Austria

LLMs encounter significant challenges in resource consumption nowadays, especially with long contexts. Despite extensive efforts dedicate to enhancing inference efficiency, these methods primarily exploit internal sparsity within the models, without leveraging external information for optimization. We identify the high similarity of attention matrices across different-scale LLMs, which offers a novel perspective for optimization. We first conduct a comprehensive analysis of how to measure similarity, how to select mapping Layers and whether mapping is consistency. Based on these insights, we introduce the IAM framework, which achieves dual benefits of accelerated attention computation and reduced KV cache usage by performing attention mapping between small and large LLMs. Our experimental results demonstrate that IAM can accelerate prefill by 15% and reduce KV cache usage by 22.1% without appreciably sacrificing performance. Experiments on different series of models show the generalizability of IAM. Importantly, it is also orthogonal to many existing KV cache optimization methods, making it a versatile addition to the current toolkit for enhancing LLM efficiency.

ACL 2025

IAM: Efficient Inference through Attention Mapping between Different-scale LLMs

attention mapping

efficient inference

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

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)

Jailbreaking attacks can effectively induce unsafe behaviors in Large Language Models (LLMs); however, the transferability of these attacks across different models remains limited. This study aims to understand and enhance the transferability of gradient-based jailbreaking methods, which are among the standard approaches for attacking white-box models. Through a detailed analysis of the optimization process, we introduce a novel conceptual framework to elucidate transferability and identify superfluous constraints—specifically, the response pattern constraint and the token tail constraint—as significant barriers to improved transferability. Removing these unnecessary constraints substantially enhances the transferability and controllability of gradient-based attacks. Evaluated on Llama-3-8B-Instruct as the source model, our method increases the overall Transfer Attack Success Rate (T-ASR) across a set of target models with varying safety levels from 18.4\% to 50.3\%, while also improving the stability and controllability of jailbreak behaviors on both source and target models.

Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints

Large Language Models (LLMs) are increasingly employed as automated evaluators to assess the safety of generated content, yet their reliability in this role remains uncertain. This study evaluates a diverse set of 11 LLM judge models across critical safety domains, examining three key aspects: self-consistency in repeated judging tasks, alignment with human judgments, and susceptibility to input artifacts such as apologetic or verbose phrasing. Our findings reveal that biases in LLM judges can significantly distort the final verdict on which content source is safer, undermining the validity of comparative evaluations. Notably, apologetic language artifacts alone can skew evaluator preferences by up to 98%. Contrary to expectations, larger models do not consistently exhibit greater robustness, while smaller models sometimes show higher resistance to specific artifacts. To mitigate LLM evaluator robustness issues, we investigate jury-based evaluations aggregating decisions from multiple models. Although this approach both improves robustness and enhances alignment to human judgements, artifact sensitivity persists even with the best jury configurations. These results highlight the urgent need for diversified, artifact-resistant methodologies to ensure reliable safety assessments.

Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts

Acoustic individual identification of wild animals is an essential task for understanding animal vocalizations within their social contexts, and for facilitating conservation and wildlife monitoring efforts. However, most of the work in this space relies on human efforts, as the development of methods for automatic individual identification is hindered by the lack of data. In this paper, we explore cross-species pre-training to address the task of individual classification in white-faced capuchin monkeys. Using acoustic embeddings from birds and humans, we find that they can be effectively used to identify the calls from individual monkeys. Moreover, we find that joint multi-species representations can lead to further improvements over the use of one representation at a time. Our work demonstrates the potential of cross-species data transfer and multi-species representations, as strategies to address tasks on species with very limited data.

Acoustic Individual Identification of White-Faced Capuchin Monkeys Using Joint Multi-Species Embeddings

Most of the world's languages and dialects are low-resource, and lack support in mainstream machine translation (MT) models. However, many of them have a closely-related high-resource language (HRL) neighbor, and differ in linguistically regular ways from it. This underscores the importance of model robustness to dialectal variation and cross-lingual generalization to the HRL dialect continuum. We present DialUp, consisting of a training-time technique for adapting a pretrained model to dialectal data (M-->D), and an inference-time intervention adapting dialectal data to the model expertise (D-->M). M-->D induces model robustness to potentially unseen and unknown dialects by exposure to synthetic data exemplifying linguistic mechanisms of dialectal variation, whereas D-->M treats dialectal divergence for known target dialects. These methods show considerable performance gains for several dialects from four language families, and modest gains for two other language families. We also conduct feature and error analyses, which show that language varieties with low baseline MT performance are more likely to benefit from these approaches.

DialUp! Modeling the Language Continuum by Adapting Models to Dialects and Dialects to Models

The surge of LLM studies makes synthesizing their findings challenging. 
Analysis of experimental results from literature can uncover important trends across studies, but the time-consuming nature of manual data extraction limits its use.
Our study presents a semi-automated approach for literature analysis that accelerates data extraction using LLMs.
It automatically identifies relevant arXiv papers, extracts experimental results and related attributes, and organizes them into a structured dataset, LLMEvalDB.
We then conduct an automated literature analysis of frontier LLMs, reducing the effort of paper surveying and data extraction by more than 93% compared to manual approaches.
We validate LLMEvalDB by showing that it reproduces key findings from a recent manual analysis of Chain-of-Thought (CoT) reasoning and also uncovers new insights that go beyond it, showing, for example, that in-context examples benefit coding & multimodal tasks but offer limited gains in math reasoning tasks compared to zero-shot CoT.
Our automatically updatable dataset enables continuous tracking of target models by extracting evaluation studies as new data becomes available. 
Through LLMEvalDB and empirical analysis, we provide insights into LLMs while facilitating ongoing literature analyses of their behavior.

Can LLMs Help Uncover Insights about LLMs? A Large-Scale, Evolving Literature Analysis of Frontier LLMs

Measurement systems (e.g., currencies) differ across cultures, but the conversions between them are well defined so that humans can state using any measurement system of their choice. Being available to users from diverse cultural backgrounds, Large Language Models (LLMs) should also be able to provide accurate information irrespective of the measurement system at hand. Using newly compiled datasets we test if this is truly the case for seven open-source LLMs, addressing three key research questions: (RQ1) What is the default system used by LLMs for each type of measurement? (RQ2) Do LLMs' answers and their accuracy vary across different measurement systems? (RQ3) Can LLMs mitigate potential challenges w.r.t. underrepresented systems via reasoning? Our findings show that LLMs default to the measurement system predominantly used in the data. Additionally, we observe considerable instability and variance in performance across different measurement systems. While this instability can in part be mitigated by employing reasoning methods such as chain-of-thought (CoT), this implies longer responses and thereby significantly increases test-time compute (and inference costs), marginalizing users from cultural backgrounds that use underrepresented measurement systems.

On Generalization across Measurement Systems: LLMs Entail More Test-Time Compute for Underrepresented Cultures

The sparse Mixture-of-Experts (MoE) has achieved significant progress for neural machine translation (NMT). However, there exist two limitations in current MoE solutions which may lead to sub-optimal performance: 1) they directly use the task knowledge of NMT into MoE (\emph{e.g.}, domain/linguistics-specific knowledge), which are generally unavailable at practical application and neglect the naturally grouped domain/linguistic properties; 2) the expert selection only depends on the localized token representation without considering the context, which fully grasps the state of each token in a global view. To address the above limitations, we propose THOR-MoE via arming the MoE with hierarchical task-guided and context-responsive routing policies. Specifically, it 1) firstly predicts the domain/language label and then extracts mixed domain/language representation to allocate task-level experts in a hierarchical manner; 2) injects the context information to enhance the token routing from the pre-selected task-level experts set, which can help each token to be accurately routed to more specialized and suitable experts. Extensive experiments on multi-domain translation and multilingual translation benchmarks with different architectures consistently demonstrate the superior performance of THOR-MoE. Additionally, the THOR-MoE operates as a plug-and-play module compatible with existing Top-\cite{shazeer2017} or Top-\cite{huang-etal-2024-harder} routing schemes, ensuring broad applicability across diverse MoE architectures. For instance, compared with vanilla Top-~\cite{huang-etal-2024-harder} routing, the context-aware manner can achieve an average improvement of 0.75 BLEU with less than 22% activated parameters on multi-domain translation tasks.

THOR-MoE: Hierarchical Task-Guided and Context-Responsive Routing for Neural Machine Translation

Recent advances in large vision-language models (LVLMs) have shown promise for embodied task planning, yet they struggle with fundamental challenges like dependency constraints and efficiency. Existing approaches either solely optimize action selection or directly leverage pre-trained models as world models during inference, overlooking the benefits of learning to model the world as a way to enhance planning capabilities. We propose Dual Preference Optimization (D$^2$PO), a new learning framework that jointly optimizes state prediction and action selection through preference learning, enabling LVLMs to understand environment dynamics for better planning. To automatically collect trajectories and stepwise preference data without human annotation, we introduce a tree search mechanism for extensive exploration via trial-and-error. Extensive experiments on VoTa-Bench demonstrate that our D$^2$PO-based method significantly outperforms existing methods and GPT-4o when applied to Qwen2-VL (7B), LLaVA-1.6 (7B), and LLaMA-3.2 (11B), achieving superior task success rates with more efficient execution paths.

World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning

Unvoiced electromyography (EMG) is an effective communication tool for individuals unable to produce vocal speech. However, most prior methods rely on paired voiced and unvoiced EMG signals, along with speech data, for unvoiced EMG-to-text conversion, which is not practical for these individuals. Given the rise of large language models (LLMs) in speech recognition, we explore their potential to understand unvoiced speech. To this end, we address the challenge of \emph{learning from unvoiced EMG alone} and propose a novel EMG adaptor module that maps EMG features to an LLM’s input space, achieving an average word error rate of 0.49 on a closed-vocabulary unvoiced EMG-to-text task. Even with a conservative data availability of just six minutes, our approach improves performance over specialized models by nearly 20%. While LLMs have been shown to be extendable to new language modalities—such as audio—understanding articulatory biosignals, like unvoiced EMG, is more challenging. This work takes a crucial first step toward enabling LLMs to comprehend unvoiced speech using surface EMG.

Can LLMs Understand Unvoiced Speech? Exploring EMG-to-Text Conversion with LLMs

Data contamination poses a significant challenge to the fairness of LLM evaluations in natural language processing tasks by inadvertently exposing models to test data during training.
Current studies mitigate this issue by modifying existing datasets or generating new ones from freshly collected information. However, these methods fall short of ensuring contamination-resilient evaluation, as they fail to fully eliminate pre-existing knowledge from models or preserve the semantic complexity of the original datasets. To address these limitations, we propose $\textbf{CoreEval}$, a $\textbf{Co}$ntamination-$\textbf{re}$silient $\textbf{Eval}$uation strategy for automatically updating data with real-world knowledge. This approach begins by extracting entity relationships from the original data and leveraging the GDELT database to retrieve relevant and up-to-date knowledge. The retrieved knowledge is then recontextualized and integrated with the original data, which is refined and restructured to ensure semantic coherence and enhanced task relevance. Ultimately, a robust data reflection mechanism in a Chain-of-Thought manner to iteratively verify and refine labels, ensuring consistency between the updated and original datasets. Extensive experiments on updated datasets validate the robustness of CoreEval, demonstrating its effectiveness in mitigating performance overestimation caused by data contamination.

Downloads

Next from ACL 2025

Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints

Similar lecture

Eigen Attention: Attention in Low-Rank Space for KV Cache Compression