Morocco

Large language models (LLMs) struggle with ex-ante reasoning - making inferences or predictions without access to future information. Even under explicit temporal cutoffs, they often rely on internalized post-cutoff knowledge. To systematically evaluate this issue, we introduce a benchmark that assesses LLMs&#39; ex-ante inference ability across four tasks: stock prediction, question answering, Wikipedia event generation, and scientific publication generation. We quantify temporal leakage using a leakage rate metric, which measures models&#39; reliance on future information beyond cutoff timestamps, and a quality measure that evaluates task performance. Experimental results show that LLMs frequently violate temporal constraints across tasks, revealing persistent challenges in ex-ante reasoning. Our benchmark serves as a rigorous testbed for studying temporal reasoning in time-sensitive contexts and provides complete datasets, results, and evaluation resources to support future research on improving temporal consistency in modern LLMs.

EACL 2026

ExAnte: A Benchmark for Ex-Ante Inference in Large Language Models

ex-ante inference

temporal reasoning

large language models

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

AAAI 2021

Large language models (LLMs) struggle with ex-ante reasoning - making inferences or predictions without access to future information. Even under explicit temporal cutoffs, they often rely on internalized post-cutoff knowledge. To systematically evaluate this issue, we introduce a benchmark that assesses LLMs' ex-ante inference ability across four tasks: stock prediction, question answering, Wikipedia event generation, and scientific publication generation. We quantify temporal leakage using a leakage rate metric, which measures models' reliance on future information beyond cutoff timestamps, and a quality measure that evaluates task performance. Experimental results show that LLMs frequently violate temporal constraints across tasks, revealing persistent challenges in ex-ante reasoning. Our benchmark serves as a rigorous testbed for studying temporal reasoning in time-sensitive contexts and provides complete datasets, results, and evaluation resources to support future research on improving temporal consistency in modern LLMs.

technical paper

#### *Message from the General Chair, Aline Villavicencio*
I’m delighted and honoured to welcome you to the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026), taking place in the beautiful city of Rabat, in Morocco, in March 24-29, 2026. EACL is the flagship European conference of the Association and EACL 2026 proudly continues our field’s tradition of excellence in scholarship, innovation, and inclusivity. I am deeply grateful to the many volunteers whose dedication, generosity, and tireless efforts have made this conference possible.
For the first time EACL is being hosted in the African continent. This is an important milestone for our community, and we are grateful to our Moroccan hosts for enabling this historic moment by bringing this edition of EACL to Rabat. We are also delighted that the Second Arabic NLP School is co-located with EACL. We hope attendees enjoy this wonderful opportunity to strengthen ties with the Computational Linguistics communities across the African continent. *[Read full message](https://drive.google.com/file/d/14NlmHvwM6fPJuMmOvVh7K0vtQbEyv3SZ/view?usp=sharing)*<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://underline.io/events/522/reception','_blank')">Go to Workshops and Tutorials Program</button></html>
<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 EACL 2026". 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 are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.eacl.org/registration/) first.

**Online Registration Form**: https://acl.swoogo.com/eacl2026

Registration Required

Welcome to the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL). EACL 2026 will be held in Rabat, Morocco, from March 24–29, 2026. 

The miscalibration of Large Reasoning Models (LRMs) undermines their reliability in high-stakes domains, necessitating methods to accurately estimate the confidence of their long-form, multi-step outputs. To address this gap, we introduce the Reasoning Model Confidence estimation Benchmark (RMCB), a public resource of 347,496 reasoning traces from six popular LRMs across different architectural families. The benchmark is constructed from a diverse suite of datasets spanning high-stakes domains, including clinical, financial, legal, and mathematical reasoning, alongside complex general reasoning benchmarks, with correctness annotations provided for all samples. Using RMCB, we conduct a large-scale empirical evaluation of over ten distinct representation-based methods, spanning sequential, graph-based, and text-based architectures. Our central finding is a persistent trade-off between discrimination (AUROC) and calibration (ECE): text-based encoders achieve the best AUROC (0.672), while structurally-aware models yield the best ECE (0.148), with no single method dominating both. Furthermore, we find that increased architectural complexity does not reliably outperform simpler sequential baselines, suggesting a performance ceiling for methods relying solely on chunk-level hidden states. This work provides the most comprehensive benchmark for this task to date, establishing rigorous baselines and demonstrating the limitations of current representation-based paradigms.

How Reliable are Confidence Estimators for Large Reasoning Models? A Systematic Benchmark on High-Stakes Domains

Large language models (LLMs) have achieved remarkable success across a wide range of tasks, yet fine-tuning them efficiently under black-box or memory-constrained settings remains challenging. Parameter-efficient fine-tuning (PEFT) techniques such as LoRA alleviate memory usage by restricting updates to low-rank adapters, while zeroth-order (ZO) optimization further avoids back-propagation by estimating gradients from function evaluations. Recent work, such as LOZO, leverages random low-rank perturbations to reduce the variance of ZO estimates, but it overlooks the intrinsic geometric structure of LoRA adapters and suffers from unstable convergence and limited integration with adaptive optimizers. To address these limitations, we propose RoZO, a Riemannian zeroth-order optimization framework that constrains updates to the tangent space of the LoRA manifold. By exploiting geometry-aware updates with parallel transport, adaptive preconditioning, and trust-region control, RoZO achieves more stable convergence, tighter variance bounds, and superior performance compared to existing ZO methods.

RoZO: Geometry-Aware Zeroth-Order Fine-Tuning on Low-Rank Adapters for Black-Box Large Language Models

LLMs have recently been explored by psychometrics researchers as proxies for human participants. Although they show considerable potential in automating labor-intensive tasks and bridging AI research with psychological studies, these models often fail to generate heterogeneous data with human-like diversity, which diminishes their value in advancing social science research. To address this gap, we proposed a novel method to incorporate psychological insights into LLM simulation through the Personality Structured Interview (PSI). PSI leveraged psychometric scale-development procedures to capture personality-related linguistic information from a formal psychological perspective. To systematically evaluate the simulation fidelity, we developed a measurement theory grounded evaluation procedure that considers the latent construct nature of personality and evaluates its reliability, structural validity, and external validity. Results from three experiments demonstrate that PSI effectively improves human-like heterogeneity in LLM-simulated personality data and predicts personality-related behavioral outcomes. We further develop a theoretical framework for designing theory-informed structured interviews to enhance the reliability and effectiveness of LLMs in simulating human-like data for broader psychometric research.

Generative Personality Simulation via Theory-Informed Structured Interview

Large Language Models (LLMs) have achieved substantial progress in alignment, ensuring safer and more reliable outputs. However, jailbreak attacks can still bypass these safeguards and provoke harmful responses from well-aligned models. While some studies have achieved defenses against jailbreak attacks by modifying output distributions or detecting harmful content, the exact rationale still remains elusive. In this work, we present a novel neuron-level interpretability method that focuses on the role of safety-related knowledge neurons. Unlike existing approaches, our method projects the model's internal representation into a more consistent and interpretable vocabulary space. We then show that adjusting the activation of safety-related neurons can effectively control the model's behavior with a mean ASR higher than 97%. Building on this insight, we propose SafeTuning, a fine-tuning strategy that reinforces safety-critical neurons to improve model robustness against jailbreaks. SafeTuning consistently reduces attack success rates across multiple LLMs and outperforms all four baseline defenses. These findings offer a new perspective on understanding and defending against jailbreak attacks.

Unraveling LLM Jailbreaks Through Safety Knowledge Neurons

The advent of Large Language Models (LLMs) has significantly advanced web-based Question Answering (QA) systems over semi-structured content, raising questions about the continued utility of knowledge extraction for question answering. This paper investigates the value of triple extraction in this new paradigm by extending an existing benchmark with knowledge extraction annotations and evaluating commercial and open-source LLMs of varying sizes. Our results show that web-scale knowledge extraction remains a challenging task for LLMs. Despite achieving high QA accuracy, LLMs can still benefit from knowledge extraction, through augmentation with extracted triples and multi-task learning. These findings provide insights into the evolving role of knowledge triple extraction in web-based QA and highlight strategies for maximizing LLM effectiveness across different model sizes and resource settings.

Knowledge Extraction on Semi-Structured Content: Does It Remain Relevant for Question Answering in the Era of LLMs?

Visual metonymy is a cognitive mechanism through which a concept is evoked indirectly by presenting associated visual cues rather than explicitly depicting it. These associative links prompt viewers to infer broader concepts. In this work, we present the first computational investigation of visual metonymy. We introduce a novel pipeline grounded in semiotic theory, that leverages large language models and text-to-image models to generate metonymic visual representations. Using this framework, we construct ViMET, the first visual metonymy dataset comprising 2,000 multiple-choice questions to evaluate the cognitive reasoning abilities in multimodal language models. Experimental results on our dataset reveal a significant gap between human performance (86.9%) and state-of-the-art vision-language models (65.9%), highlighting limitations in machines ability to interpret indirect visual references.

Inferring the Unseen: A Computational Approach to Visual Metonymy

Large language model (LLM)-based systems now power chatbots, computer-use agents, and even robots, relying on prompts that often require costly manual tuning. LLM-based prompt optimizers cut that effort by iteratively refining prompts with scored feedback, yet their security has gone largely unexamined. Our work provides the first systematic analysis of poisoning risks in this optimization loop, revealing that optimization itself can become a new vulnerability point. Using HarmBench, we show optimized systems are far more vulnerable to manipulated feedback than to malicious queries, with Attack Success Ratio jumping by up by 48% absolute points. We propose a feedback-poisoning attack that embeds fake reward tokens in prompts, significantly boosting attack success under realistic assumptions, and evaluate tailored defenses that drastically decrease that threat. Our findings establish prompt optimization pipelines as an urgent and underexplored attack surface for LLM safety research, calling for stronger safeguards in future optimization frameworks.

Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers

Health wellness agents typically rely on large language models (LLMs) for response generation, where contextual information from a user's conversation history can be used for response grounding and personalization. High-quality conversation summaries are one such method which can reduce the number of input tokens during response generation, decreasing overhead and inference latency. However, directly purposing LLMs for this task is infeasible due to the scale of the task, the compute overhead, and health data compliance regulations. Furthermore, ground truth for real-world datasets is scarce due to privacy concerns and the high cost of health expert annotators. These factors necessitate the development of small, potentially on-device, language models capable of health dialogue summarization, particularly in the absence of ground truth labels. In this paper, we first present a comprehensive empirical study that benchmarks a variety of state-of-the-art smaller language models to better understand their baseline capabilities. Second, we present an unsupervised method that uses the summaries from multiple models, refined with iterative feedback, to generate high-quality summaries of health dialogues. Experiments illustrate that our method is able to outperform baseline on both open-source and proprietary benchmarks. Notably, our method can be run viably on local compute without a GPU, using just a single Macbook with 16 GB of memory.

Compact Language Models with Iterative Text Refinement for Health Dialogue Summarization

There are many methods and systems to tackle the ontology alignment problem, yet a major challenge persists in producing high-quality mappings among a set of input ontologies. Adopting a human-in-the-loop approach during the alignment process has become essential in applications requiring very accurate mappings. However, user involvement is expensive when dealing with large ontologies. In this paper, we evaluate the feasibility of using Large Language Models (LLM) to aid the ontology alignment problem. The use of LLMs is focused only on the validation of a subset of correspondences where an ontology alignment system (e.g., LogMap) is very uncertain. We have conducted an extensive analysis over several tasks of the Ontology Alignment Evaluation Initiative (OAEI), reporting in this paper the performance of several state-of-the-art LLMs using different ontology-driven prompt templates. In the OAEI 2025 Bio-ML track, LogMap with an LLM-based Oracle has achieved the top-2 overall results. LLM efficacy is also assessed against simulated Oracles with varying error rates.

Large Language Models as Oracles for Ontology Alignment

Most realistic task automation problems require large language models (LLMs) to call tools, which often return complex JSON responses. These responses must be further processed to derive the information necessary for task completion. The ability of LLMs to do so is under-studied. In this paper, we study the tool response processing task and LLMs' abilities to process structured (JSON) responses. We created a dataset for this task, and evaluated 15 open and closed weight models using multiple prompting approaches. Our results show that JSON processing remains a difficult task even for frontier models across multiple prompting strategies. The optimal response processing strategy depends on both the nature and size of the tool outputs, as well as the complexity of the required reasoning. Variations in processing approaches can lead to performance differences ranging from 3% to 50%.

Downloads

Next from EACL 2026

How Reliable are Confidence Estimators for Large Reasoning Models? A Systematic Benchmark on High-Stakes Domains

Similar lecture

Bayesian Persuasion under Ex Ante and Ex Post Constraints

.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 EACL 2026

How Reliable are Confidence Estimators for Large Reasoning Models? A Systematic Benchmark on High-Stakes Domains

Similar lecture

Bayesian Persuasion under Ex Ante and Ex Post Constraints

Downloads