Morocco

Multi-LLM systems enhance the creativity of large language models by simulating human collective intelligence but suffer from significant drawbacks, such as high computational costs and inference latency. To address these limitations, we propose BILLY (BlendIng persona vectors for Large Language model creativitY), a training-free framework that captures the benefits of multi-LLM collaboration, i.e. inducing diverse perspectives and specialized expertise, within a single model. BILLY operates by extracting and blending multiple distinct persona vectors directly in the model&#39;s activation space. We steer the model&#39;s generation process with this merged vector while inference, enabling multi-perspective output without explicit multi-LLM communication. Our experiments across creativity-oriented benchmarks demonstrate that BILLY surpasses single model prompting and traditional multi-LLM approaches, while substantially reducing inference time and computational costs. Our analyses further reveal that distinct persona vectors can be blended to achieve both effective control over complementary aspects of generation and greater interpretability.

EACL 2026

BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generation

activation steering

creativity

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

ACL 2024

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

Multi-LLM systems enhance the creativity of large language models by simulating human collective intelligence but suffer from significant drawbacks, such as high computational costs and inference latency. To address these limitations, we propose BILLY (BlendIng persona vectors for Large Language model creativitY), a training-free framework that captures the benefits of multi-LLM collaboration, i.e. inducing diverse perspectives and specialized expertise, within a single model. BILLY operates by extracting and blending multiple distinct persona vectors directly in the model's activation space. We steer the model's generation process with this merged vector while inference, enabling multi-perspective output without explicit multi-LLM communication. Our experiments across creativity-oriented benchmarks demonstrate that BILLY surpasses single model prompting and traditional multi-LLM approaches, while substantially reducing inference time and computational costs. Our analyses further reveal that distinct persona vectors can be blended to achieve both effective control over complementary aspects of generation and greater interpretability.

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. 

Multi-hop reasoning over long contexts remains challenging, as it requires integrating relevant contexts scattered across distant sources while resisting semantic drift and noise from distracting content. While retrieval-augmented generation (RAG) has emerged as the prevailing solution, most RAG approaches encode and store context in monolithic memory representations, resulting in noisy retrieval and brittle reasoning. To overcome these limitations, we introduce TAG (Tailoring Memory Granularity), a framework that prestructures memory into diverse granularities and employs a reward-guided navigator to adaptively compose hybrid memory tailored to each query. The navigator is trained with a multi-objective Bradley–Terry loss that learns the relative utility of different memory types, enabling dynamic routing across granularities. This design allows RAG systems to balance fine-grained detail with high-level abstraction, yielding more reliable reasoning. Extensive experiments on long-context multi-hop question answering (QA) benchmarks show that TAG achieves state-of-the-art performance. With only 0.033% additional parameters, it remains lightweight, highlighting its practicality as a scalable and effective solution for enhancing language model agents in complex, real-world scenarios.

Tailoring Memory Granularity for Multi-Hop Reasoning over Long Contexts

Social engineering scams increasingly employ personalized, multi-turn deception, exposing the limits of traditional detection methods. While Large Language Models (LLMs) show promise in identifying deception, their cognitive assistance potential remains underexplored. We propose ScriptMind, an integrated framework for LLM-based scam detection that bridges automated reasoning and human cognition. It comprises three components: the Crime Script Inference Task (CSIT) for scam reasoning, the Crime Script–Aware Inference Dataset (CSID) for fine-tuning small LLMs, and the Cognitive Simulation-based Evaluation of Social Engineering Defense (CSED) for assessing real-time cognitive impact. Using 571 Korean scam cases, we built 22,712 structured scammer-sequence training instances. Experimental results show that the 11B small LLM fine-tuned with ScriptMind outperformed GPT-4o by 13%, achieving superior performance over commercial models in detection accuracy, false-positive reduction, scammer utterance prediction, and rationale quality. Moreover, in phone scam simulation experiments, it significantly enhanced and sustained users’ suspicion levels, improving their cognitive awareness of scams. ScriptMind represents a step toward human-centered, cognitively adaptive LLMs for scam defense.

SCRIPTMIND: Crime Script Inference and Cognitive Evaluation for LLM-based Social Engineering Scam Detection System

Automatic Speech Recognition (ASR) is increasingly integral to healthcare services, where medical conversations present unique transcription challenges due to specialized terminology and frequent introduction of new terms. Existing ASR models, including widely used systems like Whisper, struggle with high word error rates (WER) on clinical vocabulary, especially medication names, primarily due to the scarcity of annotated audio-transcript data in the medical domain. This paper proposes and evaluates a novel synthetic data generation pipeline that produces comprehensive doctor-patient dialogues in both text and audio forms, specifically targeting a curated set of over 124,000 medical terms. The pipeline generated over 1 billion audios with ground truth transcriptions. Fine-tuning ASR models with this synthetic corpus significantly reduced overall WER and improved transcription accuracy on medical terms, marking a significant advance in healthcare ASR accuracy. Data generation code, dataset, and training and evaluation scripts are released.

Synthetic Doctor-Patient Dialogue Generation for Robust Medical ASR: A Scalable Pipeline for Vocabulary Expansion and Privacy Preservation

Fine-tuning a task-specific multilingual large language model (LLM) involves training the model on a multilingual dataset with examples in all the required languages. Updating one or more supported languages with additional data or adding support for a new language involves retraining the model, which can be computationally inefficient and creates a severe maintenance bottleneck. Recent research on merging multilingual multitask models has shown promise in terms of improved quality, but its computational and maintenance efficiency remains unstudied. In this work, we provide the first focused analysis of this merging strategy from an efficiency perspective, evaluating it across three independent tasks. We demonstrate significant efficiency gains while maintaining parity in terms of quality: this merging approach reduces the initial training time by up to 50\%. We also demonstrate that updating an individual language and re-merging as part of model maintenance reduces training costs by more than 60\%, compared to re-training the full multilingual model. We show this on both public and proprietary industry datasets confirming that the approach works well for industrial use cases in addition to academic settings already studied in previous work.

Improving Training Efficiency and Reducing Maintenance Costs via Language Specific Model Merging

Multi-turn tool-calling LLMs — models capable of invoking external APIs or tools across several user turns — have emerged as a key feature in modern AI assistants, enabling extended dialogues from benign tasks to critical business, medical, and financial operations. Yet implementing multi-turn pipelines *remains difficult for many safety-critical industries* due to ongoing concerns regarding model resilience. While standardized benchmarks, such as the Berkeley Function-Calling Leaderboard (BFCL), have underpinned confidence concerning advanced function-calling models (like Salesforce’s xLAM V2), there is still a lack of visibility into multi-turn conversation-level robustness, especially given their exposure to real-world systems. In this paper, we introduce **Assertion-Conditioned Compliance (A-CC)**, a novel evaluation paradigm for multi-turn function-calling dialogues. A-CC provides holistic metrics that evaluate a model’s behavior when confronted with misleading assertions originating from two distinct vectors: (1) user-sourced assertions (USAs), which measure sycophancy toward plausible but misinformed user beliefs, and (2) function-sourced assertions (FSAs), which measure compliance with plausible but contradictory system policies (e.g., stale hints from unmaintained tools). Our results show that models are highly vulnerable to both USA sycophancy and FSA policy conflicts, confirming A-CC as a critical, latent vulnerability in deployed agents.

Assertion-Conditioned Compliance: A Provenance-Aware Vulnerability in Multi-Turn Tool-Calling Agents

Extracting actionable suggestions from customer reviews is essential for operational decision-making, yet these directives are often embedded within mixed-intent, unstructured text. Existing approaches either classify suggestion-bearing sentences or generate high-level summaries, but rarely isolate the precise improvement instructions businesses need. We evaluate a hybrid pipeline combining a high-recall RoBERTa classifier trained with a precision–recall surrogate to reduce unrecoverable false negatives with a controlled, instruction-tuned LLM for suggestion extraction, categorization, clustering, and summarization. Across real-world hospitality and food datasets, the hybrid system outperforms prompt-only, rule-based, and classifier-only baselines in extraction accuracy and cluster coherence. Human evaluations further confirm that the resulting suggestions and summaries are clear, faithful, and interpretable. Overall, our results show that hybrid reasoning architectures achieve meaningful improvements fine-grained actionable suggestion mining while highlighting challenges in domain adaptation and efficient local deployment.

A Hybrid Supervised-LLM Pipeline for Actionable Suggestion Mining in Unstructured Customer Reviews

Medical vision-language models (Med-VLMs) offer a new and effective paradigm for digital health in tasks such as disease diagnosis using clinical images and text. In these tasks, an important but underexplored research question is how Med-VLMs interpret and respond to user-provided clinical information, especially when the prompts are noisy. For a systematic evaluation, we construct Med-CP, a large-scale visual question answering (VQA) benchmark designed to comprehensively evaluate the influence of clinical prompts across diverse modalities, anatomical regions, and diagnostic tasks. Our experiments reveal that existing Med-VLMs tend to follow user-provided prompts blindly, regardless of whether they are accurate or not, raising concerns about their reliability in real-world interactions. To address this problem, we introduce a novel supervised fine-tuning (SFT) approach for Med-VLMs based on cross-modal reflection chain-of-thought (CoT) across medical images and text. In our SFT method, the Med-VLM is trained to produce reasoning paths for the analysis of the medical image and the user-provided prompt. Then, the final answer is determined by conducting a reflection on the visual and textual information. Experimental results demonstrate that our method considerably enhances the robustness against noisy user-provided prompts for both in-domain and out-of-domain evaluation scenarios.

Benchmarking and Mitigating the Impact of Noisy User Prompts in Medical VLMs via Cross-Modal Reflection

Rigorous evaluation of large language models (LLMs) relies on comparing models by the prevalence of desirable or undesirable behaviors, such as task pass rates or policy violations. These prevalence estimates are produced by a classifier, either an LLM-as-a-judge or human annotators, making the choice of classifier central to trustworthy evaluation. Common metrics used for this choice, such as Accuracy, Precision, and F1, are sensitive to class imbalance and to arbitrary choices of positive class, and can favor judges that distort prevalence estimates. We show that Youden’s J statistic is theoretically aligned with choosing the best judge to compare models, and that Balanced Accuracy is an equivalent linear transformation of J. Through both analytical arguments and empirical examples and simulations, we demonstrate how selecting judges using Balanced Accuracy leads to better, more robust classifier selection.

Balanced Accuracy: The Right Metric for Evaluating LLM Judges - Explained through Youden’s J statistic

We introduce MEET-MR (Machine Translation EnglishвЂ“Thai MQM and Ranking Dataset), a comprehensive benchmark for evaluating EnglishвЂ“Thai machine translation systems. The dataset is constructed using the Multidimensional Quality Metrics (MQM) annotation framework, providing fine-grained human judgments of translation quality. In addition, MEET-MR includes human preference rankings and reference translations, enabling both absolute and relative assessments of translation quality. The dataset spans 9 diverse domains ensuring rich linguistic and contextual diversity. By combining high-quality reference translations, objective MQM error annotations, and subjective preference rankings, MEET-MR serves as a valuable resource for studying translation quality estimation, model alignment with human evaluation, and cross-domain performance in EnglishвЂ“Thai machine translation.

Machine translation Evaluation Eng-Thai MQM Ranking dataset

Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, yet their limited truthfulness and tendency toward overconfidence restrict their reliability when needing to state facts. Uncertainty quantification offers a promising approach to identify and manage unreliable outputs from LLMs. However, most existing uncertainty quantification methods typically require multiple sampling or external inference models, resulting in increased computational overhead. To address these limitations, we propose an efficient uncertainty quantification method that leverages semantic information inherently encoded within LLMs. Specifically, we cluster tokens into semantically coherent groups based on embedding similarity and prefix matching, and compute a cluster-based uncertainty score at each decoding step. Our approach requires only a single deterministic generation and does not rely on external inference models. Experiments across multiple datasets and models show that our method achieves performance comparable to existing baselines while significantly reducing computational overhead.

Downloads

Next from EACL 2026

Tailoring Memory Granularity for Multi-Hop Reasoning over Long Contexts

Similar lecture

Quantifying the Persona Effect in LLM Simulations

.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

Tailoring Memory Granularity for Multi-Hop Reasoning over Long Contexts

Similar lecture

Quantifying the Persona Effect in LLM Simulations

Downloads