Morocco

he rapid integration of large language models (LLMs) into high-stakes legal work has exposed a critical gap: no benchmark exists to systematically stress-test their reliability against the nuanced, adversarial, and often subtle flaws present in real-world contracts. To address this, we introduce CLAUSE, a first-of-its-kind benchmark designed to evaluate the fragility of an LLM&#39;s legal reasoning. We study the capabilities of LLMs to detect and reason about fine-grained discrepancies by producing over 7500 real-world perturbed contracts from foundational datasets like CUAD and ContractNLI. Our novel, persona-driven pipeline generates 10 distinct anomaly categories, which are then validated against official statutes using a Retrieval-Augmented Generation (RAG) system to ensure legal fidelity. We use CLAUSE to evaluate leading LLMs’ ability to detect embedded legal flaws and explain their significance. Our analysis shows a key weakness: these models often miss subtle errors and struggle even more to justify them legally. Our work outlines a path to identify and correct such reasoning failures in legal AI.

EACL 2026

Better Call CLAUSE: A Discrepancy Benchmark for Auditing LLMs Legal Reasoning Capabilities

legal reasoning in llms

llm robustness

anomaly detection

benchmark

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community."<br>

*Message from the General Chair, Dirk Hovy*





<br>

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

he rapid integration of large language models (LLMs) into high-stakes legal work has exposed a critical gap: no benchmark exists to systematically stress-test their reliability against the nuanced, adversarial, and often subtle flaws present in real-world contracts. To address this, we introduce CLAUSE, a first-of-its-kind benchmark designed to evaluate the fragility of an LLM's legal reasoning. We study the capabilities of LLMs to detect and reason about fine-grained discrepancies by producing over 7500 real-world perturbed contracts from foundational datasets like CUAD and ContractNLI. Our novel, persona-driven pipeline generates 10 distinct anomaly categories, which are then validated against official statutes using a Retrieval-Augmented Generation (RAG) system to ensure legal fidelity. We use CLAUSE to evaluate leading LLMs’ ability to detect embedded legal flaws and explain their significance. Our analysis shows a key weakness: these models often miss subtle errors and struggle even more to justify them legally. Our work outlines a path to identify and correct such reasoning failures in legal AI.

poster

#### *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. 

We introduce ChemComp, the first chemistry-focused benchmark for evaluating compositional multi-hop reasoning in large language models (LLMs). Our automated pipeline constructs benchmarks from proprietary or public data by integrating generative reasoning models, chemical named-entity recognition, and external knowledge bases to build knowledge graphs. Applied to recent chemistry literature, this approach minimizes overlap with LLM pretraining data. The resulting dataset comprises 1,188 multi-hop questions, refined through domain-expert feedback and robust evaluation protocols. Using ChemComp, we systematically compare LLM performance with and without retrieval augmentation, including an idealized gold-context scenario. Our results show that even state-of-the-art models struggle with compositional reasoning: retrieval significantly improves accuracy, yet reasoning errors persist even under perfect retrieval. These findings highlight the limitations of current LLMs and the critical role of retrieval-augmented methods in scientific reasoning. Furthermore, our pipeline is generalizable with fine-tuning, enabling the creation of challenging multi-hop reasoning benchmarks across domains and proprietary datasets.

Evaluating Multi-Hop Reasoning in Large Language Models: A Chemistry-Centric Benchmark

We introduce SymPyBench, a large-scale synthetic benchmark of 15K university-level physics problems (90/10% train/test split). Each problem is fully parameterized, supporting an effectively infinite range of input configurations, and is accompanied by structured, step-by-step reasoning and executable Python code that produces the ground-truth solution for any parameter set. The benchmark contains three question types: MC-Symbolic (multiple-choice with symbolic options), MC-Numerical (multiple-choice with numerical options), and free-form (open-ended responses). These diverse formats test complementary reasoning skills. In addition to standard accuracy, we introduce three new metrics: Consistency Score, Failure Rate, and Confusion Rate, that quantify variability and uncertainty across problem variants. Experiments with state-of-the-art instruction-tuned language models reveal both strengths and limitations in scientific reasoning, positioning SymPyBench as a foundation for developing more robust and interpretable reasoning systems.

