United Arab Emirates

Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks. In Natural Language Processing (NLP), DNNs are often backdoored during the fine-tuning process of a large-scale Pre-trained Language Model (PLM) with poisoned samples. Although the clean weights of PLMs are readily available, existing methods have ignored this information in defending NLP models against backdoor attacks. In this work, we take the first step to exploit the pre-trained (unfine-tuned) weights to mitigate backdoors in fine-tuned language models. Specifically, we leverage the clean pre-trained weights via two complementary techniques: (1) a two-step Fine-mixing technique, which first mixes the backdoored weights (fine-tuned on poisoned data) with the pre-trained weights, then fine-tunes the mixed weights on a small subset of clean data; (2) an Embedding Purification (E-PUR) technique, which mitigates potential backdoors existing in the word embeddings. We compare Fine-mixing with typical backdoor mitigation methods on three single-sentence sentiment classification tasks and two sentence-pair classification tasks and show that it outperforms the baselines by a considerable margin in all scenarios. We also show that our E-PUR method can benefit existing mitigation methods. Our work establishes a simple but strong baseline defense for secure fine-tuned NLP models against backdoor attacks.

EMNLP 2022

Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models

backdoor mitigation

nlp backdoor attacks

pre-trained language model

### 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**. 

ACL 2025

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

findings / work in progress

## Welcome to EMNLP 2022!
I am delighted to welcome you to EMNLP 2022! I believe this conference has been complicated beyond any precedent. Over the past year, it’s been thrilling to see the organization team approach each new puzzle with creativity and enthusiasm. We hope that those participating in Abu Dhabi as well as those joining remotely will leave the conference feeling newly inspired by the program and newly connected to our ever-growing community. Following EMNLP 2021 and major NLP conferences since, EMNLP 2022 is “hybrid,” serving both virtual and in-person participants.

Our key innovations for EMNLP 2022 include:

* EMNLP 2022 is “hybrid” in a second sense, as well: we allowed both direct and rolling review paper submissions, building on the pilot experiment of EMNLP 2021, which considered a small number of ARR submissions. 
* Familiar from NAACL but new to EMNLP, we’ve added an industry track.
* During the conference, “portals” will link virtual poster sessions to in-person conference participants during poster sessions each day.
* The first ACL-family conference in the United Arab Emirates.

 *Message from Noah A. Smith, University of Washington and Allen Institute for AI, Seattle, Washington, USA* 
***EMNLP 2022 General Chair***
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/9eec7d4a287ee18c278b08229290aa83.png)](https://drive.google.com/file/d/1OlPv6QBeo62VVTughj2jkiLeyHd1WnUt/view)
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/a3db7a768409f05192210d98601edb25.png)](https://emnlp2022.rocket.chat/)

To access this site you need to register. Please register [here](https://2022.emnlp.org/registration/).

Register here

Welcome!
EMNLP 2022 will take place in Abu Dhabi from December 7th to December 11th, 2022. And it will be held in hybrid mode, both online and offline.

This paper presents an empirical study to build relation extraction systems in low-resource settings. Based upon recent pre-trained language models, we comprehensively investigate three schemes to evaluate the performance in low-resource settings: (i) different types of prompt-based methods with few-shot labeled data; (ii) diverse balancing methods to address the long-tailed distribution issue; (iii) data augmentation technologies and self-training to generate more labeled in-domain data. We create a benchmark with 8 relation extraction (RE) datasets covering different languages, domains and contexts and perform extensive comparisons over the proposed schemes with combinations. Our experiments illustrate: (i) Though prompt-based tuning is beneficial in low-resource RE, there is still much potential for improvement, especially in extracting relations from cross-sentence contexts with multiple relational triples; (ii) Balancing methods are not always helpful for RE with long-tailed distribution; (iii) Data augmentation complements existing baselines and can bring much performance gain, while self-training may not consistently achieve advancement to low-resource RE. Code and datasets are in https://github.com/zjunlp/LREBench.

Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study

Language-based environment manipulation requires agents to manipulate the environment following natural language instructions, which is challenging due to the huge space of the environments.
To address this challenge, various approaches have been proposed in recent work. Although these approaches work well for their intended environments, they are difficult to generalize across environments. In this work, we propose LEMON, a general framework for language-based environment manipulation tasks. Specifically, we first specify a general approach for language-based environment manipulation tasks, which can deal with various environments using the same generative language model. Then we propose an execution-guided pre-training strategy to inject prior knowledge of environments to the language model with a pure synthetic pre-training corpus. Experimental results on tasks including Alchemy, Scene, Tangrams, ProPara and Recipes demonstrate the effectiveness of LEMON: it achieves new state-of-the-art results on four of the tasks, and the execution-guided pre-training strategy brings remarkable improvements on all experimental tasks.

LEMON: Language-Based Environment Manipulation via Execution-Guided Pre-training

Text data can pose a risk of harm. However, the risks are not fully understood, and how to handle, present, and discuss harmful text in a safe way remains an unresolved issue in the NLP community. We provide an analytical framework categorising harms on three axes: (1) the harm type (e.g., misinformation, hate speech or racial stereotypes); (2) whether a harm is sought as a feature of the research design if explicitly studying harmful content (e.g., training a hate speech classifier), versus unsought if harmful content is encountered when working on unrelated problems (e.g., language generation or part-of-speech tagging); and (3) who it affects, from people (mis)represented in the data to those handling the data and those publishing on the data. We provide advice for practitioners, with concrete steps for mitigating harm in research and in publication. To assist implementation we introduce HarmCheck -- a documentation standard for handling and presenting harmful text in research.

Handling and Presenting Harmful Text in NLP Research

Language Models (LMs) can perform new tasks by adapting to a few in-context examples. For humans, explanations that connect examples to task principles can improve learning. We therefore investigate whether explanations of few-shot examples can help LMs. We annotate questions from 40 challenging tasks with answer explanations, and various matched control explanations. We evaluate how different types of explanations, instructions, and controls affect zero- and few-shot performance. We analyze these results using statistical multilevel modeling techniques that account for the nested dependencies among conditions, tasks, prompts, and models. We find that explanations can improve performance—even without tuning. Furthermore, explanations hand-tuned for performance on a small validation set offer substantially larger benefits, and building a prompt by selecting examples and explanations together substantially improves performance over selecting examples alone. Finally, even untuned explanations outperform carefully matched controls, suggesting that the benefits are due to the link between an example and its explanation, rather than lower-level features. However, only large models benefit. In summary, explanations can support the in-context learning of large LMs on challenging tasks.

Can language models learn from explanations in context?

Logical reasoning is a challenge for many current NLP neural network models since it requires more than the ability of learning informative representations from data. Inspired by the Dual Process Theory in cognitive science — which proposes that human cognition process involves two stages: an intuitive, unconscious and fast process relying on perception calledSystem 1, and a logical, conscious and slow process performing complex reasoning called System 2 — we leverage neural logic reasoning (System 2) on top of the representation learning models (System 1), which conducts explicit neural-based differentiable logical reasoning on top of the representations learned by the base neural models. Based on experiments on the commonsense knowledge graph completion task, we show that the two-system architecture always improves from its System 1 model alone. Experiments also show that both the rule-driven logical regularizer and the data-driven value regularizer are important and the performance improvement is marginal without the two regularizers, which indicates that learning from both logical prior and training data is important for reasoning tasks.

System 1 + System 2 = Better World: Neural-Symbolic Chain of Logic Reasoning

Existing textual adversarial attacks usually utilize the gradient or prediction confidence to generate adversarial examples, making it hard to be deployed in real-world applications. To this end, we consider a rarely investigated but more rigorous setting, namely hard-label attack, in which the attacker can only access the prediction label. In particular, we find we can learn the importance of different words via the change on prediction label caused by word substitutions on the adversarial examples. Based on this observation, we propose a novel adversarial attack, termed Text Hard-label attacker (TextHacker). TextHacker randomly perturbs lots of words to craft an adversarial example. Then, TextHacker adopts a hybrid local search algorithm with the estimation of word importance from the attack history to minimize the adversarial perturbation. Extensive evaluations for text classification and textual entailment show that TextHacker significantly outperforms existing hard-label attacks regarding the attack performance as well as adversary quality.

TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attack

Neural language models encode rich knowledge about entities and their relationships which can be extracted from their representations using probing. Common properties of nouns (e.g., red strawberries, small ant) are, however, more challenging to extract compared to other types of knowledge because they are rarely explicitly stated in texts.
We hypothesize this to mainly be the case for perceptual properties which are obvious to the participants in the communication. We propose to extract these properties from images and use them in an ensemble model, in order to complement the information that is extracted from language models. We consider perceptual properties to be more concrete than abstract properties (e.g., interesting, flawless). We propose to use the adjectives' concreteness score as a lever to calibrate the contribution of each source (text vs. images). We evaluate our ensemble model in a ranking task where the actual properties of a noun need to be ranked higher than other non-relevant properties. Our results show that the proposed combination of text and images greatly improves noun property prediction compared to powerful text-based language models.

Visualizing the Obvious: A Concreteness-based Ensemble Model for Noun Property Prediction

Natural language processing (NLP) models are known to be vulnerable to backdoor attacks, which poses a newly arisen threat to NLP models. Prior online backdoor defense methods for NLP models only focus on the anomalies at either the input or output level, still suffering from fragility to adaptive attacks and high computational cost. In this work, we take the first step to investigate the unconcealment of textual poisoned samples at the intermediate-feature level and propose a feature-based efficient online defense method. Through extensive experiments on existing attacking methods, we find that the poisoned samples are far away from clean samples in the intermediate feature space of a poisoned NLP model. Motivated by this observation, we devise a distance-based anomaly score (DAN) to distinguish poisoned samples from clean samples at the feature level. Experiments on sentiment analysis and offense detection tasks demonstrate the superiority of DAN, as it substantially surpasses existing online defense methods in terms of defending performance and enjoys lower inference costs. Moreover, we show that DAN is also resistant to adaptive attacks based on feature-level regularization. Our code is available at https://github.com/lancopku/DAN.

Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks

Knowledge Graph(KG) grounded conversations often use large pre-trained models and usually suffer from fact hallucination. Frequently entities with no references in knowledge sources and conversation history are introduced into responses, thus hindering the flow of the conversation—existing work attempt to overcome this issue by tweaking the training procedure or using a multi-step refining method. However, minimal effort is put into constructing an entity-level hallucination detection system, which would provide fine-grained signals that control fallacious content while generating responses. As a first step to address this issue, we dive deep to identify various modes of hallucination in KG-grounded chatbots through human feedback analysis. Secondly, we propose a series of perturbation strategies to create a synthetic dataset named FADE (FActual Dialogue Hallucination DEtection Dataset). Finally, we conduct comprehensive data analyses and create multiple baseline models for hallucination detection to compare against human-verified data and already established benchmarks.

Diving Deep into Modes of Fact Hallucinations in Dialogue Systems

State-of-the-art keyphrase generation methods generally depend on large annotated datasets, limiting their performance in domains with limited annotated data. To overcome this challenge, we design a data-oriented approach that first identifies salient information using retrieval-based corpus-level statistics, and then learns a task-specific intermediate representation based on a pre-trained language model using large-scale unlabeled documents. We introduce salient span recovery and salient span prediction as denoising training objectives that condense the intra-article and inter-article knowledge essential for keyphrase generation. Through experiments on multiple keyphrase generation benchmarks, we show the effectiveness of the proposed approach for facilitating low-resource keyphrase generation and zero-shot domain adaptation. Our method especially benefits the generation of absent keyphrases, approaching the performance of models trained with large training sets.

Downloads

Next from EMNLP 2022

Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study

Similar lecture

When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from EMNLP 2022

Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study

Similar lecture

When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations

Downloads