Canada

Privacy concerns have attracted increasing attention in data-driven products due to the tendency of machine learning models to memorize sensitive training data. Generating synthetic versions of such data with a formal privacy guarantee, such as differential privacy (DP), provides a promising path to mitigating these privacy concerns, but previous approaches in this direction have typically failed to produce synthetic data of high quality. In this work, we show that a simple and practical recipe in the text domain is effective: simply fine-tuning a pretrained generative language model with DP enables the model to generate useful synthetic text with strong privacy protection. Through extensive empirical analyses on both benchmark and private customer data, we demonstrate that our method produces synthetic text that is competitive in terms of utility with its non-private counterpart, meanwhile providing strong protection against potential privacy leakages.

&lt;iframe src=&quot;https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/e43ddc43-dc33-44b2-a0d8-8d21d4ca653f&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe

llms

synthetic data

privacy

text generation

differential privacy

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. <br>
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) <br><br><br>
<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>
<br><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 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.

**Online Registration Form**: https://acl.swoogo.com/acl2026

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.

Privacy concerns have attracted increasing attention in data-driven products due to the tendency of machine learning models to memorize sensitive training data. Generating synthetic versions of such data with a formal privacy guarantee, such as differential privacy (DP), provides a promising path to mitigating these privacy concerns, but previous approaches in this direction have typically failed to produce synthetic data of high quality. In this work, we show that a simple and practical recipe in the text domain is effective: simply fine-tuning a pretrained generative language model with DP enables the model to generate useful synthetic text with strong privacy protection. Through extensive empirical analyses on both benchmark and private customer data, we demonstrate that our method produces synthetic text that is competitive in terms of utility with its non-private counterpart, meanwhile providing strong protection against potential privacy leakages.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/e43ddc43-dc33-44b2-a0d8-8d21d4ca653f" 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.

Targeted syntactic evaluations of language models ask whether models show stable preferences for syntactically acceptable content over minimal-pair unacceptable inputs. Our best syntactic evaluation datasets, however, provide substantially less linguistic context than models receive during pretraining. This mismatch raises an important question: how robust are models' syntactic judgements across different contexts? In this paper, we vary the input contexts based on: length, the types of syntactic phenomena it contains, and whether or not there are grammatical violations. We find that model judgements are generally robust when placed in randomly sampled linguistic contexts, but are unstable when contexts match the test stimuli in syntactic structure. Among all tested models (GPT-2 and five variants of OPT), we find that model performance is affected when we provided contexts with matching syntactic structure: performance significantly improves when contexts are acceptable, and it significantly declines when they are unacceptable. This effect is amplified by the length of the context, except for unrelated inputs. We show that these changes in model performance are not explainable by acceptability-preserving syntactic perturbations. This sensitivity to highly specific syntactic features of the context can only be explained by the models' implicit in-context learning abilities.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/afea25f5-53ec-4661-ad8e-488bb63dfba3" width="300" height="400"></iframe>

Language model acceptability judgements are not always robust to context

This study presents a diverse set of freely available linguistic resources for Turkish natural language processing, including corpora, pretrained models and education material. Although Turkish is spoken by a sizeable population of over 80 million people, Turkish linguistic resources for natural language processing remain scarce. In this study, we provide corpora to allow practitioners to build their own applications and pretrained models that would assist industry researchers in creating quick prototypes. The provided corpora include named entity recognition datasets of diverse genres, including Wikipedia articles and supplement products customer reviews. In addition, crawling e-commerce and movie reviews websites, we compiled several sentiment analysis datasets of different genres. Our linguistic resources for Turkish also include pretrained spaCy language models. To the best of our knowledge, our models are the first spaCy models trained for the Turkish language. Finally, we provide various types of education material, such as video tutorials and code examples, that can support the interested audience on practicing Turkish NLP. The advantages of our linguistic resources are three-fold: they are freely available, they are first of their kind, and they are easy to use in a broad range of implementations. Along with a thorough description of the resource creation process, we also explain the position of our resources in the Turkish NLP world.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/c680138d-2fcc-45e6-b886-105cc3a162ae" width="300" height="400"></iframe>

A Diverse Set of Freely Available Linguistic Resources for Turkish

As the number of recorded meetings increases, it becomes increasingly important to utilize summarization technology to create useful summaries of these recordings. However, there is a crucial lack of annotated meeting corpora for developing this technology, as it can be hard to collect meetings, especially when the topics discussed are confidential. Furthermore, meeting summaries written by experienced writers are scarce, making it hard for abstractive summarizers to produce sensible output without a reliable reference. This lack of annotated corpora has hindered the development of meeting summarization technology. In this paper, we present MeetingBank, a new benchmark dataset of city council meetings over the past decade. MeetingBank is unique among other meeting corpora due to its divide-and-conquer approach, which involves dividing professionally written meeting minutes into shorter passages and aligning them with specific segments of the meeting. This breaks down the process of summarizing a lengthy meeting into smaller, more manageable tasks. The dataset provides a new testbed of various meeting summarization systems and also allows the public to gain insight into how council decisions are made. We make the collection, including meeting video links, transcripts, reference summaries, agenda, and other metadata, publicly available to facilitate the development of better meeting summarization techniques.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/c7478c27-714a-4a51-ba87-b339af8300e3" width="300" height="400"></iframe>

MeetingBank: A Benchmark Dataset for Meeting Summarization

Relation extraction (RE) is the core NLP task of inferring semantic relationships between entities from text. Standard supervised RE techniques entail training modules to tag tokens comprising entity spans and then predict the relationship between them. Recent work has instead treated the problem as a sequence-to-sequence task, linearizing relations between entities as target strings to be generated conditioned on the input. Here we push the limits of this approach, using larger language models (GPT-3 and Flan-T5 large) than considered in prior work and evaluating their performance on standard RE tasks under varying levels of supervision. We address issues inherent to evaluating generative approaches to RE by doing human evaluations, in lieu of relying on exact matching. Under this refined evaluation, we find that: (1) Few-shot prompting with GPT-3 achieves near SOTA performance, i.e., roughly equivalent to existing fully supervised models; (2) Flan-T5 is not as capable in the few-shot setting, but supervising and fine-tuning it with Chain-of-Thought (CoT) style explanations (generated via GPT-3) yields SOTA results. We release this model as a new baseline for RE tasks.

<iframe src="https://app.sli.do/event/6qSnTPZvioRLfFJpZUjhCw/embed/polls/973ea1c9-e40d-4451-ad9a-9eb69e89c849" width="300" height="400"></iframe>

Revisiting Relation Extraction in the era of Large Language Models

Large-scale code generation models such as Copilot and CodeT5 have achieved impressive performance. However, libraries are upgraded or deprecated very frequently and re-training large-scale language models is computationally expensive. Therefore, Continual Learning (CL) is an important aspect that remains under-explored in the code domain. In this paper, we introduce a benchmark called CodeTask-CL that covers a wide range of tasks, including code generation, translation, summarization, and refinement, with different input and output programming languages. Next, on our CodeTask-CL benchmark, we compare popular CL techniques from NLP and Vision domains. We find that effective methods like Prompt Pooling (PP) suffer from catastrophic forgetting due to the unstable training of the prompt selection mechanism caused by stark distribution shifts in coding tasks. We address this issue with our proposed method, Prompt Pooling with Teacher Forcing (PP-TF), that stabilizes training by enforcing constraints on the prompt selection mechanism and leads to a 21.54% improvement over Prompt Pooling. Along with the benchmark, we establish a training pipeline that can be used for CL on code models, which we believe can motivate further development of CL methods for code models.

<iframe src="https://app.sli.do/event/6qSnTPZvioRLfFJpZUjhCw/embed/polls/3af664b2-c6eb-4726-92bd-eb175a1af76d" width="300" height="400"></iframe>

Exploring Continual Learning for Code Generation Models

Recent studies show that sentence-level extractive QA, i.e., based on Answer Sentence Selection (AS2), is outperformed by Generation-based QA (GenQA) models, which generate answers using the top-k answer sentences ranked by AS2 models (a la retrieval-augmented generation style). In this paper, we propose a novel training paradigm for GenQA using supervision from automatic QA evaluation models (GAVA). Specifically, we propose three strategies to transfer knowledge from these QA evaluation models to a GenQA model: (i) augmenting training data with answers generated by the GenQA model and labelled by GAVA (either statically, before training, or (ii) dynamically, at every training epoch); and (iii) using the GAVA score for weighting the generator loss during the learning of the GenQA model. We evaluate our proposed methods on two academic and one industrial dataset, obtaining a significant improvement in answering accuracy over the previous state of the art.

<iframe src="https://app.sli.do/event/6qSnTPZvioRLfFJpZUjhCw/embed/polls/a7823e93-e84d-4b7f-9716-7e872f8c6902" width="300" height="400"></iframe>

Learning Answer Generation using Supervision from Automatic Question Answering Evaluators

Standard decoding approaches for conditional text generation tasks typically search for an output hypothesis with high model probability, but this may not yield the best hypothesis according to human judgments of quality. Reranking to optimize for "downstream" metrics can more closely optimize for quality, but many metrics of interest are computed with pre-trained language models, which are slow to apply to large numbers of hypotheses. We explore an approach for reranking hypotheses by using Transformers to efficiently encode lattices of generated outputs, a method we call EEL. With a single Transformer pass over the entire lattice, we can approximately compute a contextualized representation of each token as if it were only part of a single hypothesis in isolation. We combine this approach with a new class of token-factored rerankers (TFRs) that allow for efficient extraction of high reranker-scoring hypotheses from the lattice. Empirically, our approach incurs minimal degradation error compared to the exponentially slower approach of encoding each hypothesis individually. When applying EEL with TFRs across three text generation tasks, our results show both substantial speedup compared to naive reranking and often better performance on downstream metrics than comparable approaches.

<iframe src="https://app.sli.do/event/6qSnTPZvioRLfFJpZUjhCw/embed/polls/2b3eb2d5-16fe-4f90-be96-92f4d4d44c65" width="300" height="400"></iframe>

EEL: Efficiently Encoding Lattices for Reranking

With emerging online topics as a source for numerous new events, detecting unseen / rare event types presents an elusive challenge for existing event detection methods, where only limited data access is provided for training. To address the data scarcity problem in event detection, we propose MetaEvent, a meta learning-based framework for zero- and few-shot event detection. Specifically, we sample training tasks from existing event types and perform meta training to search for optimal parameters that quickly adapt to unseen tasks. In our framework, we propose to use the cloze-based prompt and a trigger-aware soft verbalizer to efficiently project output to unseen event types. Moreover, we design a contrastive meta objective based on maximum mean discrepancy (MMD) to learn class-separating features. As such, the proposed MetaEvent can perform zero-shot event detection by mapping features to event types without any prior knowledge. In our experiments, we demonstrate the effectiveness of MetaEvent in both zero-shot and few-shot scenarios, where the proposed method achieves state-of-the-art performance in extensive experiments on benchmark datasets FewEvent and MAVEN.

<iframe src="https://app.sli.do/event/6qSnTPZvioRLfFJpZUjhCw/embed/polls/888bfd1e-5983-4268-a21e-28c6ec185652" width="300" height="400"></iframe>

Zero- and Few-Shot Event Detection via Prompt-Based Meta Learning

The ability to connect language units to their referents in the physical world, referred to as grounding, is crucial to learning and understanding grounded meanings of words. While humans demonstrate fast mapping in new word learning, it remains unclear whether modern vision-language models can truly represent language with their grounded meanings, and how grounding may further bootstrap new word learning. To this end, we introduce Grounded Open Vocabulary Acquisition (GOVA) to examine grounding and bootstrapping in open-world language learning. As an initial attempt, we propose World-to-Words (W2W), a novel visually-grounded language model by pre-training on image-text pairs highlighting grounding as an objective. Through extensive experiments and analysis, we demonstrate that W2W is a more coherent and fast grounded word learner, and that the grounding ability acquired during pre-training helps the model to learn unseen words more rapidly and robustly.

<iframe src="https://app.sli.do/event/6qSnTPZvioRLfFJpZUjhCw/embed/polls/df9c63c6-8436-42bb-a085-e6cc1ff8eec4" width="300" height="400"></iframe>

World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models

Current clustering-based Open Relation Extraction (OpenRE) methods usually adopt a two-stage pipeline, which simultaneously learns relation representations and assignments in the first stage, then manually labels relation for each cluster.However, unsupervised objectives struggle to explicitly optimize clusters to align with relational semantics, and the number of clusters K has to be supplied in advance.In this paper, we present a novel setting, named actively supervised clustering for OpenRE. Our insight lies in that clustering learning and relation labeling can be performed simultaneously, which provides the necessary guidance for clustering without a significant increase in human effort. Along with this setting, we propose an active labeling strategy tailored for clustering. Instead of only focusing on improving the clustering of relations that have been discovered, our strategy is encouraged to discover new relations through diversity regularization. This is particularly beneficial for long-tail relations in the real world.Experimental results show that our method is able to discover almost all relational clusters in the data and improve the SOTA methods by 13.8% and 10.6%, on two datasets respectively.

<iframe src="https://app.sli.do/event/6qSnTPZvioRLfFJpZUjhCw/embed/polls/2bfee534-d7c9-439d-be00-1fdc94b3e7c7" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

Language model acceptability judgements are not always robust to context

Similar lecture

Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation