Austria

RAG systems rely on rerankers to identify relevant documents. However, fine-tuning these models remains challenging due to the scarcity of annotated query-document pairs. Existing distillation-based approaches suffer from training-inference misalignment and fail to capture interdependencies among candidate documents. To overcome these limitations, we reframe the reranking process as an attention-mask problem and propose Gumbel Reranking, an end-to-end training framework for rerankers aimed at minimizing the training-inference gap. In our approach, reranker optimization is reformulated as learning a stochastic, document-wise Top-$k$ attention mask using the Gumbel Trick and Relaxed Top-$k$ Sampling. This formulation enables end-to-end optimization by minimizing the overall language loss. Experiments across various settings consistently demonstrate performance gains, including a 10.4% improvement in recall on HotpotQA for distinguishing indirectly relevant documents.

ACL 2025

Gumbel Reranking: Differentiable End-to-End Reranker Optimization

reranking

information retrieval

It is my great pleasure and honor to welcome you to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), held in San Diego, California, USA, July 2–7, 2026. ACL 2026 continues our fields 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.

It is exciting to see the many developments in the field reflected at our conference, such as the advancement of large language models (born out of our community) into many application directions. This is not without challenges, partly due to unsolved problems, and partly due to misuse of the technology. All this is reflected well at ACL 2026. The conference also reflects that the field is not only about advancing technology, but also the science of fundamentally understanding language and how it is use by many different speaker communities. 
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/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://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing')">Conference Handbook</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 ACL 2026". 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 are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.aclweb.org/registration/) first.

Registration Required

ACL 2026

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

technical paper

### 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)

Knowledge neuron theory provides a key approach to understanding the mechanisms of factual knowledge in Large Language Models (LLMs), which suggests that facts are stored within multi-layer perceptron neurons. This paper further explores **Degenerate Knowledge Neurons** (DKNs), where distinct sets of neurons can store identical facts, but unlike simple redundancy, they also participate in storing other different facts. Despite the novelty and unique properties of this concept, it has not been rigorously defined and systematically studied. Our contributions are: (1) We pioneer the study of structures in knowledge neurons by analyzing weight connection patterns, providing a comprehensive definition of DKNs from both functional and structural aspects. (2) Based on this definition, we develop the **Neuronal Topology Clustering** method, leading to a more accurate DKN identification. (3) We demonstrate the practical applications of DKNs in two aspects: guiding LLMs to learn new knowledge and relating to LLMs' robustness against input errors.

Cracking Factual Knowledge: A Comprehensive Analysis of Degenerate Knowledge Neurons in Large Language Models

We demonstrate that features, rather than neurons, serve as superior analytical units for understanding the mechanisms of factual knowledge in Language Models (LMs). Previous studies primarily utilize MLP neurons as units of analysis; however, neurons suffer from polysemanticity, leading to limited knowledge expression and poor interpretability. We first conduct preliminary experiments to validate that SAE can effectively decompose neurons into features. With this established, our core findings reveal three key advantages of features over neurons: (1) Features exhibit stronger influence on knowledge expression and superior interpretability. (2) Features demonstrate enhanced monosemanticity, showing distinct activation patterns between related and unrelated facts. (3) Feature-based method demonstrates superior performance over neuron-based approaches in erasing privacy-sensitive information from LMs. Additionally, we propose FeatureEdit, the first feature-based editing method. Code and dataset will be available.

The Knowledge Microscope: Features as Better Analytical Lenses than Neurons

Knowledge Graph Embedding (KGE) is a common approach for Knowledge Graphs (KGs) in AI tasks. Embedding dimensions depend on application scenarios. Requiring a new dimension means training a new KGE model from scratch, increasing cost and limiting efficiency and flexibility. In this work, we propose a novel KGE training framework MED. It allows one training to obtain a croppable KGE model for multiple scenarios with different dimensional needs. Sub-models of required dimensions can be directly cropped and used without extra training. In MED, we propose a mutual learning mechanism to improve the low-dimensional sub-models and make high-dimensional sub-models retain the low-dimensional sub-models' capacity, an evolutionary improvement mechanism to promote the high-dimensional sub-models to master the triple that the low-dimensional sub-models can not, and a dynamic loss weight to adaptively balance the multiple losses. Experiments on 4 KGE models across 4 standard KG completion datasets, 3 real-world scenarios using a large-scale KG, and extending MED to the BERT language model demonstrate its effectiveness, high efficiency, and flexible extensibility.

Croppable Knowledge Graph Embedding

Automatically generating high-quality mathematical problems that align with educational objectives is a crucial task in NLP-based educational technology. Traditional generation methods focus primarily on textual quality, but they often overlook educational objectives. Moreover, these methods address only single-dimensional, simple question generation, failing to meet complex, multifaceted educational requirements. To address these challenges, we constructed and annotated EduMath, a dataset of 16k mathematical questions with multi-dimensional educational objectives. Based on this dataset, we developed EQGEVAL, which incorporates three evaluation dimensions and is designed to assess the ability of models to generate educational questions. Drawing inspiration from teachers' problem design processes, we propose the Educational Question Planning with self-Reflection (EQPR) method for educational mathematical question generation, following a "plan-evaluate-optimize" approach. Specifically, by combining planning algorithm based on Monte Carlo Tree Search with the generative capabilities of Large Language Models, we continuously optimize questions through iterative feedback. This self-optimization mechanism ensures that the generated questions both fit the educational context and strategically achieve specific basic educational objectives. Through extensive experiments based on EQGEVAL, we have demonstrated that EQPR achieves significant improvements in generating questions that meet multi-dimensional educational objectives.

From Objectives to Questions: A Planning-based Framework for Educational Mathematical Question Generation

Simultaneous speech translation (SST) outputs translations in parallel with streaming speech input, balancing translation quality and latency. While large language models (LLMs) have been extended to handle the speech modality, streaming remains challenging as speech is pre-pended as a prompt for the entire generation process. To unlock LLM streaming capability, this paper proposes SimulS2S-LLM, which trains speech LLMs offline and employs a test-time policy to guide simultaneous inference. SimulS2S-LLM alleviates the mismatch between training and inference by extracting boundary-aware speech prompts that allows it to be better matched with text input data. SimulS2S-LLM achieves simultaneous speech-to-speech translation (Simul-S2ST) by predicting discrete output speech tokens and then synthesising output speech using a pre-trained vocoder. An incremental beam search is designed to expand the search space of speech token prediction without increasing latency. Experiments on the CVSS speech data show that SimulS2S-LLM offers a better translation quality-latency trade-off than existing methods that use the same training data, such as improving ASR-BLEU scores by 3 points at similar latency.

SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation

Supervised fine-tuning (SFT) has enabled large language models (LLMs) to exhibit promising performance on various tasks. However, this fine-tuning process only compares current predictions and labels on each sample, yet fails to perceive and understand its error outputs from different degrees, which may potentially produce a large percentage of serious errors. This poses a problem for aspect-based sentiment analysis (ABSA) in that these serious errors bring a greater negative impact than acceptable ones. Humans tend to compare mistakes to understand the varying degrees of mistakes, thus avoiding major bad decisions. Inspired by this, we propose a simple yet effective framework that could perceive and understand the degree of different errors by learning from comparative error pairs. It utilizes the SFT model to yield multiple outputs on each sample and selects acceptable and severe errors based on the acceptable scores. Together with the labels, we construct two comparative error pairs and exploit their calibration losses to optimize parameters. We conduct comprehensive experiments on ABSA datasets to demonstrate the effectiveness of our framework over baselines.

Error Comparison Optimization for Large Language Models on Aspect-Based Sentiment Analysis

Current Large Language Models excel in general reasoning yet struggle with specialized tasks requiring proprietary or domain-specific knowledge. Fine-tuning large models for every niche application is often infeasible due to black-box constraints and high computational overhead. To address this, we propose a collaborative framework that pairs a specialized weak model with a general strong model. The weak model, tailored to specific domains, produces initial drafts and background information, while the strong model leverages its advanced reasoning to refine these drafts, extending LLMs’ capabilities to critical yet specialized tasks. To optimize this collaboration, we introduce a collaborative feedback to fine-tunes the weak model, which quantifies the influence of the weak model’s contributions in the collaboration procedure and establishes preference pairs to guide preference tuning of the weak model. We validate our framework through experiments on three domains. We find that the collaboration significantly outperforms each model alone by leveraging complementary strengths. Moreover, aligning the weak model with the collaborative preference further enhances overall performance.

Synergistic Weak-Strong Collaboration by Aligning Preferences

Most current automated essay quality assessment systems treat score prediction and feedback generation as separate tasks, overlooking the fact that scores provide a quantitative evaluation of quality, while feedback offers a qualitative assessment. Both aspects reflect essay quality from different perspectives, and they are inherently consistent and can reinforce each other. In this paper, we propose a novel bidirectional reinforcement learning framework that effectively utilizes this consistency constraint to jointly optimize score prediction and feedback generation, ensuring mutual reinforcement and alignment between them. In this way, our model is hope to obtain a simultaneous accurate ratings and consistent text feedback. We conducted extensive experiments on publicly available datasets. The results demonstrate that our approach surpasses the current state-of-the-art models, enhancing both scoring accuracy and feedback quality.

CEAES: Bidirectional Reinforcement Learning Optimization for Consistent and Explainable Essay Assessment

We propose a training-free framework that enables large language models (LLMs) to effectively process long texts, using a divide-and-conquer strategy for comprehensive document understanding.
The proposed LLM$\times$MapReduce framework splits the entire document into several chunks for LLMs to read and then aggregates the intermediate outputs to produce the final response. The main challenge for divide-and-conquer long text processing frameworks lies in the risk of losing essential long-range information due to document splitting, which can lead the model to produce incomplete or incorrect answers based on the segmented texts.
Disrupted long-range information can be classified into two categories: inter-chunk dependency and inter-chunk conflict.
We design a structured information protocol to better cope with inter-chunk dependency and an in-context confidence calibration mechanism to resolve inter-chunk conflicts. Experiments demonstrate that LLM$\times$MapReduce outperforms representative open-source and commercial long-context LLMs and is compatible with several models.
Our framework can also function as a data synthesis engine, capable of generating high-quality long-alignment data using only short-context LLMs.

LLM×MapReduce: Simplified Long-Sequence Processing using Large Language Models

Evaluating Large Language Models (LLMs) requires effective methods to assess semantic consistency across multiple reversible transformations. Traditional self-consistency methods often fail to capture subtle semantic errors in multi-step tasks. We introduce ConsistencyChecker, a tree-based evaluation framework that measures LLMs' ability to preserve semantic consistency during reversible transformation processes, sidestepping benchmark data contamination issues. Our approach constructs self-consistency trees where nodes represent text states after transformations (e.g., translation, code modification, paraphrasing) and edges represent pairs of opposite transformations. By analyzing semantic preservation between nodes at different tree depths, ConsistencyChecker quantifies model reliability without requiring manually annotated reference data. Experiments demonstrate that ConsistencyChecker reliably measures generalization abilities across models from 1.5B to 72B parameters. On translation tasks, GPT-4o Mini achieves the highest L3 consistency score of 98.0%. For code generation, Qwen 2.5 32B leads with 85.1% semantic consistency at L3. Results show Pearson correlation greater than 0.7 between our embedding-based scores and WMT 2024 rankings on 4 out of 5 shared language pairs, validating the method's effectiveness for benchmarking LLM performance without constructing new datasets.

Downloads

Next from ACL 2025

Cracking Factual Knowledge: A Comprehensive Analysis of Degenerate Knowledge Neurons in Large Language Models

Similar lecture

Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning