in-domain configurations. Our code is publically made available at https://anonymous.4open.science/r/ETR-MTL-C60E.

Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generation

Existing reinforcement learning (RL) strategies based on outcome supervision have proven effective in enhancing the performance of large language models (LLMs) for code generation. While reinforcement learning based on process supervision shows great potential in multi-step reasoning tasks, its effectiveness in the field of code generation still lacks sufficient exploration and verification. The primary obstacle stems from the resource-intensive nature of constructing a high-quality process-supervised reward dataset, which requires substantial human expertise and computational resources. To overcome this challenge, this paper proposes a "mutation/refactoring-execution verification" strategy. Specifically, the teacher model is used to mutate and refactor the statement lines or blocks, and the execution results of the compiler are used to automatically label them, thus generating a process-supervised reward dataset. Based on this dataset, we have carried out a series of RL experiments. The experimental results show that, compared with the method relying only on outcome supervision, reinforcement learning based on process supervision performs better in handling complex code generation tasks. In addition, this paper for the first time confirms the advantages of the Direct Preference Optimization (DPO) method in the RL task of code generation based on process supervision, providing new ideas and directions for code generation research.

Process-Supervised Reinforcement Learning for Code Generation

Sentiment Analysis (SA) tools harbor inherent social biases that can be harmful in real-world applications. These biases are identified by examining the output of SA models for sentences that only vary in the identity groups of the subjects. Constructing natural, linguistically rich, relevant, and diverse sets of sentences that provide sufficient coverage over the domain is expensive, especially when addressing a wide range of biases: it requires domain experts and/or crowd-sourcing. In this paper, we present a novel bias testing framework, BTC-SAM, which generates high-quality test cases for bias testing in SA models with minimal specification using Large Language Models (LLMs) for the controllable generation of test sentences. Our experiments show that relying on LLMs can provide high linguistic variation and diversity in the test sentences, thereby offering better test coverage compared to base prompting methods even for previously unseen biases.

BTC-SAM: Leveraging LLMs for Generation of Bias Test Cases for Sentiment Analysis Models

With the widespread adoption of Large Language Models (LLMs) across various applications, it is empirical to ensure their fairness across all user communities. However, most LLMs are trained and evaluated on Western centric data, with little attention paid to low-resource languages and regional contexts. To address this gap, we introduce PakBBQ, a culturally and regionally adapted extension of the original Bias Benchmark for Question Answering (BBQ) dataset. PakBBQ comprises over 214 templates, 17180 QA pairs across 8 categories in both English and Urdu, covering eight bias dimensions including age, disability, appearance, gender, socio-economic status, religious, regional affiliation, and language formality that are relevant in Pakistan. We evaluate multiple multilingual LLMs under both ambiguous and explicitly disambiguated contexts, as well as negative versus non negative question framings. Our experiments reveal (i) an average accuracy gain of 12% with disambiguation, (ii) consistently stronger counter bias behaviors in Urdu than in English, and (iii) marked framing effects that reduce stereotypical responses when questions are posed negatively. These findings highlight the importance of contextualized benchmarks and simple prompt engineering strategies for bias mitigation in low resource settings.

PakBBQ: A Culturally Adapted Bias Benchmark for QA

Recent research has shown that carefully crafted jailbreak inputs can induce large language models to produce harmful outputs, despite safety measures such as alignment. It is important to anticipate the range of potential Jailbreak attacks to guide effective defenses and accurate assessment of model safety. In this paper, we present a new approach for generating highly effective Jailbreak attacks that manipulate the attention of the model to selectively strengthen or weaken attention among different parts of the prompt. By harnessing attention loss, we develop more effective jailbreak attacks, that are also transferrable. The attacks amplify the success rate of existing Jailbreak algorithms, including GCG, AutoDAN, and ReNeLLM, while lowering their generation cost (for example, the amplified GCG attack achieves 91.2% ASR, vs. 67.9% for the original attack on Llama2-7B-chat/AdvBench, using less than a third of the generation time).

Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment

As one of the world's most populous countries, with 700 languages spoken, Indonesia is behind in terms of NLP progress. We introduce LORAXBENCH, a benchmark that focuses on low-resource languages of Indonesia and covers 6 diverse tasks: reading comprehension, open-domain QA, language inference, causal reasoning, translation, and cultural QA. Our dataset cover 20 languages, with the addition of two formality registers for three languages. We evaluate a diverse set of multilingual and region-focused LLMs and found that this benchmark is challenging. We note a visible discrepancy between performance in Indonesian and other languages, especially the low-resource ones. There is no clear lead when using a region-specific model as opposed to the general multilingual model. Lastly, we show that a change in register affects model performance, especially with registers not commonly found in social media, such as high-level politeness `Krama' Javanese.

LORAXBENCH: A Multitask, Multilingual Benchmark Suite for 20 Indonesian Languages

Compact dual-encoder models are widely used for retrieval owing to their efficiency and scalability. However, such models often underperform compared to their Large Language Model (LLM)-based retrieval counterparts, likely due to their limited world knowledge. While LLM-based data augmentation has been proposed as a strategy to bridge this performance gap, there is insufficient understanding of its effectiveness and scalability to real-world retrieval problems. Existing research does not systematically explore key factors such as the optimal augmentation scale, the necessity of using large augmentation models, and whether diverse augmentations improve generalization, particularly in out-of-distribution (OOD) settings. This work presents a comprehensive study of the effectiveness of LLM augmentation for retrieval, comprising over 100 distinct experimental settings of retrieval models, augmentation models and augmentation strategies. We find that, while augmentation enhances retrieval performance, its benefits diminish beyond a certain scale, even with diverse augmentation strategies. Surprisingly, we observe that augmentation with smaller LLMs can achieve performance competitive with larger augmentation models. Moreover, we examine how augmentation effectiveness varies with retrieval model pre-training, revealing that augmentation provides the most benefit to models which are not well pre-trained. Our insights pave the way for more judicious and efficient augmentation strategies, thus enabling informed decisions and maximizing retrieval performance while being more cost-effective.

Evaluating the Effectiveness and Scalability of LLM-Based Data Augmentation for Retrieval

Recent advances in large language models (LLMs) have demonstrated significant promise in document understanding and question-answering. Despite the progress, existing approaches can only process short documents due to limited context length or fail to fully leverage multi-modal information. In this work, we introduce DocAgent, a multi-agent framework for long-context document understanding that imitates human reading practice. Specifically, we first extract a structured, tree-formatted outline from documents to help agents identify relevant sections efficiently. Further, we develop an interactive reading interface that enables agents to query and retrieve various types of content dynamically. To ensure answer reliability, we introduce a reviewer agent that cross-checks responses using complementary sources and maintains a task-agnostic memory bank to facilitate knowledge sharing across tasks. We evaluate our method on two long-context document understanding benchmarks, where it bridges the gap to human-level performance by surpassing competitive baselines, while maintaining a short context length.

DocAgent: An Agentic Framework for Multi-Modal Long-Context Document Understanding

Software debugging is a time-consuming endeavor involving a series of steps, such as fault localization and patch generation, each requiring thorough analysis and a deep understanding of the underlying logic. While large language models (LLMs) demonstrate promising potential in coding tasks, their performance in debugging remains limited. Current LLM-based methods often focus on isolated steps and struggle with complex bugs. In this paper, we propose the first end-to-end framework, UniDebugger, for unified debugging through multi-agent synergy. It mimics the entire cognitive processes of developers, with each agent specialized as a particular component of this process rather than mirroring the actions of an independent expert as in previous multi-agent systems. Agents are coordinated through a three-level design, following a cognitive model of debugging, allowing adaptive handling of bugs with varying complexities. Experiments on extensive benchmarks demonstrate that UniDebugger significantly outperforms state-of-the-art repair methods, fixing 1.25x to 2.56x bugs on the repo-level benchmark, Defects4J. This performance is achieved without requiring ground-truth root-cause code statements, unlike the baselines. Our source code is available on an anonymous link: https://github.com/AcceptePapier/UniDebugger.

UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debugging

An Agentic AI Workflow (AAW), also known as an LLM-based multi-agent system, is an autonomous system that assembles several LLM-based agents to work collaboratively towards a shared goal. The high autonomy, widespread adoption, and growing interest in such AAWs highlight the need for a deeper understanding of their operations, from both quality and security aspects. To this day, there are no existing methods to assess the influence of each agent on the AAW's final output. Adopting techniques from related fields is not feasible since existing methods perform only static structural analysis, which is unsuitable for inference time execution. We present Counterfactual-based Agent Influence Ranker (CAIR) - the first method for assessing the influence level of each agent on the AAW's output and determining which agents are the most influential. By performing counterfactual analysis, CAIR provides a task-agnostic analysis that can be used both offline and at inference time. We evaluate CAIR using an AAWs dataset of our creation, containing 30 different use cases with 230 different functionalities. Our evaluation showed that CAIR produces consistent rankings, outperforms baseline methods, and can easily enhance the effectiveness and relevancy of downstream tasks.

Downloads

Next from EMNLP 2025

Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generation

Similar lecture

HydraRAG: Structured Cross-Source Enhanced Large Language Model Reasoning