SymPyBench: A Dynamic Benchmark for Scientific Reasoning with Executable Python Code

When language models correctly parse "The cat that the dog chased meowed,'' are they analyzing syntax or simply familiar with dogs chasing cats? Despite extensive benchmarking, we lack methods to distinguish structural understanding from semantic pattern matching. We introduce **CenterBench**, a dataset of 9,720 comprehension questions on center-embedded sentences (like "The cat [that the dog chased] meowed'') where relative clauses nest recursively, creating processing demands from simple to deeply nested structures. Each sentence has a syntactically identical but semantically implausible counterpart (e.g., mailmen prescribe medicine, doctors deliver mail) and six comprehension questions testing surface understanding, syntactic dependencies, and causal reasoning. Testing six models reveals that performance gaps between plausible and implausible sentences widen systematically with complexity, with models showing median gaps up to 26.8 percentage points, quantifying when they abandon structural analysis for semantic associations. Notably, semantic plausibility harms performance on questions about resulting actions, where following causal relationships matters more than semantic coherence. Reasoning models improve accuracy while their traces expose semantic shortcuts, overthinking, and answer refusal. Unlike models whose plausibility advantage systematically widens with complexity, humans show variable semantic effects. CenterBench provides the first framework to identify when models shift from structural analysis to pattern matching.

The Dog the Cat Chased Stumped the Model: Measuring When Language Models Abandon Structure for Shortcuts

Extremist groups develop complex in-group language, also referred to as cryptolects, to exclude or mislead outsiders. We investigate the ability of current language technologies to detect and interpret the cryptolects of two online extremist platforms. Evaluating eight models across six tasks, our results indicate that general purpose LLMs cannot consistently detect or decode extremist language. However, performance can be significantly improved by domain adaptation and specialised prompting techniques. These results provide important insights to inform the development and deployment of automated moderation technologies. We further develop and release novel labelled and unlabelled datasets, including 19.4M posts from extremist platforms and lexicons validated by human experts.

IYKYK: Using language models to decode extremist cryptolects

We present AutoBool, a reinforcement learning (RL) framework that trains large language models (LLMs) to generate effective Boolean queries for medical systematic reviews. Boolean queries are the primary mechanism for literature retrieval in this domain and must achieve high recall while maintaining reasonable precision---a challenging balance that existing prompt-based LLM approaches often struggle to achieve. A major limitation in this space is the lack of ground-truth best Boolean queries for each topic, which makes supervised fine-tuning impractical. AutoBool addresses this challenge by leveraging RL to directly optimize query generation against retrieval performance metrics, without requiring ideal target queries. To support this effort, we create and release the largest dataset of its kind: 65 588 topics in total for training and evaluating the task of automatic Boolean query formulation. Experiments on our new dataset and two established datasets (CLEF TAR and Seed Collection) show that AutoBool significantly outperforms zero-shot/few-shot prompting and matches or exceeds the effectiveness of much larger GPT-based models (e.g., GPT-4o, O3) using smaller backbones. It also approaches effectiveness of expert-authored queries while retrieving 10вЂ“16 times fewer documents. Ablation studies reveal the critical roles of model backbone, size, decoding temperature, and prompt design. Code and data are available at https://anonymous.4open.science/r/AutoBool-B3E5/.

AutoBool: Reinforcement-Learned LLM for Effective Automatic Systematic Reviews Boolean Query Generation

Understanding narratives requires identifying which events are most salient for a story's progression. We present a contrastive learning framework for modeling narrative salience that learns story embeddings from narrative twins: stories that share the same plot but differ in surface form. Our model is trained to distinguish a story from both its narrative twin and a distractor with similar surface features but different plot. Using the resulting embeddings, we evaluate four narratologically motivated operations for inferring salience (deletion, shifting, disruption, and summarization). Experiments on short narratives (ROCStories) and longer Wikipedia plot summaries show that contrastively learned story embeddings outperform a masked-language-model baseline, and that summarization is the most reliable operation for identifying salient sentences. If retellings are not available, random dropout can be used to generate narrative twins from a single story. Effective distractors can be obtained either by prompting LLMs or, in long-form narratives, by using different parts of the same story.

Contrastive Learning with Narrative Twins for Modeling Story Salience

The intentional creation and spread of disinformation poses a significant threat to public discourse. However, existing English datasets and research rarely address the intentionality behind the disinformation. This work presents MALINT, the first human-annotated English corpus developed in collaboration with expert fact-checkers to capture disinformation and its malicious intent. We utilize our novel corpus to benchmark 12 language models, including small language models (SLMs) such as BERT and large language models (LLMs) like Llama 3.3, on binary and multilabel intent classification tasks. Moreover, inspired by inoculation theory from psychology and communication studies, we investigate whether incorporating knowledge of malicious intent can improve disinformation detection. To this end, we propose intent-based inoculation, an intentвЂ‘augmented reasoning for LLMs that integrates intent analysis to mitigate the persuasive impact of disinformation. Analysis on six disinformation datasets, five LLMs, and seven languages shows that intentвЂ‘augmented reasoning improves zeroвЂ‘shot disinformation detection. To support research in intentвЂ‘aware disinformation detection, we release the MALINT dataset with annotations from each annotation step.

MALicious INTent Dataset and Inoculating LLMs for Enhanced Disinformation Detection

Quality estimation is omnipresent in machine translation, for both evaluation and generation. Unfortunately, quality estimation models are often opaque and computationally expensive, making them impractical to be part of large-scale pipelines. In this work, we tackle two connected challenges: (1) reducing the cost of quality estimation at scale, and (2) developing an inexpensive uncertainty estimation method for quality estimation. To address the latter, we introduce Instant Confidence COMET, an uncertainty-aware quality estimation model that matches the performance of previous approaches at a fraction of their costs. We extend this to Early-Exit COMET, a quality estimation model that can compute quality scores and associated confidences already at early model layers, allowing us to early-exit computations and reduce evaluation costs. We also apply our model to machine translation reranking. We combine Early-Exit COMET with an upper confidence bound bandit algorithm to find the best candidate from a large pool without having to run the full evaluation model on all candidates. In both cases (evaluation and reranking) our methods reduce the required compute by 50% with very little degradation in performance. Finally, we show how Instant Confidence COMET can be used to decide which translations a human evaluator should score rather than relying on the COMET score.

Early-Exit and Instant Confidence Translation Quality Estimation

Multi-modal summarization (MMS) has emerged as a critical research area driven by the proliferation of multimedia content, focusing on generating condensed summaries by cross-modal complementary information synthesis. Previous studies have demonstrated the effectiveness of heterogeneous fusion paradigms, particularly through visual-centric feature extraction mechanisms, in constructing cross-modal representations that yield substantial performance gains. However, the use of multi-modal information and the inter-correlation among textual content, visual elements, and summary generation are still underestimated. We propose the Patch-Refined Visual Information Network (PRVIN) to address the insufficient exploitation of visual information. The essential patch selector and patch refiner components in PRVIN work collaboratively to progressively identify and refine critical visual features. An additional vision-to-summary alignment mechanism is also introduced to enhance the semantic connections between multi-modal representations and summary outputs. Extensive experiments conducted on two public MMS benchmark datasets demonstrate the superiority of PRVIN while quantitatively validating the crucial role of comprehensive visual information utilization in MMS tasks.\footnote{Our code will be available at

Progressive Visual Refinement for Multi-modal Summarization

Neuro-symbolic NLP methods aim to leverage the complementary strengths of large language models and formal logical solvers. However, current approaches are mostly static in nature, i.e., the integration of a target solver is predetermined at design time, hindering the ability to employ diverse formal inference strategies. To address this, we introduce an adaptive, multi-paradigm, neuro-symbolic inference framework that: (1) automatically identifies formal reasoning strategies from problems expressed in natural language; and (2) dynamically selects and applies specialized formal logical solvers via autoformalization interfaces. Extensive experiments on individual and multi-paradigm reasoning tasks support the following conclusions: LLMs are effective at predicting the necessary formal reasoning strategies with an accuracy above 90%. This enables flexible integration with formal logical solvers, resulting in our framework outperforming competing baselines -- by 17% and 6% compared to GPT-4o and DeepSeek-V3.1, respectively. Moreover, adaptive reasoning can even positively impact pure LLM methods, yielding gains of 10%, 5%, and 6% on zero-shot, CoT, and CoT sym settings with GPT-4o. Finally, although smaller models struggle with adaptive neuro-symbolic reasoning, post-training offers a viable path to improvement. Overall, this work establishes the foundations for adaptive LLM-symbolic reasoning, offering a path forward for unifying material and formal inferences on heterogeneous reasoning challenges. The code and data are available [online](https://github.com/idiap/adaptive symbolic reasoning).

Downloads

Next from EACL 2026

Evaluating Multi-Hop Reasoning in Large Language Models: A Chemistry-Centric Benchmark

Similar lecture

CLaw: Benchmarking Chinese Legal Knowledge in Large Language Models - A Fine-grained Corpus and Reasoning Analysis