Canada

Parameter-Efficient Tuning (PET) has shown remarkable performance by fine-tuning only a small number of parameters of the pre-trained language models (PLMs) for the downstream tasks, while it is also possible to construct backdoor attacks due to the vulnerability of pre-trained weights. However, a large reduction in the number of attackable parameters in PET will cause the user&#39;s fine-tuning to greatly affect the effectiveness of backdoor attacks, resulting in backdoor forgetting. We find that the backdoor injection process can be regarded as multi-task learning, which has a convergence imbalance problem between the training of clean and poisoned data. And this problem might result in forgetting the backdoor. Based on this finding, we propose a gradient control method to consolidate the attack effect, comprising two strategies. One controls the gradient magnitude distribution cross layers within one task and the other prevents the conflict of gradient directions between tasks. Compared with previous backdoor attack methods in the scenario of PET, our method improve the effect of the attack on sentiment classification and spam detection respectively, which shows that our method is widely applicable to different tasks.

&lt;iframe src=&quot;https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/ba8f441f-bb4c-4a7a-a64e-b180b60672c8&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

A Gradient Control Method for Backdoor Attacks on Parameter-Efficient Tuning

parameter-efficient tuning

backdoor attack

multi-task learning

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair:<br>
*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.*<br>
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)<br><br><br>



To access this event page, you need to log in with the **email address you registered with**. <br>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**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Parameter-Efficient Tuning (PET) has shown remarkable performance by fine-tuning only a small number of parameters of the pre-trained language models (PLMs) for the downstream tasks, while it is also possible to construct backdoor attacks due to the vulnerability of pre-trained weights. However, a large reduction in the number of attackable parameters in PET will cause the user's fine-tuning to greatly affect the effectiveness of backdoor attacks, resulting in backdoor forgetting. We find that the backdoor injection process can be regarded as multi-task learning, which has a convergence imbalance problem between the training of clean and poisoned data. And this problem might result in forgetting the backdoor. Based on this finding, we propose a gradient control method to consolidate the attack effect, comprising two strategies. One controls the gradient magnitude distribution cross layers within one task and the other prevents the conflict of gradient directions between tasks. Compared with previous backdoor attack methods in the scenario of PET, our method improve the effect of the attack on sentiment classification and spam detection respectively, which shows that our method is widely applicable to different tasks.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/ba8f441f-bb4c-4a7a-a64e-b180b60672c8" width="300" height="400"></iframe>

poster

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
<br>The conference will be held in Toronto, Canada, July 9-14, 2023.<br><br>
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience.<br>
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**
<br><br><br><br>

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing.

Attribute extraction aims to identify attribute names and the corresponding values from descriptive texts, which is the foundation for extensive downstream applications such as knowledge graph construction, search engines, and e-Commerce. In previous studies, attribute extraction is generally treated as a classification problem for predicting attribute types or a sequence tagging problem for labeling attribute values, where two paradigms, i.e., closed-world and open-world assumption, are involved. However, both of these paradigms have limitations in terms of real-world applications. And prior studies attempting to integrate these paradigms through ensemble, pipeline, and co-training models, still face challenges like cascading errors, high computational overhead, and difficulty in training. To address these existing problems, this paper presents Attribute Tree, a unified formulation for real-world attribute extraction application, where closed-world, open-world, and semi-open attribute extraction tasks are modeled uniformly. Then a text-to-tree generation model, AtTGen, is proposed to learn annotations from different scenarios efficiently and consistently. Experiments demonstrate that our proposed paradigm well covers various scenarios for real-world applications, and the model achieves state-of-the-art, outperforming existing methods by a large margin on three datasets. Our code, pretrained model, and datasets are available at https://github.com/lsvih/AtTGen.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/4456f002-b71e-4b0b-bb8c-5164cea3d1bd" width="300" height="400"></iframe>

AtTGen: Attribute Tree Generation for Real-World Attribute Joint Extraction

Multilingual Vision-Language Pre-training (VLP) is a promising but challenging topic due to the lack of large-scale multilingual image-text pairs. Existing works address the problem by translating English data into other languages, which is intuitive and the generated data is usually limited in form and scale. In this paper, we explore a more practical and scalable setting: weakly supervised multilingual VLP with only English image-text pairs and multilingual text corpora. We argue that the universal multilingual representation learned from texts allows the cross-modal interaction learned in English to be transferable to other languages. To this end, we propose a framework to effectively unify cross-lingual and cross-modal pre-training. For unified modeling on different data, we design an architecture with flexible modules to learn different interactions. Moreover, two unified tasks are introduced to efficiently guide the unified cross-lingual cross-modal learning. Extensive experiments demonstrate that our pre-trained model learns universal multilingual multimodal representations, allowing effective cross-lingual transfer on multimodal tasks. Code and models are available at https://github.com/FudanDISC/weakly-supervised-mVLP.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/71e7957f-1e50-4d34-abe4-3bd1f6ff68ea" width="300" height="400"></iframe>

Unifying Cross-Lingual and Cross-Modal Modeling Towards Weakly Supervised Multilingual Vision-Language Pre-training

Chinese Spelling Correction (CSC) is the task of detecting and correcting misspelled charac- ters in Chinese texts. As an important step for various downstream tasks, CSC confronts two challenges: 1) Character-level errors consist not only of spelling errors but also of missing and redundant ones that cause variable length between input and output texts, for which most CSC methods could not handle well because of the consistence length of texts required by their inherent detection-correction framework. Con- sequently, the two errors are considered out- side the scope and left to future work, despite the fact that they are widely found and bound to CSC task in Chinese industrial scenario, such as Automatic Speech Recognition (ASR) and Optical Character Recognition (OCR). 2) Most existing CSC methods focus on either detector or corrector and train different mod- els for each one, respectively, leading to in- sufficiency of parameters sharing. To address these issues, we propose a novel model UMR- Spell to learn detection and correction parts together at the same time from a multi-task learning perspective by using a detection trans- mission self-attention matrix, and flexibly deal with both missing, redundant, and spelling er- rors through re-tagging rules. Furthermore, we build a new dataset ECMR-2023 containing five kinds of character-level errors to enrich the CSC task closer to real-world applications. Ex- periments on both SIGHAN benchmarks and ECMR-2023 demonstrate the significant effec- tiveness of UMRSpell over previous represen- tative baselines.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/e073e615-b1ec-45cc-ab7d-70cb459da3ff" width="300" height="400"></iframe>

UMRSpell: Unifying the Detection and Correction Parts of Pre-trained Models towards Chinese Missing, Redundant, and Spelling Correction

Data augmentation is an effective solution to improve model performance and robustness for low-resource named entity recognition (NER). However, synthetic data often suffer from poor diversity, which leads to performance limitations.In this paper, we propose a novel Graph Propagated Data Augmentation (GPDA) framework for Named Entity Recognition (NER), leveraging graph propagation to build relationships between labeled data and unlabeled natural texts. By projecting the annotations from the labeled text to the unlabeled text, the unlabeled texts are partially labeled, which has more diversity rather than synthetic annotated data.To strengthen the propagation precision, a simple search engine built on Wikipedia is utilized to fetch related texts of labeled data and to propagate the entity labels to them in the light of the anchor links. Besides, we construct and perform experiments on a real-world low-resource dataset of the E-commerce domain, which will be publicly available to facilitate the low-resource NER research.Experimental results show that GPDA presents substantial improvements over previous data augmentation methods on multiple low-resource NER datasets.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/7e2343b4-85e9-4176-b402-939d99c76e36" width="300" height="400"></iframe>

Graph Propagation based Data Augmentation for Named Entity Recognition

With the popularity of social media, detecting sentiment from multimodal posts (e.g. image-text pairs) has attracted substantial attention recently. Existing works mainly focus on fusing different features but ignore the challenge of modality heterogeneity. Specifically, different modalities with inherent disparities may bring three problems: 1) introducing redundant visual features during feature fusion; 2) causing feature shift in the representation space; 3) leading to inconsistent annotations for different modal data. All these issues will increase the difficulty in understanding the sentiment of the multimodal content. In this paper, we propose a novel Multi-View Calibration Network (MVCN) to alleviate the above issues systematically. We first propose a text-guided fusion module with novel Sparse-Attention to reduce the negative impacts of redundant visual elements. We then devise a sentiment-based congruity constraint task to calibrate the feature shift in the representation space. Finally, we introduce an adaptive loss calibration strategy to tackle inconsistent annotated labels. Extensive experiments demonstrate the competitiveness of MVCN against previous approaches and achieve state-of-the-art results on two public benchmark datasets.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/9879dd6d-6de6-4587-ac5a-c37102fe3195" width="300" height="400"></iframe>

Tackling Modality Heterogeneity with Multi-View Calibration Network for Multimodal Sentiment Detection

Image translation is a task that translates an image containing text in the source language to the target language. One major challenge with image translation is the modality gap between visual text inputs and textual inputs/outputs of machine translation (MT). In this paper, we propose PEIT, an end-to-end image translation framework that bridges the modality gap with pre-trained models. It is composed of four essential components: a visual encoder, a shared encoder-decoder backbone network, a vision-text representation aligner equipped with the shared encoder and a cross-modal regularizer stacked over the shared decoder. Both the aligner and regularizer aim at reducing the modality gap. To train PEIT, we employ a two-stage pre-training strategy with an auxiliary MT task: (1) pre-training the MT model on the MT training data to initialize the shared encoder-decoder backbone network; and (2) pre-training PEIT with the aligner and regularizer on a synthesized dataset with rendered images containing text from the MT training data. In order to facilitate the evaluation of PEIT and promote research on image translation, we create a large-scale image translation corpus ECOIT containing 480K image-translation pairs via crowd-sourcing and manual post-editing from real-world images in the e-commerce domain. Experiments on the curated ECOIT benchmark dataset demonstrate that PEIT substantially outperforms both cascaded image translation systems (OCR+MT) and previous strong end-to-end image translation model, with fewer parameters and faster decoding speed.

PEIT: Bridging the Modality Gap with Pre-trained Models for End-to-End Image Translation

Humans can effortlessly understand the coordinate structure of sentences such as "Niels Bohr and Kurt Cobain were born in Copenhagen and Seattle, *respectively*". In the context of natural language inference (NLI), we examine how language models (LMs) reason with respective readings (Gawron and Kehler, 2004) from two perspectives: syntactic-semantic and commonsense-world knowledge. We propose a controlled synthetic dataset WikiResNLI and a naturally occurring dataset NatResNLI to encompass various explicit and implicit realizations of "respectively''. We show that fine-tuned NLI models struggle with understanding such readings without explicit supervision. While few-shot learning is easy in the presence of explicit cues, longer training is required when the reading is evoked implicitly, leaving models to rely on common sense inferences. Furthermore, our fine-grained analysis indicates models fail to generalize across different constructions. To conclude, we demonstrate that LMs still lag behind humans in generalizing to the long tail of linguistic constructions.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/3638c8cf-8037-4ef1-b57e-4c80464383a2" width="300" height="400"></iframe>

What does the Failure to Reason with "Respectively'' in Zero/Few-Shot Settings Tell Us about Language Models?

Recently, various intermediate layer distillation (ILD) objectives have been shown to improve compression of BERT models via Knowledge Distillation (KD). However, a comprehensive evaluation of the objectives in both task-specific and task-agnostic settings is lacking. To the best of our knowledge, this is the first work comprehensively evaluating distillation objectives in both settings. We show that attention transfer gives the best performance overall. We also study the impact of layer choice when initializing the student from the teacher layers, finding a significant impact on the performance in task-specific distillation. For vanilla KD and hidden states transfer, initialisation with lower layers of the teacher gives a considerable improvement over higher layers, especially on the task of QNLI (up to an absolute percentage change of 17.8 in accuracy). Attention transfer behaves consistently under different initialisation settings. We release our code as an efficient transformer-based model distillation framework for further studies.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/a66d6f7d-b366-4c39-9289-f02b4347d430" width="300" height="400"></iframe>

How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives

High-quality datasets are significant to the development of dialogue models.However, most existing datasets for open-domain dialogue modeling are limited to a single language.The absence of multilingual open-domain dialog datasets not only limits the research on multilingual or cross-lingual transfer learning, but also hinders the development of robust open-domain dialog systems that can be deployed in other parts of the world.In this paper, we provide a multilingual parallel open-domain dialog dataset, XDailyDialog, to enable researchers to explore the challenging task of multilingual and cross-lingual open-domain dialog. XDailyDialog includes 13K dialogues aligned across 4 languages (52K dialogues and 410K utterances in total). We then propose a dialog generation model, kNN-Chat, which has a novel kNN-search mechanism to support unified response retrieval for monolingual, multilingual, and cross-lingual dialogue. Experiment results show the effectiveness of this framework. We will make XDailyDialog and kNN-Chat publicly available soon.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/596699af-24af-4aaf-8197-73d491da5cb0" width="300" height="400"></iframe>

XDailyDialog: A Multilingual Parallel Dialogue Corpus

As 3rd-person pronoun usage shifts to include novel forms, e.g., neopronouns, we need more research on identity-inclusive NLP. Exclusion is particularly harmful in one of the most popular NLP applications, machine translation (MT). Wrong pronoun translations can discriminate against marginalized groups, e.g., non-binary individuals (Dev et al., 2021). In this ``reality check'', we study how three commercial MT systems translate 3rd-person pronouns. Concretely, we compare the translations of gendered vs. gender-neutral pronouns from English to five other languages (Danish, Farsi, French, German, Italian), and vice versa, from Danish to English.Our error analysis shows that the presence of a gender-neutral pronoun often leads to grammatical and semantic translation errors. Similarly, gender neutrality is often not preserved. By surveying the opinions of affected native speakers from diverse languages, we provide recommendations to address the issue in future MT research.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/131cc2b4-c48e-407f-aeb9-c5d86396c349" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

AtTGen: Attribute Tree Generation for Real-World Attribute Joint Extraction

Similar lecture

ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models