Austria

Large language models have shown remarkable performance across a wide range of language tasks, owing to their exceptional capabilities in context modeling. The most commonly used method of context modeling is full self-attention, as seen in standard decoder-only Transformers. Although powerful, this method can be inefficient for long sequences and may overlook inherent input structures. To address these problems, an alternative approach is parallel context encoding, which splits the context into sub-pieces and encodes them parallelly. Because parallel patterns are not encountered during training, naively applying parallel encoding leads to performance degradation. However, the underlying reasons and potential mitigations are unclear. In this work, we provide a detailed analysis of this issue and identify that unusually high attention entropy can be a key factor. Furthermore, we adopt two straightforward methods to reduce attention entropy by incorporating attention sinks and selective mechanisms. Experiments on various tasks reveal that these methods effectively lower irregular attention entropy and narrow performance gaps. We hope this study can illuminate ways to enhance context modeling mechanisms.

ACL 2025

Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models

parallel context encoding

attention entropy

model analysis

## 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.

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)

Large language models (LLMs) have gained extended context windows through scaling positional encodings and lightweight continual pre-training. However, this often leads to degraded performance on short-text tasks, while the reasons for this degradation remain insufficiently explored. In this work, we identify two primary factors contributing to this issue: distribution drift in hidden states and attention scores, and catastrophic forgetting during continual pre-training. To address these challenges, we propose Long Context Pre-training with Restoration Distillation (LongReD), a novel approach designed to mitigate short-text performance degradation through minimizing the distribution discrepancy between the extended and original models. Besides training on long texts, LongReD distills the hidden state of selected layers from the original model on short texts. Additionally, LongReD also introduces a short-to-long distillation, aligning the output distribution on short texts with that on long texts by leveraging skipped positional indices. Experiments on common benchmarks demonstrate that LongReD effectively preserves the model's short-text performance while maintaining or even enhancing its long-context abilities.

LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation

Recent advancements in large language models (LLMs) have demonstrated their impressive generative capabilities, primarily due to their extensive parameterization, which enables them to encode vast knowledge. However, effectively integrating new knowledge into LLMs remains a major challenge. Current research typically first constructs novel knowledge datasets and then injects this knowledge into LLMs through various techniques. However, existing methods for constructing new datasets either rely on timestamps, which lack rigor, or use simple templates for synthesis, which are simplistic and do not accurately reflect the real world. To address this issue, we propose a novel knowledge dataset construction approach that simulates biological evolution using knowledge graphs to generate synthetic entities with diverse attributes, resulting in a dataset, NovelHuman. Systematic analysis on NovelHuman reveals that the intra-sentence position of knowledge significantly affects the acquisition of knowledge. Therefore, we introduce an intra-sentence permutation to enhance knowledge acquisition. Furthermore, given that potential conflicts exist between autoregressive (AR) training objectives and permutation-based learning, we propose PermAR, a permutation-based language modeling framework for AR models. PermAR seamlessly integrates with mainstream AR architectures, endowing them with bidirectional knowledge acquisition capabilities. Extensive experiments demonstrate the superiority of PermAR, outperforming knowledge augmentation methods by 3.3%-38%.

Acquisition and Application of Novel Knowledge in Large Language Models

In this work, we prove the NP-completeness of two variants of tokenisation, defined here as the problem of compressing a dataset to at most $\delta$ symbols by either finding a vocabulary directly (_direct_ tokenisation), or selecting a sequence of merge operations (_bottom-up_ tokenisation).

Tokenisation is NP-Complete

Abstention, the refusal of large language models (LLMs) to provide an answer, is increasingly recognized for its potential to mitigate hallucinations and enhance safety in LLM systems. In this survey, we introduce a framework to examine abstention from three perspectives: the query, the model, and human values. We organize the literature on abstention methods, benchmarks, and evaluation metrics using this framework, and discuss merits and limitations of prior work. We further identify and motivate areas for future work, centered around whether abstention can be achieved as a meta-capability that transcends specific tasks or domains, while still providing opportunities to optimize abstention abilities based on context.

Know Your Limits: A Survey of Abstention in Large Language Models

Low-Rank Adaptation (LoRA) is a popular technique for efficient fine-tuning of foundation models. However, applying LoRA in federated learning environments, where data is distributed across multiple clients, presents unique challenges. Existing methods rely on traditional federated averaging of LoRA adapters, resulting in inexact updates. To address this, we propose Federated Exact LoRA, or FedEx-LoRA, which adds a residual error term to the pre-trained frozen weight matrix. Our approach achieves exact updates with minimal computational and communication overhead, preserving LoRA’s efficiency. We evaluate the method on various models across arithmetic reasoning, commonsense reasoning, natural language understanding and natural language generation tasks, showing consistent performance gains over state-of-the-art methods across multiple settings. Through extensive analysis, we quantify that the deviations in updates from the ideal solution are significant, highlighting the need for exact aggregation. Our method's simplicity, efficiency, and broad applicability position it as a promising solution for accurate and effective federated fine-tuning of foundation models.

FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Large Language Models

The rapid growth in the parameters of LLMs has made inference latency a fundamental bottleneck. Speculative decoding represents a lossless approach to accelerate inference through a guess-and-verify paradigm. Some methods rely on additional architectures to guess draft tokens, which need extra training before use. Alternatively, retrieval-based train-free techniques build libraries from pre-existing corpora or by n-gram generation. However, they face challenges like large storage requirements, time-consuming retrieval, and limited adaptability. Observing that candidate tokens generated during the decoding process are likely to reoccur in future sequences, we propose Token Recycling. This approach stores candidate tokens in an adjacency matrix and employs a breadth-first-search (BFS)-like algorithm to construct a draft tree, which is then validated through tree attention. New candidate tokens from the decoding process are then used to update the matrix. Token Recycling requires <2MB of additional storage and achieves approximately 2x speedup across all sizes of LLMs. It significantly outperforms existing train-free methods by 30% and even a training method by 25%.

Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling

The composition of pre-training datasets for large language models (LLMs) remains largely undisclosed, hindering transparency and efforts to optimize data quality—a critical driver of model performance. Current data selection methods, such as natural language quality assessments, diversity-based filters, and classifier-based approaches, are limited by single-dimensional evaluation or redundancy-focused strategies. To address these gaps, we propose four dimensions to evaluate data quality: professionalism, readability, reasoning, and cleanliness. We further introduce \textbf{Meta-rater}, a multi-dimensional data selection method that integrates these dimensions with existing quality metrics through learned optimal weightings. Meta-rater employs proxy models to train a regression model that predicts validation loss, enabling the identification of optimal combinations of quality scores. Experiments demonstrate that Meta-rater \textbf{doubles convergence speed} for 1.3B parameter models and improves downstream task performance by \textbf{3.23\%}, with advantages that scale to models as large as 7.2B parameters. Our work establishes that holistic, multi-dimensional quality integration significantly outperforms conventional single-dimension approaches, offering a scalable paradigm for enhancing pre-training efficiency and model capability. To advance future research, we release scripts, data, and models at \url{https://github.com/opendatalab/Meta-rater}.

Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models

Parameter-efficient fine-tuning (PEFT) has become a common method for fine-tuning large language models, where a base model can serve multiple users through PEFT module switching. To enhance user experience, base models require periodic updates. However, once updated, PEFT modules fine-tuned on previous versions often suffer substantial performance degradation on newer versions. Re-tuning these numerous modules to restore performance would incur significant computational costs. Through a comprehensive analysis of the changes that occur during base model updates, we uncover an interesting phenomenon: continual training primarily affects task-specific knowledge stored in Feed-Forward Networks (FFN), while having less impact on the task-specific pattern in the Attention mechanism. Based on these findings, we introduce Trans-PEFT, a novel approach that enhances the PEFT module by focusing on the task-specific pattern while reducing its dependence on certain knowledge in the base model. Further theoretical analysis supports our approach. Extensive experiments across 7 base models and 12 datasets demonstrate that Trans-PEFT trained modules can maintain performance on updated base models without re-tuning, significantly reducing maintenance overhead in real-world applications.

Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models

Language model (LM) distillation aims at distilling the knowledge in a large teacher LM to a small student one. As a critical issue facing LM distillation, a superior student often arises from a teacher of a relatively small scale instead of a larger one, especially in the presence of substantial capacity gap between the teacher and student. This issue, often referred to as the \textit{curse of capacity gap}, suggests that there is likely an optimal teacher yielding the best-performing student along the scaling course of the teacher. Consequently, distillation trials on teachers of a wide range of scales are called for to determine the optimal teacher, which becomes computationally intensive in the context of large LMs (LLMs). This paper addresses this critical bottleneck by providing the \textit{law of capacity gap} inducted from a preliminary study on distilling a broad range of small-scale (<3B) LMs, where the optimal teacher consistently scales linearly with the student scale across different model and data scales. By extending the law to LLM distillation on a larger scale (7B), we succeed in obtaining versatile LLMs that outperform a wide array of competitors.

Towards the Law of Capacity Gap in Distilling Language Models

Large Language Models (LLMs) have advanced rapidly but face significant memory demands. While quantization has shown promise for LLMs, current methods typically require lengthy training to alleviate the performance degradation from quantization loss. However, deploying LLMs across diverse scenarios with different resource constraints, e.g., servers and personal computers, requires repeated training per application, which amplifies the lengthy training problem. Given that, it is advantageous to train a once-for-all (OFA) supernet capable of yielding diverse optimal subnets for downstream applications through one-shot training. Nonetheless, the scale of current language models impedes efficiency and amplifies interference from weight sharing between subnets. We make an initial attempt to extend the once-for-all framework to large language models. Specifically, we decouple shared weights to eliminate the interference and incorporate Low-Rank adapters for training efficiency. Furthermore, we observe the imbalance allocation of training resources from the traditional uniform sampling. A non-parametric scheduler is introduced to adjust the sampling rate for each quantization configuration, achieving a more balanced allocation among subnets with varying demands. We validate the approach on LLaMA2 families and Mistral on downstream evaluation, demonstrating high performance while significantly reducing deployment time faced with multiple scenarios.

Downloads

Next from ACL 2025

LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation

Similar lecture

Variance Sensitivity Induces Attention Entropy Collapse and Instability in Transformers