Morocco

We investigate how the choice of output format influences the fine-tuning performance of large language models on sequence labelling- based information extraction tasks. Across more than 280 experiments spanning multiple benchmarks, model families, and formats, we find that the output format is a critical yet often overlooked hyperparameter. In some cases, the choice of format alone can shift F1 scores by over 40% on the same dataset and model. Further, we observe that no single format consistently dominates across settings - the optimal choice depends on factors like model family, size and dataset characteristics. Overall, these results demonstrate that even informationally equivalent output formats can produce substantial performance variation, highlighting the need to treat output formatting as a key factor in building robust and reliable information extraction systems.

EACL 2026

Lost in Formatting: How Output Formats Skew LLM Performance on Information Extraction

semantic role labelling

event extraction

benchmarking

named entity recognition

structured prediction

fine-tuning

evaluation

information extraction

### Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Welcome to the 2025 meeting of the Nations of the Americas Chapter of the Association for Computational Linguistics! I am proud to help organize the first NAACL conference to carry the new name of our organization, one that emphasizes inclusion for all of the Americas. I am also pleased to welcome you to Albuquerque, New Mexico, a state whose unique blend of cultural influences will make for an excellent backdrop for NAACL 2025, especially with this year’s special theme on NLP in a Multicultural World. 
**[Continue reading...](https://drive.google.com/file/d/1jX-qGhqVSZZCIrAnJaz798pflu5Irrdn/view?usp=sharing)**

*- Colin Cherry, Google, NAACL 2025 General Chair* 

[![](https://assets.underline.io/markdown_image/1/image/b087f8a4dc5816d6e1a6514e59c59ac3.png)](https://drive.google.com/file/d/1T96GzPqObXrMln2BMByCSXTSizjTg69P/view?usp=sharing)

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Please log in to explore this event.

To access NAACL 2025 event page you are required to register. Please follow [**this link**](https://2025.naacl.org/registration/registration/) to register. Access will depend on your registration type.

Please register!

NAACL 2025

Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

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)* 

<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>

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 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. 

Real-world financial filings report critical information about an entity's investment holdings, essential for assessing that entity's risk, profitability, and relationship profile. Yet, these details are often buried in messy, multi-page, fragmented tables that are difficult to parse, hindering downstream QA and data normalization. Specifically, 99.4% of the tables in our financial table dataset lack bounding boxes, with the largest table spanning 44 pages. To address this, we present TASER (Table Agents for Schema-guided Extraction and Recommendation), a continuously learning, agentic table extraction system that converts highly unstructured, multi-page, heterogeneous tables into normalized, schema-conforming outputs. Guided by an initial portfolio schema, TASER executes table detection, classification, extraction, and recommendations in a single pipeline. Our Recommender Agent reviews unmatched outputs and proposes schema revisions, enabling TASER to outperform vision-based table detection models such as Table Transformer by 10.1%. Within this continuous learning process, larger batch sizes yield a 104.3% increase in useful schema recommendations and a 9.8% increase in total extractions. To train TASER, we manually labeled 22,584 pages and 3,213 tables covering $731.7 billion in holdings, culminating in TASERTab to facilitate research on real-world financial tables and structured outputs. Our results highlight the promise of continuously learning agents for robust extractions from complex tabular data.

TASER: Table Agents for Schema-guided Extraction and Recommendation

Recent advances in mathematical reasoning typically rely on massive scale, yet the question remains: can strong reasoning capabilities be induced in small language models (<=1.5B) under extreme constraints? We investigate this by training models on a single A40 GPU (48GB) for under 24 hours using Reinforcement Learning with Verifiable Rewards (RLVR) and Low-Rank Adaptation (LoRA). We find that the success of this ``micro-budget" regime depends critically on the interplay between adapter capacity and model initialization. While low-rank adapters (r=8) consistently fail to capture the complex optimization dynamics of reasoning, high-rank adapters (r=256) unlock significant plasticity in standard instruction-tuned models. Our best result achieved an impressive 40.0% Pass@1 on AIME 24 (an 11.1% absolute improvement over baseline) and pushed Pass@16 to 70.0%, demonstrating robust exploration capabilities. However, this plasticity is not universal: while instruction-tuned models utilized the budget to elongate their chain-of-thought and maximize reward, heavily math-aligned models suffered performance collapse, suggesting that noisy, low-budget RL updates can act as destructive interference for models already residing near a task-specific optimum.

