Canada

Fact verification aims to automatically judge the veracity of a claim according to several pieces of evidence. Due to the manual construction of datasets, spurious correlations between claim patterns and its veracity (i.e., biases) inevitably exist. Recent studies show that models usually learn such biases instead of understanding the semantic relationship between the claim and evidence. Existing debiasing works can be roughly divided into data-augmentation-based and weight-regularization-based pipeline, where the former is inflexible and the latter relies on the uncertain output on the training stage. Unlike previous works, we propose a novel method from a counterfactual view, namely CLEVER, which is augmentation-free and mitigates biases on the inference stage. Specifically, we train a claim-evidence fusion model and a claim-only model independently. Then, we obtain the final prediction via subtracting output of the claim-only model from output of the claim-evidence fusion model, which counteracts biases in two outputs so that the unbiased part is highlighted. Comprehensive experiments on several datasets have demonstrated the effectiveness of CLEVER.

&lt;iframe src=&quot;https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/2519e0ea-4028-45cb-bcc3-cb23abe30546&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

Counterfactual Debiasing for Fact Verification

debiasing

fact verification

counterfactual inference

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.

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.

Fact verification aims to automatically judge the veracity of a claim according to several pieces of evidence. Due to the manual construction of datasets, spurious correlations between claim patterns and its veracity (i.e., biases) inevitably exist. Recent studies show that models usually learn such biases instead of understanding the semantic relationship between the claim and evidence. Existing debiasing works can be roughly divided into data-augmentation-based and weight-regularization-based pipeline, where the former is inflexible and the latter relies on the uncertain output on the training stage. Unlike previous works, we propose a novel method from a counterfactual view, namely CLEVER, which is augmentation-free and mitigates biases on the inference stage. Specifically, we train a claim-evidence fusion model and a claim-only model independently. Then, we obtain the final prediction via subtracting output of the claim-only model from output of the claim-evidence fusion model, which counteracts biases in two outputs so that the unbiased part is highlighted. Comprehensive experiments on several datasets have demonstrated the effectiveness of CLEVER.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/2519e0ea-4028-45cb-bcc3-cb23abe30546" 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.

Language models (LMs) are pretrained on diverse data sources---news, discussion forums, books, online encyclopedias. A significant portion of this data includes facts and opinions which, on one hand, celebrate democracy and diversity of ideas, and on the other hand are inherently socially biased. Our work develops new methods to (1) measure media biases in LMs trained on such corpora, along social and economic axes, and (2) measure the fairness of downstream NLP models trained on top of politically biased LMs. We focus on hate speech and misinformation detection, aiming to empirically quantify the effects of political (social, economic) biases in pretraining data on the fairness of high-stakes social-oriented tasks. Our findings reveal that pretrained LMs do have political leanings which reinforce the polarization present in pretraining corpora, propagating social biases into hate speech predictions and media biases into misinformation detectors. We discuss the implications of our findings for NLP research and propose future directions to mitigate unfairness.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/45895f18-0222-4f96-a94a-1a1ae6eb09b7" width="300" height="400"></iframe>

From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models

User simulators are agents designed to imitate human users; recent advances have found that Task-oriented Dialogue (ToD) systems optimized toward a user simulator could better satisfy the need of human users. However, this might result in a sub-optimal ToD system if it is tailored to only one \textit{ad hoc} user simulator, since human users can behave differently. In this paper, we propose a framework called MUST to optimize ToD systems via leveraging Multiple User SimulaTors. The main challenges of implementing MUST fall in 1) how to adaptively determine which user simulator to interact with the ToD system at each optimization step, since the ToD system might be over-fitted to some specific user simulators, and simultaneously under-fitted to some others; 2) how to avoid catastrophic forgetting of the adaption for a simulator that is not selected for several consecutive optimization steps.To tackle these challenges, we formulate MUST as a Multi-armed bandits (MAB) problem and provide a method called MUST$_{\mathrm{adaptive}}$ that balances \textit{i}) the \textit{boosting adaption} for adaptive interactions between different user simulators and the ToD system and\textit{ii}) the \textit{uniform adaption} to avoid the catastrophic forgetting issue.With both automatic evaluations and human evaluations, our experimental results on MultiWOZ show that the dialogue system trained by MUST achieves a better performance than those trained by a single user simulator. It also has a better generalization ability when testing with unseen user simulators.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/8a6b9f60-373d-40e9-86b7-025065db126d" width="300" height="400"></iframe>

One Cannot Stand for Everyone! Leveraging Multiple User Simulators\\ to train Task-oriented Dialogue Systems

Long-form question answering systems provide rich information by presenting paragraph-level answers, often containing optional background or auxiliary information. While such comprehensive answers are helpful, not all information is required to answer the question (e.g. users with domain knowledge do not need an explanation of background). Can we provide a concise version of the answer by summarizing it, while still addressing the question? We conduct a user study on summarized answers generated from state-of-the-art models and our newly proposed extract-and-decontextualize approach. We find a large proportion of long-form answers (over 90%) in the ELI5 domain can be adequately summarized by at least one system, while complex and implicit answers are challenging to compress. We observe that decontextualization improves the quality of the extractive summary, exemplifying its potential in the summarization task. To promote future work, we provide an extractive summarization dataset covering 1K long-form answers and our user study annotations. Together, we present the first study on summarizing long-form answers, taking a step forward for QA agents that can provide answers at multiple granularities.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/78962a9e-8d78-4edf-b726-37954b80c784" width="300" height="400"></iframe>

Concise Answers to Complex Questions: Summarization of Long-form Answers

Fine-grained emotion classification (FEC) is a challenging task. Specifically, FEC needs to handle subtle nuance between labels, which can be complex and confusing. Most existing models only address text classification problem in the euclidean space, which we believe may not be the optimal solution as labels of close semantic (e.g., afraid and terrified) may not be differentiated in such space, which harms the performance. In this paper, we propose HypEmo, a novel framework that can integrate hyperbolic embeddings to improve the FEC task. First, we learn label embeddings in the hyperbolic space to better capture their hierarchical structure, and then our model projects contextualized representations to the hyperbolic space to compute the distance between samples and labels. Experimental results show that incorporating such distance to weight cross entropy loss substantially improve the performance on two benchmark datasets, with around 3% improvement compared to previous state-of-the-art, and could even improve up to 8.6% when the labels are hard to distinguish. Code is available at https://github.com/dinobby/HypEmo.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/2d0cc541-fed6-45ea-a43a-386ed52f3a6d" width="300" height="400"></iframe>

Label-Aware Hyperbolic Embeddings for Fine-grained Emotion Classification

Methods to generate text from structured data have advanced significantly in recent years, primarily due to fine-tuning of pre-trained language models on large datasets. However, such models can fail to produce output faithful to the input data, particularly on out-of-domain data. Sufficient annotated data is often not available for specific domains, leading us to seek an unsupervised approach to improve the faithfulness of output text. Since the problem is fundamentally one of consistency between the representations of the structured data and text, we evaluate the effectiveness of cycle training in this work. Cycle training uses two models which are inverses of each other: one that generates text from structured data, and one which generates the structured data from natural language text. We show that cycle training, when initialized with a small amount of supervised data (100 samples in our case), achieves nearly the same performance as fully supervised approaches for the data-to-text generation task on the WebNLG, E2E, WTQ, and WSQL datasets. We perform extensive empirical analysis with automated evaluation metrics and a newly designed human evaluation schema to reveal different cycle training strategies' effectiveness of reducing various types of generation errors.Our code is publicly available at https://github.com/Edillower/CycleNLG.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/80679978-e161-41be-bf61-19620b4ef9a1" width="300" height="400"></iframe>

Faithful Low-Resource Data-to-Text Generation through Cycle Training

Natural language understanding (NLU) tasks face a non-trivial amount of ambiguous samples where veracity of their labels is debatable among annotators. NLU models should thus account for such ambiguity, but they approximate the human opinion distributions quite poorly and tend to produce over-confident predictions. To address this problem, we must consider how to exactly capture the degree of relationship between each sample and its candidate classes. In this work, we propose a novel method with deep model compression and show how such relationship can be accounted for. We see that more reasonably represented relationships can be discovered in the lower layers and that validation accuracies are converging at these layers, which naturally leads to layer pruning. We also see that distilling the relationship knowledge from a lower layer helps models produce better distribution. Experimental results demonstrate that our method makes substantial improvement on quantifying ambiguity without gold distribution labels. As positive side-effects, our method is found to reduce the model size significantly and improve latency, both attractive aspects of NLU products.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/32bf6552-ecc5-4200-be92-d175e1706eee" width="300" height="400"></iframe>

Deep Model Compression Also Helps Models Capture Ambiguity

Vector representations of natural language are ubiquitous in search applications. Recently, various methods based on contrastive learning have been proposed to learn textual representations from unlabelled data; by maximizing alignment between minimally-perturbed embeddings of the same text, and encouraging a uniform distribution of embeddings across a broader corpus. Differently, we propose maximizing alignment between texts and a composition of their phrasal constituents. We consider several realizations of this objective and elaborate the impact on representations in each case. Experimental results on semantic textual similarity tasks show improvements over baselines that are comparable with state-of-the-art approaches. Moreover, this work is the first to do so without incurring costs in auxiliary training objectives or additional network parameters.

Composition-contrastive Learning for Sentence Embeddings

Universal Information Extraction (UIE) has been introduced as a unified framework for various Information Extraction (IE) tasks and has achieved widespread success. Despite this, UIE models have limitations. For example, they rely heavily on span boundaries in the data during training, which does not reflect the reality of span annotation challenges. Slight adjustments to positions can also meet requirements. Additionally, UIE models lack attention to the limited span length feature in IE. To address these deficiencies, we propose the Fuzzy Span Universal Information Extraction (FSUIE) framework. Specifically, our contribution consists of two concepts: \textit{fuzzy span loss} and \textit{fuzzy span attention}. Our experimental results on a series of main IE tasks show significant improvement compared to the baseline, especially in terms of fast convergence and strong performance with small amounts of data and training epochs. These results demonstrate the effectiveness and generalization of FSUIE in different tasks, settings, and scenarios.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/69e011c4-aee7-489f-94b0-e934bb5d4eb3" width="300" height="400"></iframe>

FSUIE: A Novel Fuzzy Span Mechanism for Universal Information Extraction

Chain-of-thought prompting (e.g., "Let's think step-by-ste") primes large language models to verbalize rationalization for their predictions. While chain-of-thought can lead to dramatic performance gains, benefits appear to emerge only for sufficiently large models (beyond 50B parameters). We show that orders-of-magnitude smaller models (125M---1.3B parameters) can still benefit from chain-of-thought prompting. To achieve this, we introduce Symbolic Chain-of-Thought Distillation (SCoTD), a method to train a smaller student model on rationalizations sampled from a significantly larger teacher model. Experiments across several commonsense benchmarks show that: 1) SCoTD enhances the performance of the student model in both supervised and few-shot settings, and especially for challenge sets; 2) sampling many reasoning chains per instance from the teacher is paramount; and 3) after distillation, student chain-of-thoughts are judged by humans as comparable to the teacher, despite orders of magnitude fewer parameters. We test several hypotheses regarding what properties of chain-of-thought samples are important, e.g., diversity vs. teacher likelihood vs. open-endedness. We release our corpus of chain-of-thought samples and code.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/9c722a96-0802-4f68-972d-9818d5bcab3d" width="300" height="400"></iframe>

Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Step

Prompt-tuning based few-shot learning has garnered increasing attention in recent years due to its efficiency and promising capability. To achieve the best performance for NLP tasks with just a few samples, it is vital to include as many informative samples as possible and to avoid misleading ones. However, there is no work in prompt-tuning literature addressing the problem of differentiating informative hard samples from misleading ones in model training, which is challenging due to the lack of supervision signals about the quality of the samples to train a well-performed model. We propose a Hard Sample Aware Prompt-Tuning framework (i.e. HardPT) to solve the non-differentiable problem in hard sample identification with reinforcement learning, and to strengthen the discrimination of the feature space without changing the original data distribution via an adaptive contrastive learning method. An extensive empirical study on a series of NLP tasks demonstrates the capability of HardPT in few-shot scenarios. HardPT obtains new SOTA results on all evaluated NLP tasks, including pushing the SST-5 accuracy to 49.5\% (1.1\% point absolute improvement), QNLI accuracy to 74.6\% (1.9\% absolute improvement), NMLI accuracy to 71.5 (0.7\% absolute improvement), TACREV $F_1$-score to 28.2 (1.0 absolute improvement), and i2b2/VA $F_1$-score to 41.2 (1.3 absolute improvement).

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/96db6086-a95d-4a96-8510-da8126132b62" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models

Similar lecture

Claim Verification in the Age of Large Language Models: A Survey

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES