Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)

From Paper to Structured JSON: An Agentic AI Workflow for Compliant BMR Digital Transformation (2026.eacl-industry)

Challenge:	Large Language Models (LLMs) have shown promise in identifying deception, but their cognitive assistance potential remains underexplored.
Approach:	They propose a framework for LLM-based scam detection that bridges automated reasoning and human cognition.
Outcome:	The proposed framework outperforms GPT-4o in the Korean scam detection and phone scam simulations.

Copied to clipboard

Bhavik Agarwal, Nidhi Bendre, Viktoria Rojkova

Challenge:	Agentic AI workflow converts noisy pharmaceutical batch records into validated JSON preserving GMP-critical structure.
Approach:	They propose a workflow that transforms unstructured batch records into validated JSON using hybrid OCR, vision–language and schema-guided LLMs.
Outcome:	The proposed workflow cuts QA review time from hours to minutes while preserving key GMP-critical structure.

Compact Multimodal Language Models as Robust OCR Alternatives for Noisy Textual Clinical Reports (2026.eacl-industry)

Copied to clipboard

Nikita Neveditsin, Pawan Lingras, Salil Patil, Swarup Patil, Vijay Kumar Mago

PersonaTrace: Synthesizing Realistic Digital Footprints with LLM Agents (2026.eacl-industry)

Challenge:	Conventional OCR systems perform poorly under noisy, real-world conditions . compact multimodal models outperform classical and neural OCR pipelines .
Approach:	They evaluate compact multimodal language models for transcribing noisy medical documents . they compare eight different models to find the best transcription accuracy and noise sensitivity .
Outcome:	The proposed models outperform classical and neural OCR pipelines in transcription accuracy, noise sensitivity, numeric accuracy and computational efficiency.

Copied to clipboard

Minjia Wang, Yunfeng Wang, Xiao Ma, Dexin Lv, Qifan Guo, Lynn Zheng, Benliang Wang, Lei Wang, Jiannan Li, Yongwei Xing, Junzhe Xu, Zheng Sun

Challenge:	Publicly available corpora cover only slivers of human activity, such as email threads, chat logs, purchase histories, sensor traces, and provide large-scale supervision for data-hungry machine-learning pipelines.
Approach:	They propose a method for synthesizing realistic digital footprints using large language model agents from a structured user profile.
Outcome:	The proposed method generates diverse sequences of user events, producing corresponding digital artifacts such as emails, messages, calendar entries, reminders, etc.

Evaluating the Pre-Consultation Ability of LLMs using Diagnostic Guidelines (2026.eacl-industry)

Copied to clipboard

Jean Seo, Gibaeg Kim, Kihun Shin, Seungseop Lim, Hyunkyung Lee, Wooseok Han, Jongwon Lee, Eunho Yang

Challenge:	EPAG is a benchmark dataset and evaluation pipeline for pre-consultation of large language models.
Approach:	They propose a benchmark dataset and framework for evaluating pre-consultation ability of LLMs using diagnostic guidelines.
Outcome:	The proposed framework outperforms frontier LLMs in pre-consultation.

SELENE: Selective and Evidence-Weighted LLM Debating for Efficient and Reliable Reasoning (2026.eacl-industry)

Copied to clipboard

Akshay Verma, Swapnil Gupta, Deepak Gupta, Prateek Sircar, Siddharth Pillai

SymPyBench: A Dynamic Benchmark for Scientific Reasoning with Executable Python Code (2026.eacl-industry)

Challenge:	Existing multi-agent debate frameworks are computationally expensive and prone to degradation under pro-longed debates due to redundant exchanges and unstable judging.
Approach:	They propose a framework that unifies Selective Debate Initiation (SDI) with Evidence Weighted Self-Consistency (EWSC) for adaptive, debate-on-demand reasoning.
Outcome:	Evaluated on BoolQ, CosmosQA, and an internal QnA benchmark, the proposed framework achieves higher factual robustness and efficiency.

Copied to clipboard

Shima Imani, Seungwhan Moon, Adel Ahmadyan, Lu Zhang, Ahmed Kirmani, Babak Damavandi

KV Pareto: Systems-Level Optimization of KV Cache and Model Compression for Long Context Inference (2026.eacl-industry)

Challenge:	Existing benchmarks do not capture the complexity of structured, step-by-step reasoning essential in physics and related domains.
Approach:	They propose a large-scale synthetic benchmark of 15K university-level physics problems . they use structured, step-by-step reasoning and executable Python code to produce the ground-truth solution.
Outcome:	The proposed model is based on a set of 15K university-level physics problems with three question types.

Copied to clipboard

Sai Gokhale, Devleena Das, Rajeev Patwari, Ashish Sirasao, Elliott Delaye

MizanQA: A Benchmark for Multi-Answer Moroccan Legal QA (2026.eacl-industry)

Challenge:	Long-context Large Language Models (LLMs) face significant memory bottlenecks due to the linear growth of key-value (KV) cache with sequence length.
Approach:	They propose a framework that maps the trade-off frontier between total memory consumption and task accuracy across three complementary optimization techniques.
Outcome:	The proposed model-specific configurations achieve 68-78% total memory reduction with minimal (1-3%) accuracy degradation on long-context tasks.

Copied to clipboard

Adil Bahaj, Mounir Ghogho

Question Answering

Challenge:	Using a benchmark, large language models can be evaluated on Moroccan legal MCQs . despite their ability to comprehend and process Arabic, the language is still a challenge .
Approach:	They propose a benchmark for assessing LLMs on Moroccan legal MCQs . they use Arabic-based questions enriched with Moroccan idioms to assess their accuracy .
Outcome:	The proposed benchmark covers 1,776 expert-verified questions in Arabic enriched with Moroccan idioms . it measures accuracy, precision-penalized F1-like score, and calibration errors .

Router-Suggest: Dynamic Routing for Multimodal Auto-Completion in Visually-Grounded Dialogs (2026.eacl-industry)

Copied to clipboard

Sandeep Mishra, Devichand Budagam, Anubhab Mandal, Bishal Santra, Pawan Goyal, Manish Gupta

Beyond Unified Models: A Service-Oriented Approach to Low Latency, Context Aware Phonemization for Real Time TTS (2026.eacl-industry)

Challenge:	a task that grounds predictions in multimodal context is essential for chatbots, chatbot systems and healthcare consultations.
Approach:	They propose a task that grounds predictions in multimodal context to better capture user intent.
Outcome:	The proposed task can be used to predict upcoming characters in live chats using partially typed text and visual cues.

Copied to clipboard

Mahta Fetrat Qharabagh, Donya Navabi, Zahra Dehghanian, Morteza Abolghasemi, Hamid R. Rabiee

Retrieval Enhancements for RAG: Insights from a Deployed Customer Support Chatbot (2026.eacl-industry)

Challenge:	Lightweight, real-time text-to-speech systems often rely on lightweight phonemizers . a new framework aims to bridge the trade-off between phonemization quality and inference speed .
Approach:	They propose lightweight strategies for context-aware phonemization and a service-oriented TTS architecture that executes these modules as independent services.
Outcome:	The proposed system improves pronunciation soundness and linguistic accuracy while maintaining real-time responsiveness.

Copied to clipboard

Daniel González Juclà, Mohit Tuteja, Marcos Esteve Casademunt, Keshav Unnikrishnan, Yasir Usmani, Arvind Roshaan

Scaling Intent Understanding: A Framework for Classification with Clarification using Lightweight LLMs (2026.eacl-industry)

Challenge:	a persistent gap remains between Recall@10 and Recall @50 across datasets .
Approach:	They evaluate embedding model comparison, Reciprocal Rank Fusion and embedded concatenation techniques to improve retrieval quality.
Outcome:	The proposed methods outperform traditional cross-encoders in identifying high-relevance passages.

Copied to clipboard

Subhadip Nandi, Tanishka Agarwal, Anshika Singh, Priyanka Bhatt

Beyond IVR: Benchmarking Customer Support LLM Agents for Business-Adherence (2026.eacl-industry)

Challenge:	Proprietary large-language models (LLMs) assign intents to user utterances without addressing ambiguity.
Approach:	They propose a domain-agnostic framework that equips open-source LLMs with the ability to perform intent classification and generate clarification questions in case of ambiguity.
Outcome:	The proposed framework performs intent classification and generates clarification questions in case of ambiguity.

Copied to clipboard

Sumanth Balaji, Piyush Mishra, Aashraya Sachdeva, Suraj Agrawal

HotelQuEST: Balancing Quality and Efficiency in Agentic Search (2026.eacl-industry)

Challenge:	Existing benchmarks focus on tool usage or task completion, overlooking an agent’s capacity to adhere to multi-step policies, navigate task dependencies, and remain robust to unpredictable user or environment behavior.
Approach:	They propose a benchmark to assess policy-aware agents in customer support using a dynamic-prompt agent and a static-promped agent that explicitly models policy control.
Outcome:	The proposed benchmark assesses agent's ability to adhere to multi-step policies, navigate task dependencies, and remain robust to unpredictable user or environment behavior.

Copied to clipboard

Guy Hadad, Shadi Iskander, Sofia Tolmach, Oren Kalinsky, Haggai Roitman, Ran Levy

TASER: Table Agents for Schema-guided Extraction and Recommendation (2026.eacl-industry)

Challenge:	Existing benchmarks for agentic search focus primarily on answer quality, overlooking efficiency factors that are critical for real-world deployment.
Approach:	They propose a benchmark for hotel search queries that includes 214 hotel query queries that range from simple factual requests to complex queries.
Outcome:	The proposed benchmarks show that LLM-based agents achieve higher accuracy than traditional retrievers, but at substantially higher costs due to redundant tool calls and suboptimal routing that fails to match query complexity to model capability.

Copied to clipboard

Nicole Cho, Kirsty Fielding, William Watson, Sumitra Ganesh, Manuela Veloso

TAGQuant: Token-Aware Clustering for Group-Wise Quantization (2026.eacl-industry)

Challenge:	Real-world financial filings report critical information about an entity’s investment holdings, but they are often buried in messy, multi-page, fragmented tables that are difficult to parse.
Approach:	They propose to train a system that converts highly unstructured, multi-page, heterogeneous tables into normalized, schema-conforming outputs.
Outcome:	The proposed system outperforms vision-based table detection models by 10.1% and can generate more useful recommendations by 10%.

Copied to clipboard

Jaeseong Lee, Seung-won Hwang, Aurick Qiao, Zhewei Yao, Yuxiong He

Text Clustering

Challenge:	Existing work clusters channels using token dimension, which is suboptimal for grouping . a common challenge in LLM quantization is supporting "group-wise" quantization .
Approach:	They propose a method to group channels with similar activation distributions using tokens . they propose shuffle operation that reduces relative GSM8K error by 86% .
Outcome:	The proposed method reduces GSM8K error by 86% in both INT4 and MXFP4 formats compared to baselines .

Beyond Grid Search: Leveraging Bayesian Optimization for Accelerating RAG Pipeline Optimization (2026.eacl-industry)

Copied to clipboard

Anum Afzal, Xueru Zheng, Florian Matthes

BornoDrishti: Leveraging Vision Encoders and Domain-Adaptive Learning for Bangla OCR on Diverse Documents (2026.eacl-industry)

Challenge:	Finding optimal configurations via grid search is computationally prohibitive, limiting real-world scalability.
Approach:	They compare BO with grid search to find optimal configurations for RAG pipelines . their framework explores global pipeline and local component-wise optimization .
Outcome:	The proposed approach reduces optimization time by up to 84% while maintaining comparable accuracy.

Copied to clipboard

S M Jishanul Islam, Md Mehedi Hasan, Masbul Haider Ovi, Akm Shahariar Azad Rabby, Fuad Rahman

MobileCity: An Efficient Framework for Large-Scale Urban Behavior Simulation (2026.eacl-industry)

Challenge:	Existing solutions for OCR for Bangla scripts are limited to single-domain processing.
Approach:	They propose a unified OCR system that recognizes both printed and handwritten Bangla scripts within a single model.
Outcome:	The proposed system achieves competitive accuracy across both domains and surpasses specialized uni-domain systems.

Copied to clipboard

Xiaotong Ye, Nicolas Bougie, Toshihiko Yamasaki, Narimawa Watanabe

Is Micro Domain-Adaptive Pre-Training Effective for Real-World Operations? Multi-Step Evaluation Reveals Potential and Bottlenecks (2026.eacl-industry)

Challenge:	Existing methods for simulating realistic urban behaviors rely on static profiles and synchronous inference pipelines that hinder scalability.
Approach:	They propose a lightweight generative agent framework for city-scale simulation powered by cognitively-grounded generative agents.
Outcome:	Experiments with 4,000 agents show that MobileCity generates more human-like urban dynamics than baselines while maintaining high computational efficiency.

Copied to clipboard

Masaya Tsunokake, Yuta Koreeda, Terufumi Morishita, Koichi Nagatsuka, Hikaru Tomonari, Yasuhiro Sogawa

A Compliance-Preserving Retrieval System for Aircraft MRO Task Search (2026.eacl-industry)

Challenge:	Domain-adaptive pre-training (DAPT) is one approach for enabling LLMs to handle unseen knowledge.
Approach:	They propose to disentangle the answering process into three subtasks and evaluate the performance of each subtask.
Outcome:	The proposed model resolves the elicitation task that the base model struggled with but does not resolve other subtasks.

Copied to clipboard

Byungho Jo

No Label? No Problem: Unsupervised Continual Learning for Adaptive Medical ASR (2026.eacl-industry)

Challenge:	Aircraft Maintenance Technicians spend up to 30% of their work time searching manuals . field reports indicate that up to 60% of technicians' time is spent searching for the correct procedure .
Approach:	They propose a semantic retrieval system that adapts LLM reranking to aviation MRO environments . evaluators construct revision-robust embeddings from ATA chapter hierarchies and use vision-language parsing to structure certified content.
Outcome:	The proposed system reduces the time spent searching for procedures in manuals by 90% . the system is based on a revision-robust embedding from ATA chapter hierarchies .

Copied to clipboard

Meizhu Liu, Tao Sheng

EduPulse: A Practical LLM-Enhanced Opinion Mining System for Vietnamese Student Feedback in Educational Platforms (2026.eacl-industry)

Challenge:	Medical audio often contains specialized terminology, such as medication names, which existing ASR systems struggle to transcribe accurately.
Approach:	They propose an unsupervised continual learning ASR framework that adapts to new data while preserving prior knowledge.
Outcome:	Experiments on real-world medical audio show that the proposed framework improves over state-of-the-art models.

Copied to clipboard

Nguyen Xuan Phuc, Phi Nguyen Xuan, Vinh-Tiep Nguyen, Thìn Dang Van, Ngan Luu-Thuy Nguyen

Sentiment Analysis

Challenge:	EduPulse is a system designed specifically to analyze student feedback in Vietnamese.
Approach:	They propose a system that analyzes student feedback in Vietnamese to improve opinion mining.
Outcome:	The proposed system performs four opinion analysis tasks in Vietnamese . it is scalable and maintainable, and it is cost-effective, the authors show .

When Speed Meets Intelligence: Scalable Conversational NER in an Ever-evolving World (2026.eacl-industry)

Copied to clipboard

Karim Ghonim, Antonio Roberto, Davide Bernardi

Dialogue Systems & Conversational Agents

Challenge:	Large Language Models excel at understanding conversational semantics, but lack of data makes them impractical for production deployment.
Approach:	They propose a pipeline for generating multilingual conversational NER datasets with minimal human validation and a framework that leverages LLMs as semantic filters combined with catalog-based entity grounding to label live traffic data.
Outcome:	The proposed framework outperforms existing models on public and private conversations by 97.12% on CoNLL-2003 and 83.09% on OntoNotes 5.0.

ReflectiveRAG: Rethinking Adaptivity in Retrieval-Augmented Generation (2026.eacl-industry)

Copied to clipboard

Akshay Verma, Swapnil Gupta, Siddharth Pillai, Prateek Sircar, Deepak Gupta

OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale Datasets (2026.eacl-industry)

Challenge:	Existing methods for retrieval-augmented generation (RAG) fail to assess evidence sufficiency, detect subtle mismatches or reduce redundancy.
Approach:	They propose a lightweight yet reasoning-driven architecture that enhances factual grounding . ReflectiveRAG employs self-reflective retrieval and Contrastive noise removal .
Outcome:	a new architecture improves factual grounding by using self-reflective retrieval and Contrastive noise removal.

Copied to clipboard

Jiyuan Shen, Yuan Peiyue, Atin Ghosh, Yifan Mai, Daniel Dahlmeier

PatentVision: A multimodal method for drafting patent applications (2026.eacl-industry)

Challenge:	Multimodal Large Language Models (MLLMs) are used for document information extraction, but their impact on document information processing remains unclear.
Approach:	They propose an automated hierarchical error analysis framework that leverages large language models to diagnose errors systematically.
Outcome:	The proposed framework can achieve comparable performance to OCR-enhanced approaches.

Copied to clipboard

Ruo Yang, Sai Krishna Reddy Mudhiganti, Manali Sharma

VideoMind: Thinking in Steps for Long Video Understanding (2026.eacl-industry)

Challenge:	PatentVision integrates textual and visual inputs to generate patent specifications . existing systems fail to capture the nuanced interplay between textual, visual components .
Approach:	They propose a multimodal framework that integrates textual and visual inputs to generate patent specifications.
Outcome:	The proposed framework surpasses text-only methods in patent writing, the authors show . it integrates visual data to better represent intricate design features and functional connections .

Copied to clipboard

Shubhang Bhatnagar, Renxiong Wang, Kapil Krishnakumar, Adel Ahmadyan, Zhaojiang Lin, Lambert Mathias, Xin Luna Dong, Babak Damavandi, Narendra Ahuja, Seungwhan Moon

Visual Data in NLP

Challenge:	Multimodal Large Language Models struggle with Long Video Understanding due to their limited context window and the distributed nature of salient information across many redundant frames.
Approach:	They propose a training framework that mimics a human reasoning process to train Long Video Understanding models.
Outcome:	The proposed framework achieves 77.6% performance on Video MME, LongVideo, and MLVU benchmarks while yielding 5% improvement on Llama 4 Scout.

RegNLI: Detecting Online Product Misbranding through Legal and Linguistic Alignment (2026.eacl-industry)

Copied to clipboard

Diya Saha, Abhishek Bharadwaj Varanasi, Tirthankar Dasgupta, Manjira Sinha

CASPER: Bridging Discrete and Continuous Prompt Optimization through Feedback-Guided Gradient Descent (2026.eacl-industry)

Challenge:	Existing approaches to claim verification focus on keyword matching or generic text classification . misbranding involves deceptive labeling or advertising that misleads consumers about a product's nature or quality .
Approach:	They propose a framework that formulates misbranding detection as an inference task between product claims and regulatory provisions.
Outcome:	The proposed framework outperforms baselines in misbranding detection and regulation alignment metrics.

Copied to clipboard

Aryan Jain, Pushpendu Ghosh, Promod Yenigalla

Adaptive Data Flywheel: Applying MAPE Control Loops to AI Agent Improvement (2026.eacl-industry)

Challenge:	Existing pipelines for generative tasks require extensive manual effort and domain expertise to achieve task-optimal performance.
Approach:	They propose a framework bridging discrete and continuous prompt optimization through feedback-guided gradient descent in embedding space.
Outcome:	The proposed framework bridges discrete and continuous prompt optimization through feedback-guided gradient descent in embedding space.

Copied to clipboard

Aaditya Shukla, Sidney Knowles, Meenakshi Madugula, David Farris, Ryan Angilly, Santiago Pombo, Lu An, Anbang Xu, Abhinav Balasubramanian, Tan Yu, Jiaxiang Ren, Rama Akkiraju

Robustness in NLP

Challenge:	NVInfo AI is a generative AI agent that can be deployed in production without full-scale retraining or infrastructure overhauls.
Approach:	They propose to implement a retrieval-augmented generation (RAG)-driven data flywheel in NVInfo AI, a mixture-of-experts knowledge assistant, for 30,000 employees.
Outcome:	The proposed system addresses failures in retrieval-augmented generation pipelines and enables continuous learning.

Medical Summarization in Practice: Design, Deployment, and Analysis of a Clinical Summarization System for a German Hospital (2026.eacl-industry)

Copied to clipboard

Moiz Rauf, Sean Papay

Text Generation

Challenge:	a large number of EHRs are created for a patient, which must be summarized into a discharge summary.
Approach:	They propose to integrate a clinical summarization system into a live german hospital workflow to help with the generation of discharge summaries.
Outcome:	The proposed system can be used in a live german hospital to help with discharge summaries.

Feedback-Aware Prompt Optimization Framework for Generating Job Postings (2026.eacl-industry)

Copied to clipboard

Suraj Maharjan, Ainur Yessenalina, Srinivasan H. Sengamedu

Enhancing User Safety: Context-Aware Detection of Offensive Query-Ad Pairs in Multimodal Search Advertising (2026.eacl-industry)

Challenge:	Creating high-quality job postings is time-consuming and requires significant time from hiring managers and recruiters.
Approach:	They propose a feedback-aware prompt optimization framework that automates high-quality job posting generation through iterative human-in-the-loop refinement.
Outcome:	The proposed framework shows high compliance rates and strong satisfaction scores in both automated and human evaluations.

Copied to clipboard

Gaurav Kumar, Qiangjian Xi, Tanmaya Shekhar Dabral, Hooshang Ghasemi, Abishek Krishnamoorthy, Danqing Fu, Rui Min, Emilio Antunez, Zhongli Ding, Pradyumna Narayana

SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models (2026.eacl-industry)

Challenge:	Multi-modal online advertisements require robust content moderation to ensure user safety . key challenges include nuanced, multi-modal nature of ads, severe data scarcity and class imbalance due to the rarity of offensive content .
Approach:	They propose a framework that detects offensive content only when a user's search query is paired with a specific ad .
Outcome:	The proposed framework reduces the serving of offensive query-ad pairs by more than 80% while maintaining the efficiency required for real-time advertising systems.

Copied to clipboard

Jiaojiao Han, Wujiang Xu, Mingyu Jin, Mengnan Du

Explainability & Interpretability in NLP

Challenge:	Large language models (LLMs) have achieved remarkable progress, yet their internal mechanisms remain largely opaque.
Approach:	They propose an agent-based framework that recasts feature interpretation from a passive, single-pass generation task into an explanation-driven process.
Outcome:	The proposed framework produces explanations with significantly higher generative and predictive accuracy compared to state-of-the-art baselines.

Adapting Vision-Language Models for E-commerce Understanding at Scale (2026.eacl-industry)

Copied to clipboard

Matteo Nulli, Vladimir Orshulevich, Tala Bazazo, Christian Herold, Michael Kozielski, Marcin Mazur, Szymon Tuzel, Cees G. M. Snoek, Seyyed Hadi Hashemi, Omar Javed, Yannick Versley, Shahram Khadivi

MedRiskEval: Medical Risk Evaluation Benchmark of Language Models, On the Importance of User Perspectives in Healthcare Settings (2026.eacl-industry)

Challenge:	Existing approaches to adapt VLMs to attribute-centric, multi-image, and noisy data are limited.
Approach:	They propose a novel evaluation suite that incorporates deep product understanding, strict instruction following, and dynamic attribute extraction.
Outcome:	The proposed model improves e-commerce performance while preserving broad multimodal capabilities.

Copied to clipboard

Jean-Philippe Corbeil, Minseon Kim, Maxime Griot, Sheela Agarwal, Alessandro Sordoni, Francois Beaulieu, Paul Vozila

Synthetic Doctor-Patient Dialogue Generation for Robust Medical ASR: A Scalable Pipeline for Vocabulary Expansion and Privacy Preservation (2026.eacl-industry)

Challenge:	Existing risk evaluations focused on general safety benchmarks, resulting in role-dependent vulnerabilities in real-world medical and clinical deployments.
Approach:	They propose a patient-oriented dataset called PatientSafetyBench that evaluates a variety of open- and closed-source LLMs.
Outcome:	The proposed benchmark examines medical risks from 466 open- and closed-source LLMs across 5 risk categories.

Copied to clipboard

Kefei Liu, Meizhu Liu

Text Generation

Challenge:	Existing ASR models struggle with high word error rates (WER) on clinical vocabulary, especially medication names.
Approach:	They propose to generate doctor-patient dialogues in both text and audio formats using a curated set of over 124,000 medical terms.
Outcome:	The proposed pipeline generated over 1 billion audios with ground truth transcriptions.

Lessons from the Field: An Adaptable Lifecycle Approach to Applied Dialogue Summarization (2026.eacl-industry)

Copied to clipboard

Kushal Chawla, Chenyang Zhu, Pengshan Cai, Sangwoo Cho, Scott Novotney, Ayushman Singh, Jonah Lewis, Keasha Safewright, Alfy Samuel, Erin Babinsky, Shi-Xiong Zhang, Sambit Sahu

LingVarBench: Benchmarking LLMs on Entity Recognitions and Linguistic Verbalization Patterns in Phone-Call Transcripts (2026.eacl-industry)

Challenge:	Summarization of multi-party dialogues is a critical capability in industry . but generating high-quality summaries in practice is challenging . prior work has focused on static datasets and benchmarks, a condition rare in practical scenarios .
Approach:	They present an agentic system to summarize multi-party interactions using static datasets.
Outcome:	The proposed system can summarize multi-party interactions using a set of complex requirements.

Copied to clipboard

Seyedali Mohammadi, Manas Paldhe, Amit Chhabra, Youngseo Son, Vishal Seshagiri

Low-Resource NLP

Challenge:	Existing methods degrade under disfluencies, interruptions, and speaker overlap, yet large real-call corpora are rarely shareable.
Approach:	They propose a benchmark and semantic synthetic data generation pipeline that generates linguistically varied training data via (1) LLM-sampled entity values, (2) curated linguistic verbalization patterns covering diverse disfluencies and entity-specific readout styles, and (3) a value–transcript consistency filter.
Outcome:	The proposed pipeline outperforms zero-shot baselines and matches or closely approaches human-tuned prompts on real customer transcripts.

Improving Training Efficiency and Reducing Maintenance Costs via Language Specific Model Merging (2026.eacl-industry)

Copied to clipboard

Alphaeus Dmonte, Vidhi Gupta, Daniel J Perry, Mark Arehart

The Subtle Art of Defection: Understanding Uncooperative Behaviors in LLM based Multi-Agent Systems (2026.eacl-industry)

Challenge:	Recent research on merging multilingual multitask models has shown promise in terms of improved quality, but its computational and maintenance efficiency remains unstudied.
Approach:	They propose a method for fine-tuning a multilingual large language model . they compare a "retrain-all" approach and a 'train-once, merge-as-needed' approach .
Outcome:	The proposed approach reduces training time by up to 50% while maintaining parity in terms of quality.

Copied to clipboard

Devang Kulshreshtha, Wanyu Du, Raghav Jain, Srikanth Doss, Hang Su, Sandesh Swamy, Yanjun Qi

Challenge:	Existing literature on uncooperative behavior degrades collective outcomes and requires more resilient multi-agent systems.
Approach:	They propose a game theory-based taxonomy of uncooperative agent behaviors and a structured, multi-stage simulation pipeline that dynamically generates and refines uncooperation behaviors as agents’ states evolve.
Outcome:	The proposed framework achieves 96.7% accuracy in generating realistic uncooperative behaviors, validated by human evaluations.