Plasticity vs. Rigidity: The Impact of Low-Rank Adapters on Reasoning on a Micro-Budget

The rapid adoption of Small Language Models (SLMs) for resource constrained applications has outpaced our understanding of their ethical and fairness implications. To address this gap, we introduce the Vacuous Neutrality Framework (VaNeu), a multi-dimensional evaluation paradigm designed to assess SLM fairness prior to deployment. The framework examines model robustness across four stages - biases, utility, ambiguity handling, and positional bias over diverse social bias categories. To the best of our knowledge, this work presents the first large-scale audit of SLMs in the 0.5–5B parameter range, an overlooked “middle tier” between BERT-class encoders and flagship LLMs. We evaluate nine widely used SLMs spanning four model families under both ambiguous and disambiguated contexts. Our findings show that models demonstrating low bias in early stages often fail subsequent evaluations, revealing hidden vulnerabilities and unreliable reasoning. These results underscore the need for a more comprehensive understanding of fairness and reliability in SLMs, and position the proposed framework as a principled tool for responsible deployment in socially sensitive settings. The code is available at: https://github.com/smanduru10/Vacuous-Neutrality-Framework.git.

Beyond Bias Scores: Unmasking Vacuous Neutrality in Small Language Models

Retrieval-augmented generation has become the dominant paradigm for deploying large language models in knowledge-intensive applications, yet practitioners lack guidance on model selection when both quality and costs matter. We evaluate language models from 4B to 70B parameters, including PLLuM and Bielik families of Polish LLM, within a Polish Wikipedia-based RAG pipeline. Quality assessment uses GPT-4o pairwise comparison across 1,000 PolQA questions with bias mitigation and Bradley-Terry ranking, while energy measurements capture inference costs on NVIDIA H100 hardware. Our findings challenge conventional scaling assumptions: parameter scaling beyond 12B offers minimal quality gains, with mid-size PLLuM-12 matching 70B performance while reducing energy consumption by 83\%.

Evaluating Cost-Efficiency of LLMs in a RAG Setup on Polish Wikipedia: Quality vs. Energy Consumption

The ability of AI systems to not only answer complex natural language questions, but also transparently justify their reasoning, is crucial for building trust and enabling effective human-AI collaboration. In domains requiring multi-hop reasoning, answers must often be constructed by combining multiple relevant sentences from a knowledge base to build an inferential path from the question toward the answer. We tackle this challenge by exploring a neuro-symbolic approach to reasoning through the generation of entailment trees -- structured, step-by-step proof trees -- using Large Language Models (LLMs). These trees provide interpretable justifications for the inference process. Using the EntailmentBank~\citep{dalvi2021explaining} data set, we evaluated a diverse set of prompting strategies across multiple models, along with a proposal of an inference-guided prompting approach that performs well. We also fine-tuned LLMs trained specifically for proof generation by applying several data augmentation, curriculum learning, and reinforcement-guided optimization strategies. Our results show that the fine-tuned model outperforms all prompting strategies, achieving superior performance across multiple structural and semantic metrics. We also provide a detailed evaluation of which training strategies are helpful towards proof generation. Our findings highlight the importance of proof tree generation as a benchmark for evaluating structured reasoning in LLMs.

From Sentences to Proof Trees: Leveraging Language Models for Structured Reasoning

We revisit MWE-aware linguistic tokenization as a character-level and token-level sequence labeling problem and present a systematic evaluation on English, German, Italian, and Dutch data. We compare a standard tokenizer trained without MWE-awareness as a baseline (UDPipe), a character-level SRN+CRF model (Elephant), and transformer-based MaChAmp models trained either directly on gold character labels or as token-level postprocessors on top of UDPipe. Our results show that the two-stage pipeline -- UDPipe pretokenization followed by MaChAmp postprocessing -- consistently yields the best accuracy. Our analysis of error patterns highlights how different architectures trade off over- and undersegmentation. These findings provide practical guidance for building MWE-aware tokenizers and suggest that postprocessing pipelines with transformers are a strong and general strategy for non-standard tokenization.

Trainable, Multiword-aware Linguistic Tokenization Using Modern Neural Networks

Diagram-grounded geometry problem solving is a critical benchmark for multimodal large language models (MLLMs), yet the benefits of multi-agent design over single-agent remain unclear. We systematically compare single-agent and multi-agent pipelines on four visual math benchmarks: Geometry3K, MathVerse, OlympiadBench, and We-Math. For open-source models, multi-agent consistently improves performance. For example, Qwen-2.5-VL (7B) gains +6.8 points and Qwen-2.5-VL (32B) gains +3.3 on Geometry3K, and both Qwen-2.5-VL variants see further gains on OlympiadBench and We-Math. In contrast, the closed-source Gemini-2.0-Flash generally performs better in single-agent mode on classic benchmarks, while multi-agent yields only modest improvements on the newer We-Math dataset. These findings show that multi-agent pipelines provide clear benefits for open-source models and can assist strong proprietary systems on newer, less familiar benchmarks, but agentic decomposition is not universally optimal. All code, data, and reasoning files are available at https://github.com/faiyazabdullah/Interpreter-Solver

Do Multi-Agents Solve Better Than Single? Evaluating Agentic Frameworks for Diagram-Grounded Geometry Problem Solving and Reasoning

Large language models (LLMs) require careful alignment to balance competing objectives: factuality, safety, conciseness, proactivity, and diversity. Existing studies focus on individual techniques or specific dimensions, lacking a holistic assessment of the inherent trade-offs. We propose a unified evaluation framework that compares LLM alignment methods (PPO, DPO, ORPO, KTO) across these five axes, using both in-distribution and out-of-distribution datasets. Leveraging a specialized LLM‑as‑Judge prompt, validated through human studies, we reveal that DPO and KTO excel in factual accuracy, PPO and DPO lead in safety, and PPO best balances conciseness with proactivity. Our findings provide insights into trade-offs of common alignment methods, guiding the development of more balanced and reliable LLMs.

Rethinking the Evaluation of Alignment Methods: Insights into Diversity, Generalisation, and Safety

Radiology report generation involves translating visual signals from pixels into precise clinical language. Existing encoder-decoder models often suffer from hallucinations, generating plausible but incorrect medical findings. We propose GraphRAG-Rad, a novel architecture that integrates biomedical knowledge through a novel Latent Visual-Semantic Retrieval (VSR). Unlike traditional Retrieval-Augmented Generation (RAG) methods that rely on textual queries, our approach aligns visual embeddings with the latent space of the Knowledge Graph, PrimeKG. The retrieved sub-graph guides the Visual Encoder and the Multi-Hop Reasoning Module. The reasoning module simulates clinical deduction paths (Ground-Glass Opacity → Viral Pneumonia → COVID-19) before it combines the information with visual features in a Graph-Gated Cross-Modal Decoder. Experiments on the COV-CTR dataset demonstrate that GraphRAG-Rad achieves competitive performance with strong results across multiple metrics. Furthermore, ablation studies show that integrating latent retrieval and reasoning improves performance significantly compared to a visual-only baseline. Qualitative analysis further reveals interpretable attention maps. These maps explicitly link visual regions to symbolic medical concepts, effectively bridging the modality gap between vision and language.

GraphRAG-Rad: Concept-Aware Radiology Report Generation via Latent Visual-Semantic Retrieval

Clinical Natural Language Processing (NLP) integrates large language models (LLMs) to extract biomedical insights from unstructured clinical text. Most named entity recognition (NER) and relation extraction (RE) datasets rely on manual annotation, which is costly and difficult to scale. Many biomedical knowledge graphs (KG) suffer from underspecified relations, conflate causal and correlational claims, and edges lack evidence for reasoning. This dissertation presents a semantic stability framework for constructing explainable KGs, highlighting stable extraction as fundamental for scalable NER and RE, and essential for graph structure. We applied this to Substance Use Disorders (SUD) and Social Determinants of Health (SDOH) from PubMed corpus and NER and RE annotation guide. Multiple LLMs perform extraction under shared semantic constraints, with disagreements resolved through Human-in-the-Loop (HITL) validation. We define semantic stability through NER and RE metrics, using stabilized gold data for model training and evaluation. We then develop a claim-centered KG, where edges represent evidence, provenance, relation type, directionality, polarity, and stability indicators. This benchmark and pipeline supports multi-hop reasoning, triadic SUD–SDOH–SUD mediation patterns, and feedback loop analysis. This will advance etiological inquiries and data-driven health policy analysis.

Downloads

Next from EACL 2026

TASER: Table Agents for Schema-guided Extraction and Recommendation

Similar lecture

LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs