PromptEng'26 - Workshop on Prompt Engineering for Pre-Trained Language Models

The recent achievements and availability of Large Language Models has paved the road to a new range of applications and use-cases. Pre-trained language models are now being involved at-scale in many fields where they were until now absent from. More specifically, the progress made by causal generative models has opened the door to using them through textual instructions aka. prompts. Unfortunately, the performances of these prompts are highly dependent on the exact phrasing used and therefore practitioners need to adopt fail-retry strategies.

In a nutshell, PromptEng provides the research community with a forum to discuss, exchange and design advanced prompting techniques for LLM applications.

This third international workshop on prompt engineering aims at gathering practitioners (both from Academia and Industry) to exchange good practices, optimizations, results and novel paradigms about the designing of efficient prompts to make use of LLMs.

Undoubtedly, the recent Large Language Models (LLMs) are becoming more and more omnipotent in many tasks. Different sub-fields from the Semantic Web such as Knowledge Graph construction, knowledge verbalization, Web pages summarization have considerably benefited from such a prompting mechanism. The ability to query and interact with them using prompts is crucial to generate high-quality output in the desired format. While existing contributions have been made towards prompt engineering, several difficulties and challenges remain to gain a better understanding of how those LLMs respond to different prompts. Typically, the way instructions are conveyed in prompts can lead to either distinct or similar output from the models.

Moreover, some instructions are better respected while others are simply ignored for some tasks. So far, LLM-practitioners have been mainly working on their own, developing and testing bespoke techniques to achieve their goals, re-starting the prompt-design tasks for each new model they have been using. Such an approach often leads to tackle problems which have already been explored by other researchers.

This workshop aims to investigate and analyze these behaviors, through experimental analysis and probing of LLMs, in order to gain insights into the models' sensitivity to different prompts. By uncovering significant findings, the community can greatly benefit in utilizing LLMs more effectively while also preventing the generation of harmful content. Ultimately, this workshop endeavors to compile and index successful and unavailing prompts with respect to both tasks and models.

Topics of interest include, but are not limited to themes related to the techniques of prompt engineering:

• Prompts & Chain-of-Thought Prompts Design
• Theoretical and Experimental Analysis of Prompting
• Prompts Transferability
• Specific prompt techniques for Web crawling
• Ontology generation combining LLM and Web data
• Semantic and Syntactic comparison of prompt performances
• Structured Prediction with Prompts
• Prompt Retrieval and Generation
• Visualization with Prompt Techniques

We envision five types of submissions covering the entire workshop topics spectrum:

1. Research Papers (max 10 pages), presenting novel scientific research addressing topics of the workshop.
2. Position & Demo papers (max 5 pages), encouraging papers describing significant work in progress, late breaking results or ideas of the domain, as well as functional systems relevant to the community.
3. Industry & Use Case Presentations (max 5 pages), in which industry experts can present and discuss practical solutions, use case prototypes, best practices, etc. at any stage of implementation.
4. Expression of Interest (max 2 pages), presenting a research topic, a work in progress, practical applications or needs, etc.
5. Technical prompting technique (max 2 pages), describing practically a prompt together with a minimal working example and an associated use-case motivating it.

In order to ease the reviewing process, authors may add the track they are submitting to directly in their titles, for instance: "Article Title [Industry]".

Submissions must be in double-column format, and must adhere to the ACM template and format (also available in Overleaf). The recommended setting for LaTeX is: \documentclass[sigconf, anonymous, review]{acmart}. The PDF files must have all non-standard fonts embedded. Workshop submissions must be self-contained and in English. Note: The review process is single-blind, no need for authors to submit anonymous articles.

If possible, we envision to have formal proceedings through CEUR-WS.

All papers should be submitted to https://easychair.org/my2/conference?conf=www2026workshops.

• Submission: December 18^th December 26^th, 2025
• Notification: January 20^th, 2026
• Camera-ready: February 2^nd, 2026
• Presentation: April 13^th-14^th, 2026 June 29^th, 2026

Attending the workshop

PromptEng will take place on 29^th of June 2026 afternoon from 2:00pm to 5:30pm. All hours are local Dubai time GST UTC+4.
(In the meantime, please, don't forget to register and attend... ☺)

Keynote #1

Title: Prompting LLMs to Tell the Truth: Factuality, Verification, and Trustworthy Web-Scale AI
Prof. Preslav Nakov, Department Chair and Professor of Natural Language Processing, Mohamed bin Zayed University of Artificial Intelligence, United Arab Emirates
https://mbzuai.ac.ae/study/faculty/preslav-nakov/

Abstract: Large language models are increasingly used through prompts, yet small changes in prompting can substantially affect their accuracy, factuality, confidence, and safety. We argue that prompt engineering must evolve beyond eliciting useful answers toward designing interactions that are evidence-aware, uncertainty-aware, and verifiable. We will examine prompt engineering through the lens of automated fact-checking, hallucination detection, retrieval-augmented verification, media bias analysis, multilingual safety, and human-in-the-loop trust. We will cover some recent work on using LLMs and multimodal LLMs for real-world fact-checking, decomposing complex claims into verifiable reasoning programs, iterative retrieval and verification, uncertainty-based detection of hallucinations, and benchmarks and tools for evaluating factuality. We will also discuss how prompt design can support responsible Web-scale applications, including news analysis, misinformation detection, source profiling, and safeguard evaluation across languages and cultures. The central message is that the next stage of prompt engineering is not only about better prompts, but about prompted systems that can explain, retrieve evidence, assess confidence, recognize risk, and support human judgment.

Bio: Preslav Nakov is Professor and Department Chair for NLP at the Mohamed bin Zayed University of Artificial Intelligence. He is part of the core team at MBZUAI's Institute for Foundation Models that developed Jais, the world's best open-source Arabic-centric LLM, Nanda, the world's best open-weights Hindi model, and Sherkala, the world's best open-weights Kazakh model. Previously, he was Principal Scientist at the Qatar Computing Research Institute, HBKU, where he led the Tanbih mega-project, developed in collaboration with MIT, which aims to limit the impact of "fake news", propaganda and media bias by making users aware of what they are reading, thus promoting media literacy and critical thinking. He received his PhD degree in Computer Science from the University of California at Berkeley, supported by a Fulbright grant. He is Chair of the European Chapter of the Association for Computational Linguistics (EACL), Secretary of ACL SIGSLAV, and Secretary of the Truth and Trust Online board of trustees. Formerly, he was PC chair of ACL 2022, and President of ACL SIGLEX. He is also member of the editorial board of several journals including Computational Linguistics, TACL, ACM TOIS, IEEE TASL, IEEE TAC, CS&L, NLE, AI Communications, and Frontiers in AI. He authored a Morgan & Claypool book on Semantic Relations between Nominals, two books on computer algorithms, and 250+ research papers. He received a Best Paper Award at ACM WebSci'2022, a Best Long Paper Award at CIKM'2020, a Best Resource Paper Award at EACL'2024, a Best Demo Paper Award (Honorable Mention) at ACL'2020, a Best Task Paper Award (Honorable Mention) at SemEval'2020, a Best Poster Award at SocInfo'2019, and the Young Researcher Award at RANLP’2011. He was also the first to receive the Bulgarian President's John Atanasoff award, named after the inventor of the first automatic electronic digital computer. His research was featured by over 100 news outlets, including Reuters, Forbes, Financial Times, CNN, Boston Globe, Aljazeera, DefenseOne, Business Insider, MIT Technology Review, Science Daily, Popular Science, Fast Company, The Register, WIRED, and Engadget, among others.

Keynote #2

Title: Are LLMs a Good Model of Human-like Understanding? The Challenge of Compositional Learning
Prof. Hassan Sajjad, Faculty of Computer Science, the Sexton Chair in AI, and the Director of the HyperMatrix Lab, Dalhousie University, Canada
https://hsajjad.github.io/

Abstract: Every day, we see the release of yet another large language model (LLM) with improved capabilities over its predecessors. Despite this continuous improvement, LLMs remain surprisingly fragile. A subtle change in prompt formatting can lead to substantially different outputs, exposing vulnerabilities to simple jailbreak attacks and raising concerns about their reliability and consistency. In this talk, I will study this limitation by posing a fundamental language understanding question: Do LLMs understand the precise semantics of a sentence? I’ll share insights from our probing studies that evaluate their compositional learning abilities and present our investigation of representational structure, understanding the tradeoff between lexical and semantics knowledge. I will conclude by discussing two research directions we are pursuing to advance these models towards more human-like understanding.

Bio: Hassan Sajjad is an Associate Professor in the Faculty of Computer Science, the Sexton Chair in AI, and the Director of the HyperMatrix Lab at Dalhousie University, Canada. He is a leading researcher in Safe and Trustworthy AI, with a focus on safety alignment, representation learning, interpretability and explainability. His pioneering work on AI interpretability and safety has been published at top-tier venues such as NeurIPS, ICLR, and ACL, and has been featured in leading tech blogs, including MIT News. Beyond his research, Dr. Sajjad actively contributes to the AI and NLP community as a speaker, organizer, area chair, and reviewer for leading machine learning and computational linguistics conferences and journals.

Accepted Articles

• Reasonig vs. Critic-Based Verification for Biomedical Relation Extraction with Large Language Models by Ali Assi, Nour Elislem Karabadji, Mohamed Elati, and Wajdi Dhifli
• Extracting Narrative Structure from Online Labor Discourse: A Prompt-Based Operationalization of the Actantial Model by Yuntong Ji
• WordWeaver: Interactive System for facilitating Digital Story Illustration by Maryam Kermanshahani, Sajad Shirali-Shahreza, and Gerald Penn
• Probing Instruction Execution Stability of Large Language Models under Semantic Paraphrase by Bodhisatta Maiti and Debshree Chowdhury
• TAPR: Enhancing LLM Performance with a Task-Aware Prompt Rewriter by Oliver Savolainen, Emanuele Bastianelli, Hosein Azarbonyad, and Ana Lucic
• Let My Crush See Me: Social-Facilitation Prompting for Zero-Shot LLM Performance Gains by Vikranth Udandarao
• Evaluating Mathematical Reasoning in Large Language Models: A Comprehensive Analysis of Prompting Strategies on the Google DeepMind Mathematics Dataset by Saanidhya Vats, Rui Min, Subramanyam Sahoo, Siddharth Mohapatra, Aman Chadha, Vinija Jain, and Divya Chaudhary

Agenda

Organisers

• Damien Graux (EcoVadis, UK) leads a team of research scientists at EvoVadis that is specialised in AI/ML. He has been contributing to research efforts in Knowledge Computing technologies: focusing inter alia on Semantic Web, designing complex pipelines for heterogeneous Big Data and LLM-based knowledge management. Prior to this, he had research positions at Huawei R&D (UK), at Inria (France), Trinity College Dublin (Ireland) and Fraunhofer IAIS (Germany). He has been involved in the organisations of many international workshops at major conferences such as the LASCAR (co-located with ESWC) or the MEPDaW (co-located with ISWC) series, or recently NORA at NeurIPS.
• Sebastien Montella (Huawei Ltd., UK) is a research scientist at the Huawei Edinburgh Research Center. During his Ph.D., he specialized in Natural Language Generation and Knowledge Graph Embeddings research areas. Additionally, he has a keen interest in statistical learning, geometric deep learning, natural language processing, and computer vision. In the past, Sebastien as co-organized the 18th Workshop on Spoken Dialogue Systems for PhDs, PostDocs & New Researchers (YRRSDS) in Edinburgh, Scotland (2022).
• Hajira Jabeen (UniKlinik Cologne, Germany) leads the 'AI in Research Data Management' team at the Institute for Biomedical Informatics. Her team leverages artificial intelligence and large language models (LLMs) to enhance research data management practices, particularly in the biomedical field. They focus on developing scalable, AI-driven tools and workflows that improve data organization, integration, and analysis, driving innovative, data-centric solutions. Hajira has a diverse background in research and teaching, with prior affiliations at the University of Bonn, the University of Cologne, and ITU Copenhagen. She has also organized numerous workshops and conferences in data science and informatics.

Program Committee

Important Dates

• Submission (EasyChair): December 26^th, 2025
• Notification: January 20^th, 2026
• Camera-ready: February 2^nd, 2026
• Presentation: June 29^th, 2026