Tailoring Rumor Debunking to You: Diversifying Chinese Rumor-Debunking Passages with an LLM-Driven Simulated Feedback-Enhanced Framework (2026.eacl-industry)

Copied to clipboard

Xinle Pang, Danding Wang, Qiang Sheng, Yifan Sun, Beizhe Hu, Juan Cao

Synthetic Data Fine-Tuning for Effective Team Formation in Enterprises (2026.eacl-industry)

Challenge:	Existing methods for fact-checking lack coherence and context, whereas abstractive methods lack cohesion and context.
Approach:	They propose a framework that generates Chinese user-specific debunking passages . they propose to use a generative AI framework to generate context-sensitive responses .
Outcome:	The proposed framework generates Chinese user-specific debunking passages by iteratively refining outputs based on simulated user feedback.

Copied to clipboard

Guilherme Drummond Lima, Adriano Veloso

Assertion-Conditioned Compliance: A Provenance-Aware Vulnerability in Multi-Turn Tool-Calling Agents (2026.eacl-industry)

Challenge:	Existing algorithms for semantic search fine-tune text embeddings to retrieve and rank documents . word embedders allow search systems to measure semantic similarity between vectors .
Approach:	They evaluate the effectiveness of synthetic data fine-tuning for Semantic Search in a real-world Enterprise Team Formation problem scenario.
Outcome:	The proposed model outperforms existing models on a human-curated dataset.

Copied to clipboard

Daud Waqas, Aaryamaan Golthi, Erika Hayashida, Huanzhi Mao

Dialogue Systems & Conversational Agents

Challenge:	Multi-turn tool-calling models have emerged as a key feature in modern AI assistants, but their success in safety-critical industries remains constrained by concerns about transparency and model resilience.
Approach:	They propose a new evaluation paradigm for multi-turn function-calling LLMs that provides holistic metrics that evaluate a model’s behavior when confronted with misleading assertions.
Outcome:	The proposed evaluation paradigm evaluates a model's behavior when confronted with misleading assertions originating from two distinct vectors: (1) user-sourced assertions (USAs) and (2) function-sourced assertions (FSAs).

PROBES : Performance and Relevance Observation for BEtter Search (2026.eacl-industry)

Copied to clipboard

Sejal Jain, Cyrus Andre DSouza, Jitenkumar Babubhai Rana, Aniket Joshi, Promod Yenigalla

Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement Learning (2026.eacl-industry)

Challenge:	Qualitative search is essential for the success of online platforms, authors say . large-scale evaluation of search systems is essential to ensure high-quality user experiences .
Approach:	They propose a multi-task system powered by Large Language Models for end-to-end evaluation of semantic search systems.
Outcome:	The proposed system provides more precise and consistent relevance assessments across query categories.

Copied to clipboard

Minseok Kim, Jingxiang Chen, Seong-Gyun Leem, Yin Huang, Rashi Rungta, Zhicheng Ouyang, Haibin Wu, Surya Teja Appini, Ankur Bansal, Yang Bai, Yue Liu, Florian Metze, Ahmed A Aly, Anuj Kumar, Ariya Rastrow, Zhaojiang Lin

IndicJR: A Judge-Free Benchmark of Jailbreak Robustness in South Asian Languages (2026.eacl-industry)

Challenge:	Using paralinguistic cues is challenging for speech large language models, authors say . limited training data, annotation difficulty, and models exploiting lexical shortcuts are challenges . a recent study shows that modeling paralinguistic reasoning with multitask RL improves paralinguistics understanding .
Approach:	They propose multi-task reinforcement learning with chain-of-thought prompting that elicits explicit affective reasoning.
Outcome:	The proposed model improves paralinguistics understanding over baselines and strong proprietary models by 8-12% on Expresso, IEMOCAP, and RAVDESS.

Copied to clipboard

Priyaranjan Pattnayak, Sanchari Chowdhuri

Robustness in NLP

Challenge:	Indic Jailbreak Robustness (IJR) is a judge-free benchmark for adversarial safety across 12 languages.
Approach:	They propose a judge-free benchmark for adversarial safety across 12 languages . they find contracts inflate refusals but do not stop jailbreaks .
Outcome:	The proposed benchmarks cover 45,216 prompts in JSON and Free tracks.

Synthesizing question answering data from financial documents: An End-to-End Multi-Agent Approach (2026.eacl-industry)

Copied to clipboard

Chetan Harsha, Karmvir Singh Phogat, Sridhar Dasaratha, Shashishekar Ramakrishna

Question Answering

Challenge:	Large language models excel at financial reasoning but their deployment for enterprise use cases remains costly and often constrained by latency, privacy, and regulatory requirements.
Approach:	They propose a pipeline that extracts and selects relevant content from unstructured financial documents and generates QA pairs from the selected content for SLM fine-tuning.
Outcome:	The proposed model outperforms models trained on previous manual models and achieves competitive in-distribution performance.

Toward Automatic Delegation Extraction in Japanese Law (2026.eacl-industry)

Copied to clipboard

Tsuyoshi Fujita, Yuya Sawada, Yusuke Sakai, Taro Watanabe

DIALECTIC: A Multi-Agent System for Startup Evaluation (2026.eacl-industry)

Challenge:	a higher-level law authorizes a lower-level to implement detailed provisions, which is called delegation.
Approach:	They propose a two-stage pipeline system for automatic delegation annotation in Japanese law . they extract keywords that indicate delegation using a named entity recognition approach .
Outcome:	The proposed system shows sufficient performance to assist manual annotation in practice.

Copied to clipboard

Jae Yoon Bae, Simon Malberg, Joyce Ann Clarize Galang, Andre Retterath, Georg Groh

Long-Context Long-Form Question Answering for Legal Domain (2026.eacl-industry)

Challenge:	Venture capital (VC) investors face a large number of investment opportunities but only invest in few of them.
Approach:	They propose an LLM-based system that gathers factual knowledge about a startup and organizes it into a question tree.
Outcome:	The proposed system matches the precision of human VCs in predicting startup success.

Copied to clipboard

Anagha Kulkarni, Parin Rajesh Jhaveri, Prasha Shrestha, Yu Tong Han, Reza Amini, Behrouz Madahian

Natural Language Interfaces

Challenge:	Legal documents have complex document layouts involving multiple nested sections and lengthy footnotes that make question answering challenging.
Approach:	They propose a question answering system that parses document layouts while isolating sections and footnotes and linking them appropriately.
Outcome:	The proposed system can parse complex document layouts while isolating sections and footnotes and linking them appropriately.

ELO: Efficient Layer-Specific Optimization for Continual Pretraining of Multilingual LLMs (2026.eacl-industry)

Copied to clipboard

Hangyeol Yoo, ChangSu Choi, Minjun Kim, Seohyun Song, SeungWoo Song, Inho Won, Jongyoul Park, Cheoneum Park, KyungTae Lim

MIRAGE: Metadata-guided Image Retrieval and Answer Generation for E-commerce Troubleshooting (2026.eacl-industry)

Challenge:	Recent studies have focused on enhancing multilingual large language models (MLLMs) for specific languages.
Approach:	They propose an efficient layer-specific optimization method to enhance continual pretraining (CP) for specific languages in multilingual large language models (MLLMs).
Outcome:	The proposed method achieves a training speedup of up to 6.46 times compared to existing methods while improving target language performance by up to 5.2% on qualitative benchmarks.

Copied to clipboard

Rishav Sahay, Lavanya Sita Tekumalla, Anoop Saladi

CODMAS: A Dialectic Multi-Agent Collaborative Framework for Structured RTL Optimization (2026.eacl-industry)

Challenge:	Existing multimodal systems often associate text and images based on embedding similarity or simple co-location, but fail to ensure that the linked image accurately depicts the specific product or component mentioned in a troubleshooting instruction.
Approach:	They propose a metadata-first paradigm that treats structured metadata as a modality for multimodal grounding.
Outcome:	The proposed model uses a semantic schema to capture product attributes and visual aspects.

Copied to clipboard

Che-Ming Chang, Prashanth Vijayaraghavan, Ashutosh Jadhav, Charles Mackin, Hsinyu Tsai, Vandana Mukherjee, Ehsan Degan

D3: Dynamic Docid Decoding for Multi-Intent Generative Retrieval (2026.eacl-industry)

Challenge:	generating and optimizing Hardware Description Languages (HDLs) remains challenging.
Approach:	They propose a framework that combines dialectic reasoning with domain-aware code generation and deterministic evaluation to automate RTL optimization.
Outcome:	The proposed framework reduces critical path delay and power loss by 25% compared to baselines.

Copied to clipboard

Jaeyoung Kim, Dohyeon Lee, Soona Hong, Seung-won Hwang

DisGraph-RP: Graph-Augmented Temporal Modeling with Aspect-Based Contrastive Encoding of Discharge Summary for Readmission Prediction (2026.eacl-industry)

Challenge:	Existing GR systems rely on offline DocID assignment and constrained decoding . offline Doc ID assignment and decoding often prevents GR from capturing query-specific intent .
Approach:	They propose a mechanism that adaptively refines DocIDs through query-informed identifier expansion.
Outcome:	The proposed mechanism improves retrieval accuracy on unseen and multi-intent documents.

Copied to clipboard

Sudeshna Jana, Tirthankar Dasgupta, Manjira Sinha, Pabitra Mitra

Structured Data in NLP

Challenge:	Recent data indicate that nearly 15% of hospitalized patients in the U.S. are readmitted soon after discharge.
Approach:	They propose a graph-augmented temporal modeling framework that integrates structured discourse-aware text representation with cross-admission relational reasoning.
Outcome:	The proposed model improves on baseline models and prompting-based models on real-world datasets.

CareerPathKG: Knowledge Graph Integrated Framework for Career Intelligence (2026.eacl-industry)

Copied to clipboard

Ngoc-Quang Le, Duc Duong Hoang, Mai Vu Tran, Thi-Hai-Yen Vuong

Structured Data in NLP

Challenge:	a new framework for career orientation is needed to address the challenges of the labor market . a recent study found that traditional ML and large language models are brittle when faced with heterogeneous job descriptions .
Approach:	They propose a career-path knowledge graph-based recruitment framework to capture occupations, skill requirements and career transitions using standardized taxonomies enriched with job-posting data.
Outcome:	The proposed framework captures occupations, skill requirements, and career transitions using standardized taxonomies enriched with job-posting data.

A Hybrid Supervised-LLM Pipeline for Actionable Suggestion Mining in Unstructured Customer Reviews (2026.eacl-industry)

Copied to clipboard

Aakash Trivedi, Aniket Upadhyay, Pratik Narang, Dhruv Kumar, Praveen Kumar

ShopperBench: A Benchmark for Personalized Shopping with Persona-Guided Simulation (2026.eacl-industry)

Challenge:	Existing approaches to extract actionable suggestions from customer reviews are often mixed-intent, unstructured text.
Approach:	They propose a hybrid pipeline that uses a RoBERTa classifier and a precision–recall surrogate to extract actionable suggestions from customer reviews.
Outcome:	The proposed pipeline outperforms prompt-only, rule-based, and classifier-only baselines in extraction accuracy and cluster coherence.

Copied to clipboard

Yuan Ling, Chunqing Yuan, Shujing Dong, Yongjian Yang, Nataraj Mocherla, Ayush Goyal

Challenge:	Existing evaluation frameworks lack mechanisms to assess Personalized shopping agents' ability to adapt their strategies to heterogeneous user preferences and decisionmaking patterns.
Approach:	They propose a persona-guided benchmark that augments shopping trajectories with personas . they propose persona Fidelity, Persona-Query Alignment, and Path Consistency .
Outcome:	The proposed benchmark captures how shopper types navigate product search and selection . it measures persona Fidelity, Persona-Query Alignment, and Path Consistency .

ARQA: A Benchmark for Grounded Table–Text QA in Enterprise Annual Reports (2026.eacl-industry)

Copied to clipboard

Ruilong Wang, Simone Balloccu

Do Clinical Question Answering Systems Really Need Specialised Medical Fine Tuning? (2026.eacl-industry)

Challenge:	Existing QA benchmarks focus on retrieval or single-modality reasoning . annual reports are a company's definitive record of performance .
Approach:	They propose an annual report QA benchmark that compares QAs with lookups, arithmetics, and insights.
Outcome:	The proposed benchmarks show strong factual retrieval but persistent weaknesses in grounded arithmetic and causal reasoning.

Copied to clipboard

Sushant Kumar Ray, Gautam Siddharth Kashyap, Sahil Tripathi, Nipun Joshi, Vijay Govindarajan, Rafiq Ali, Jiechao Gao, Usman Naseem

Natural Language Interfaces

Challenge:	Clinical Question-Answering (CQA) industry systems rely on Large Language Models (LLMs).
Approach:	They propose a framework that applies alignment at inference time rather than through SFT to help CQA users achieve consistent reasoning.
Outcome:	MEDASSESS-X improves Accuracy, Factual Consistency and Safety by up to 50%.

SkiLLens: Recognising and Mapping Novel Skills from Millions of Job Ads Across Europe Using Language Models (2026.eacl-industry)

Copied to clipboard

Alessia De Santo, Lorenzo Malandri, Fabio Mercorio, Mario Mezzanzanica, Navid Nobani

SYMDIREC: A Neuro-Symbolic Divide-Retrieve-Conquer Framework for Enhanced RTL Synthesis and Summarization (2026.eacl-industry)

Challenge:	Online job ads (OJAs) provide a real-time view of changing demands but require first retrieving skill mentions from unstructured text and then solving the entity linking problem of connecting them to standardized skill taxonomies.
Approach:	They propose a multilingual human-in-the-loop pipeline that extracts candidate skills from national OJA corpora using country-specific word embeddings.
Outcome:	The proposed pipeline enables timely, multilingual monitoring of emerging skills, supporting agile policy-making and targeted training initiatives.

Copied to clipboard

Prashanth Vijayaraghavan, Apoorva Nitsure, Luyao Shi, Charles Mackin, Ashutosh Jadhav, David Beymer, Ehsan Degan, Vandana Mukherjee

Benchmarking and Mitigating the Impact of Noisy User Prompts in Medical VLMs via Cross-Modal Reflection (2026.eacl-industry)

Challenge:	Existing prompting and retrieval-augmented generation methods lack symbolic planning . rigid HDL syntax, limited supervision, and weak alignment with natural language hinder RTL synthesis and summarization.
Approach:	SYMDIREC decomposes RTL tasks into symbolic subgoals and assembles verified outputs . a neuro-symbolic framework supports both Verilog and VHDL without LLM fine-tuning .
Outcome:	SYMDIREC achieves higher Pass@1 rates for synthesis and 15–20% ROUGE-L improvements for summarization over prompting and RAG . synthesis, summarizing require preserving strict HDL syntax, modular structure, and precise functional semantics, authors show .

Copied to clipboard

Zhiyu Xue, Reza Abbasi-Asl, Ramtin Pedarsani

Lightweight Domain-Specific Language Model for Real-Time Structuring of Medical Prescriptions (2026.eacl-industry)

Challenge:	Existing medical vision-language models follow user-provided prompts blindly, a new study finds . current models are noisy, causing problems with reliability in real-world interactions .
Approach:	They propose a method to evaluate the influence of clinical prompts on medical vision-language models . they use cross-modal reflection chain-of-thought to train the model to produce reasoning paths .
Outcome:	The proposed method significantly improves the robustness against noisy prompts . existing Med-VLMs follow user-provided prompts blindly, the authors show .

Copied to clipboard

Jonathan Pattin Cottet, Véronique Eglin, Alex Aussem

Balanced Accuracy: The Right Metric for Evaluating LLM Judges - Explained through Youden’s J statistic (2026.eacl-industry)

Challenge:	Existing language models ignore layout information, rely on expensive image-based architectures, or cannot operate under privacy and hardware constraints.
Approach:	They propose a lightweight, privacy-preserving transformer specifically designed for Entity Extraction (EE) and Entity Linking (EL) in french medical prescriptions.
Outcome:	The proposed model matches or surpasses larger document-understanding models on strict extraction metrics while maintaining essential spatial cues.

Copied to clipboard

Stephane Collot, Colin Fraser, Justin Zhao, William F. Shen, Timon Willi, Ilias Leontiadis

Explainability & Interpretability in NLP

Challenge:	False refusals and task pass rates are key to reliable evaluation of large language models.
Approach:	They propose a principled best practice for evaluating judges based on a golden set of judge-quality metrics.
Outcome:	The proposed method improves the quality of judge-quality metrics on a golden set.

PharmaQA.IT: an Italian dataset for Q&A in the pharmaceutical domain (2026.eacl-industry)

Copied to clipboard

Kamyar Zeinalipour, Andrea Zugarini, Asya Zanollo, Leonardo Rigutini