Proceedings of the 31st International Conference on Computational Linguistics: Industry Track

Improving Tool Retrieval by Leveraging Large Language Models for Query Generation (2025.coling-industry)

Challenge:	Relevance module is responsible for selecting relevant products based on user queries.
Approach:	They propose Query-aware Language Image Fusion Embedding to address these challenges . they propose query-based multimodal fusion to integrate image and title based on product types .
Outcome:	The proposed model outperforms baselines in e-commerce searches . it incorporates image and title based on product types and improves performance .

Copied to clipboard

Mohammad Kachuee, Sarthak Ahuja, Vaibhav Kumar, Puyang Xu, Xiaohu Liu

Know Your RAG: Dataset Taxonomy and Generation Strategies for Evaluating RAG Systems (2025.coling-industry)

Challenge:	Large Language Models (LLMs) have shown great promise in common sense language understanding, conversational fluency, and reasoning.
Approach:	They propose to use Large Language Models to generate a retrieval query and embed it into the prompt to find relevant tools via a nearest-neighbor search.
Outcome:	The proposed method improves retrieval for in-domain (seen tools) and out-of-domain settings.

Copied to clipboard

Rafael Teixeira de Lima, Shubham Gupta, Cesar Berrospi Ramis, Lokesh Mishra, Michele Dolfi, Peter Staar, Panagiotis Vagenas

RED-CT: A Systems Design Methodology for Using LLM-labeled Data to Train and Deploy Edge Linguistic Classifiers (2025.coling-industry)

Challenge:	Retrieval Augmented Generation (RAG) systems are widespread in the industry.
Approach:	They propose to use Q&A datasets to assess retrieval performance and label-targeted data generation to refine RAG datasets.
Outcome:	The proposed system can generate Q&A datasets with fine-tuned small LLMs.

Copied to clipboard

David Farr, Nico Manzonelli, Iain Cruickshank, Jevin West

Beyond Visual Understanding Introducing PARROT-360V for Vision Language Model Benchmarking (2025.coling-industry)

Challenge:	Large language models have improved our ability to rapidly analyze and classify unstructured natural language data.
Approach:	They propose a system approach to employing LLMs as imperfect data annotators for downstream supervised learning tasks.
Outcome:	The proposed method outperforms LLM-generated labels in six of eight tests and base classifiers in all tests.

Copied to clipboard

Harsha Vardhan Khurdula, Basem Rizk, Indus Khaitan

PDC & DM-SFT: A Road for LLM SQL Bug-Fix Enhancing (2025.coling-industry)

Challenge:	Current benchmarks for evaluating Vision Language Models (VLMs) often fail to thoroughly assess these models’ abilities to understand complex visual and textual content.
Approach:	They propose a benchmark that features 2487 visual puzzles designed to test VLMs on complex visual reasoning tasks.
Outcome:	The PARROT-360V Benchmark features 2487 visual puzzles designed to test VLMs on complex visual reasoning tasks.

Copied to clipboard

Yiwen Duan, Yonghong Yu, Xiaoming Zhao, Yichang Wu, Wenbo Liu

Multilingual Continual Learning using Attention Distillation (2025.coling-industry)

Challenge:	Existing code large language models focus on generating correct code, but struggle with bug repair.
Approach:	They propose a set of methods to enhance LLM’s SQL bug-fixing abilities by combining a data set construction and a supervised bug-fixed learning approach.
Outcome:	The proposed methods exceed current best performing model which size is much larger.

Copied to clipboard

Sanjay Agrawal, Deep Nayak, Vivek Varadarajan Sembium

FS-DAG: Few Shot Domain Adapting Graph Networks for Visually Rich Document Understanding (2025.coling-industry)

Challenge:	Existing models for Query-product relevance classification are not accurate across multiple languages.
Approach:	They propose a multilingual continual learning framework that adds adapters for each new language and incorporates a fusion layer above language-specific adapters.
Outcome:	The proposed approach reduces trainable parameters by 80% while outperforming SOTA CL methods on proprietary and external datasets.

Copied to clipboard

Amit Agarwal, Srikant Panda, Kulbhushan Pachauri

OKG: On-the-Fly Keyword Generation in Sponsored Search Advertising (2025.coling-industry)

Challenge:	Recent advances in vision-language models have significantly enhanced performance across various natural language processing and computer vision tasks.
Approach:	They propose a few shot domain adapting graph (FS-DAG) that leverages domain-specific and language/vision specific backbones within a modular framework to adapt to diverse document types with minimal data.
Outcome:	The proposed model is highly performant with less than 90M parameters, making it well-suited for complex real-world applications for information extraction tasks where computational resources are limited.

Copied to clipboard

Zhao Wang, Briti Gangopadhyay, Mengjie Zhao, Shingo Takamatsu

Best Practices for Distilling Large Language Models into BERT for Web Search Ranking (2025.coling-industry)

Challenge:	Conventionally, keyword decision-making in sponsored search advertising relies on deep generation-based methods.
Approach:	They propose an LLM agent-based method that dynamically monitors KPI changes and adapts keyword generation in real-time.
Outcome:	The proposed method shows significant improvements across various metrics and emphasizes the importance of each component.

Copied to clipboard

Dezhi Ye, Junwei Hu, Jiabin Fan, Bowen Tian, Jie Liu, Haijin Liang, Jin Ma

Rationale-Guided Distillation for E-Commerce Relevance Classification: Bridging Large Language Models and Lightweight Cross-Encoders (2025.coling-industry)

Challenge:	Recent studies have highlighted the potential of Large Language Models (LLMs) as zero-shot relevance rankers.
Approach:	They propose to use a ranking loss to transfer ranking knowledge from LLMs to smaller models like BERT.
Outcome:	The proposed model has been successfully integrated into a commercial web search engine as of February 2024.

Copied to clipboard

Sanjay Agrawal, Faizan Ahemad, Vivek Varadarajan Sembium

Automated Clinical Data Extraction with Knowledge Conditioned LLMs (2025.coling-industry)

Challenge:	Large-scale e-commerce search systems typically follow a multi-step process to retrieve relevant products for a given query.
Approach:	They propose a distillation approach that uses "rationales" generated by Large Language Models to guide smaller cross-encoder models.
Outcome:	The proposed model achieves ROC-AUC improvements of 1.4% on 9 multilingual e-commerce datasets, 2.4% on 3 ESCI datasets and 6% on GLUE datasets while being 50 times faster per sample.

Copied to clipboard

Diya Li, Asim Kadav, Aijing Gao, Rui Li, Richard Bourgon

Can Large Language Models Serve as Effective Classifiers for Hierarchical Multi-Label Classification of Scientific Documents at Industrial Scale? (2025.coling-industry)

Challenge:	Large language models (LLMs) can be effective at interpreting unstructured text in reports, but they often hallucinate due to a lack of domain-specific knowledge.
Approach:	They propose a framework that aligns generated internal knowledge with external knowledge through in-context learning (ICL) they use a retriever to identify relevant units of internal or external knowledge and a grader to evaluate the truthfulness and usefulness of the retrieved internal-knowledge rules to align and update the knowledge bases.
Outcome:	Experiments with expert-curated test datasets show that the proposed framework can increase the F1 score for key fields by 12.9% over existing methods.

Copied to clipboard

Seyed Amin Tabatabaei, Sarah Fancher, Michael Parsons, Arian Askari

EDAR: A pipeline for Emotion and Dialogue Act Recognition (2025.coling-industry)

Challenge:	Large Language Models (LLMs) have demonstrated great potential in complex tasks such as multi-label classification, but the vast number of labels can exceed LLMs’ input limits.
Approach:	They propose a method that integrates large language models with dense retrieval techniques to overcome these challenges.
Outcome:	The proposed methods avoid frequent retraining by leveraging zero-shot and few-shot learning for real-time label assignment.

Copied to clipboard

Elie Dina, Rania Ayachi Kibech, Miguel Couceiro

No Size Fits All: The Perils and Pitfalls of Leveraging LLMs Vary with Company Size (2025.coling-industry)

Challenge:	EDAR is a pipeline for Emotion and Dialogue Act Recognition for debt collection . traditional methods overlook the emotional complexities of debtors, leading to increased stress for both parties.
Approach:	They propose to integrate EDAR into decision-making systems to improve debt collection outcomes.
Outcome:	The proposed pipeline improves debt collection outcomes and debtor satisfaction by identifying emotional states and enabling empathetic responses.

Copied to clipboard

Ashok Urlana, Charaka Vinayak Kumar, Bala Mallikarjunarao Garlapati, Ajeet Kumar Singh, Rahul Mishra

Predicting Fine-tuned Performance on Larger Datasets Before Creating Them (2025.coling-industry)

Challenge:	Large language models are playing a pivotal role in deploying strategic use cases across organizations . lack of studies examining potential challenges and risks associated with LLMs .
Approach:	They propose a case study and a practical guide for industries to utilize LLMs more efficiently.
Outcome:	The proposed study examines the literature on large language models with industry practitioners and examines industrial publications to address these questions.

Copied to clipboard

Toshiki Kuramoto, Jun Suzuki

A Recipe For Building a Compliant Real Estate Chatbot (2025.coling-industry)

Challenge:	a method to estimate the performance of pretrained models fine-tuned with a larger dataset is proposed . a recent study found that fine-timing PMs with the small amount of data does not always result in ideal performance.
Approach:	They propose a method to estimate the performance of pretrained models fine-tuned with a larger dataset from the result with fewer epochs.
Outcome:	The proposed method can help resource-limited companies develop machine-learning models . it shows that when a model is fine-tuned with a larger dataset, its classification performance increases .

Copied to clipboard

Navid Madani, Anusha Bagalkotkar, Supriya Anand, Gabriel Arnson, Rohini K. Srihari, Kenneth Joseph

Geo-Spatially Informed Models for Geocoding Unstructured Addresses (2025.coling-industry)

Challenge:	In recent years, there has been significant effort to align large language models with human preferences.
Approach:	They propose to use a general instruction-following dataset to generate a chatbot that can be used without perpetuating discriminatory practices like steering and redlining.
Outcome:	The proposed model can match closed-source models like GPT-4o while being safer and more compliant.

Copied to clipboard

Uddeshya Singh, Devanapalli Ravi Shankar, Gowtham Bellala, Vikas Goel

Challenge:	e-commerce companies need to geocode their customers' addresses to reduce shipping costs and improve customer experience.
Approach:	They propose a method to geocode customer addresses in developing countries . they propose to incorporate geo-spatial relationships using an LLM backbone .
Outcome:	The proposed method outperforms the current state-of-the-art system by 20% in drift accuracy within 100 meters and the state- of-the art commercial system by 54%.

Resource-Efficient Anonymization of Textual Data via Knowledge Distillation from Large Language Models (2025.coling-industry)

Copied to clipboard

Tobias Deußer, Max Hahnbück, Tobias Uelwer, Cong Zhao, Christian Bauckhage, Rafet Sifa

Fine-Tuning Medium-Scale LLMs for Joint Intent Classification and Slot Filling: A Data-Efficient and Cost-Effective Solution for SMEs (2025.coling-industry)

Challenge:	Existing approaches to anonymize textual data from large language models pose privacy risks due to their API-based access.
Approach:	They propose a method to distill large language models into smaller encoder-only models via named entity recognition coupled with regular expressions to create a lightweight model capable of effective anonymization.
Outcome:	The proposed approach reduces computational overhead while maintaining semantic integrity of data.

Copied to clipboard

Maia Aguirre, Ariane Méndez, Arantza del Pozo, Maria Ines Torres, Manuel Torralbo

Enhancing Large Language Models for Scientific Multimodal Summarization with Multimodal Output (2025.coling-industry)

Challenge:	Current techniques for user comprehension in DS depend heavily on labeled data and the data annotation process for NLU is labor-intensive and requires expert annotators.
Approach:	They propose to fine-tune a model for joint Intent Classification and Slot Filling with only 10% of the data.
Outcome:	The proposed model outperforms existing models in monolingual and cross-lingual scenarios with only 10% of the data.

Copied to clipboard

Zusheng Tan, Xinyi Zhong, Jing-Yu Ji, Wei Jiang, Billy Chiu

“Stupid robot, I want to speak to a human!” User Frustration Detection in Task-Oriented Dialog Systems (2025.coling-industry)

Challenge:	Scientific publications are becoming more multimedia, containing both text and visual content.
Approach:	They propose a framework for Scientific Multimodal Summarization with Multimodal Output . it leverages the power of large language models and extends its capability to cross-modal understanding .
Outcome:	The proposed framework outperforms uni- and multi-modality methods on two new datasets . it leverages the power of large language models and extends its capability to cross-modal understanding .

Copied to clipboard

Mireia Hernandez Caralt, Ivan Sekulic, Filip Carevic, Nghia Khau, Diana Nicoleta Popa, Bruna Guedes, Victor Guimaraes, Zeyu Yang, Andre Manso, Meghana Reddy, Paolo Rosso, Roland Mathis

Sentiment Analysis

Challenge:	Detecting user frustration in task-oriented dialog systems is imperative for maintaining overall user satisfaction, engagement and retention.
Approach:	They compare out-of-the-box methods for user frustration detection with open-source methods . they find an LLM-based approach is promising, as it captures both emotion and dialog breakdowns .
Outcome:	The proposed method outperforms open-source methods in detecting user frustration in a TOD system.

LLM Evaluate: An Industry-Focused Evaluation Tool for Large Language Models (2025.coling-industry)

Copied to clipboard

Harsh Saini, Md Tahmid Rahman Laskar, Cheng Chen, Elham Mohammadi, David Rossouw

Enhancing Future Link Prediction in Quantum Computing Semantic Networks through LLM-Initiated Node Features (2025.coling-industry)

Challenge:	Large Language Models (LLMs) have demonstrated impressive capability to solve a wide range of tasks in recent years.
Approach:	They propose to build an on-premise system for LLM evaluation to address the challenges in the evaluation of LLMs in real-world industrial settings.
Outcome:	The proposed evaluation system protects customer privacy and protects data integrity in real-world industrial environments.

Copied to clipboard

Gilchan Park, Paul Baity, Byung-Jun Yoon, Adolfy Hoisie

Page Stream Segmentation with LLMs: Challenges and Applications in Insurance Document Automation (2025.coling-industry)

Challenge:	Quantum computing is rapidly evolving in both physics and computer science due to its potential to solve complex quantum physics problems and accelerate computational processes.
Approach:	They propose to initialize node features using LLMs to enhance node representations for link prediction tasks in graph neural networks.
Outcome:	The proposed method compared to traditional node embedding techniques on a quantum computing semantic network and demonstrated efficacy compared with other methods.

Copied to clipboard

Hunter Heidenreich, Ratish Dalvi, Nikhil Verma, Yosheb Getachew

Challenge:	Existing models for page Stream Segmentation (PSS) are inadequate for high-stakes applications.
Approach:	They propose to use large language models for page Stream Segmentation to apply parameter-efficient fine-tuning to real-world insurance data.
Outcome:	The proposed model outperforms baseline models in page- and stream-level segmentation accuracy.

Graph-Augmented Open-Domain Multi-Document Summarization (2025.coling-industry)

Copied to clipboard

Xiaoping Shen, Yekun Chai

Information Extraction & Text Mining

Challenge:	Existing methods for summarizing documents neglect the relationships between documents . existing methods treat retrieval and summarization as separate tasks .
Approach:	They propose a framework that captures global document relationships through graph-based clustering . this cluster-level thematic information is then used to guide large language models .
Outcome:	The proposed framework significantly improves retrieval accuracy and produces better summaries than existing methods.

Improve Speech Translation Through Text Rewrite (2025.coling-industry)

Copied to clipboard

Jing Wu, Shushu Wang, Kai Fan, Wei Luo, Minpeng Liao, Zhongqiang Huang

Text Generation

Challenge:	Recent advances in speech translation (ST) research have focused on the unique characteristics of spontaneous speech, including accents and presentation quality.
Approach:	They propose to transform transcribed speech into a cleaner style more in line with the expectations of translation models built from written text.
Outcome:	Experiments on public and in-house translation models show that the proposed model can be effectively distilled into a standalone translation model.

CarMem: Enhancing Long-Term Memory in LLM Voice Assistants through Category-Bounding (2025.coling-industry)

Copied to clipboard

Johannes Kirmayr, Lukas Stappen, Phillip Schneider, Florian Matthes, Elisabeth Andre

Speech & Audio in NLP

Challenge:	Large Language Models (LLMs) are stateless and present all relevant memories during each interaction, resulting in repetitive user requests and disengagement.
Approach:	They propose a long-term memory system for voice assistants structured around predefined categories that leverages Large Language Models to extract, store, and retrieve preferences within these categories.
Outcome:	The proposed system achieves an F1-score of .78 to .95 in preference extraction, depending on category granularity, and is suitable for industrial applications.

XTR meets ColBERTv2: Adding ColBERTv2 Optimizations to XTR (2025.coling-industry)

Copied to clipboard

Riyaz Ahmad Bhat, Jaydeep Sen

sDPO: Don’t Use Your Data All at Once (2025.coling-industry)

Challenge:	XTR eliminates the need for multi-stage retrieval, but doesn't incorporate efficiency optimizations from ColBERTv2 which improve indexing and retrieval speed.
Approach:	They propose a multi-vector retrieval method that simplifies retrieval into a single stage through a modified learning objective.
Outcome:	The proposed method eliminates the need for multistage retrieval but doesn't incorporate efficiency optimizations from ColBERTv2 which improve indexing and retrieval speed.

Copied to clipboard

Dahyun Kim, Yungi Kim, Wonho Song, Hyeonwoo Kim, Yunsu Kim, Sanghoon Kim, Chanjun Park

Contextual ASR Error Handling with LLMs Augmentation for Goal-Oriented Conversational AI (2025.coling-industry)

Challenge:	Large language models (LLMs) are increasingly requiring precision and accuracy in alignment tuning.
Approach:	They propose a stepwise DPO technique that partitions available preference datasets incrementally rather than utilizing entire dataset simultaneously.
Outcome:	The proposed technique improves the accuracy of reference models and the overall performance of the final model.

Copied to clipboard

Yuya Asano, Sabit Hassan, Paras Sharma, Anthony B. Sicilia, Katherine Atwell, Diane Litman, Malihe Alikhani

Speech Recognition

Challenge:	Existing ASR correction methods rely on prior user data or named entities . Existing methods based on prior data are not available for goal-oriented dialogues .
Approach:	They propose a method that integrates contextual information from the dialogue states of a goal-oriented conversational AI and its tasks into a large language model.
Outcome:	The proposed method improves recall and F1 of correction by 34% and 16% while maintaining precision and false positive rate.

Federated Retrieval Augmented Generation for Multi-Product Question Answering (2025.coling-industry)

Copied to clipboard

Parshin Shojaee, Sai Sree Harsha, Dan Luo, Akash Maharaj, Tong Yu, Yunyao Li

Luna: A Lightweight Evaluation Model to Catch Language Model Hallucinations with High Accuracy and Low Cost (2025.coling-industry)

Challenge:	Existing multi-domain RAG-QA approaches query all domains indiscriminately or rely on rigid resource selection.
Approach:	They propose a multi-product knowledge-augmented QA framework with probabilistic federated search across domains and relevant knowledge.
Outcome:	The proposed framework improves multi-product knowledge-augmented QA performance on Adobe products.

Copied to clipboard

Masha Belyi, Robert Friel, Shuai Shao, Atindriyo Sanyal

Seeing Beyond: Enhancing Visual Question Answering with Multi-Modal Retrieval (2025.coling-industry)

Challenge:	Retrieval-augmented generation (RAG) systems are crucial for enhancing the capabilities of large language models (LLMs) in industry applications.
Approach:	They propose a DeBERTA-large encoder for hallucination detection in RAG settings that is fine-tuned for halluination detection.
Outcome:	The proposed model outperforms GPT-3.5 and commercial evaluation frameworks on the hallucination detection task, with 97% and 91% reduction in cost and latency, respectively.

Copied to clipboard

Boqi Chen, Anuj Khare, Gaurav Kumar, Arjun Akula, Pradyumna Narayana

AutoProteinEngine: A Large Language Model Driven Agent Framework for Multimodal AutoML in Protein Engineering (2025.coling-industry)

Challenge:	Multi-modal Large language models still suffer from model hallucination and lack of specific knowledge when answering challenging questions.
Approach:	They propose to use a multi-modal retrieval augmented generation method to integrate knowledge from all modalities into a model to enable alignment between query and knowledge.
Outcome:	The proposed method achieves significant performance improvement on the VQA dataset.

Copied to clipboard

Yungeng Liu, Zan Chen, Yuguang Wang, Yiqing Shen

Building a Family of Data Augmentation Models for Low-cost LLM Fine-tuning on the Cloud (2025.coling-industry)

Challenge:	Deep learning models are often inefficient and resource-intensive for biologists without specialized computational expertise.
Approach:	They propose an agent framework that leverages large language models for multimodal automated machine learning (AutoML) in protein engineering.
Outcome:	The proposed framework demonstrates significant improvements in performance over previous approaches in two real-world protein engineering tasks.

Copied to clipboard

Chengyu Wang, Yuanhao Yue, Jun Huang, Peng Wang

Where do LLMs Encode the Knowledge to Assess the Ambiguity? (2025.coling-industry)

Challenge:	Existing models for learning large language models are expensive and difficult to build and fine-tune.
Approach:	They propose a family of data augmentation models to improve model fine-tuning efficiency . they leverage powerful LLMs to expand, refine and re-write instructions and responses .
Outcome:	The proposed models improve the efficiency of model fine-tuning by leveraging small datasets and quality assessment techniques.

Copied to clipboard

Hancheol Park, Geonmin Kim

Text Classification

Challenge:	False sizing of large language models can generate unreliable responses .
Approach:	They propose a method to train large language models without ambiguity labels .
Outcome:	The proposed method detects ambiguous input prompts better than representations from the final layer.

On the effective transfer of knowledge from English to Hindi Wikipedia (2025.coling-industry)

Copied to clipboard

Paramita Das, Amartya Roy, Ritabrata Chakraborty, Animesh Mukherjee

Challenge:	Existing studies show that in low-resource languages, Wikipedia articles on the same topic differ significantly due to cultural relevance and the varied expertise of contributors.
Approach:	They propose a lightweight framework to enhance knowledge equity between English and Hindi Wikipedia sections by extracting relevant information from external resources readily available.
Outcome:	The proposed framework enhances Hindi Wikipedia articles by 65% and 62% based on automatic and human judgment-based evaluations.

BackMATH: Towards Backward Reasoning for Solving Math Problems Step by Step (2025.coling-industry)

Copied to clipboard

Shaowei Zhang, Deyi Xiong

Reasoning

Challenge:	Large language models (LLMs) have impressive results in reasoning, but when faced with more complex mathematical problems, performance drops significantly.
Approach:	They propose a backward reasoning dataset that includes 14K backward thinking problems and 100K reasoning steps.
Outcome:	The proposed model achieves an accuracy of 68.1% on the GSM8K dataset and 21.9% on the MATH dataset, exceeding the SOTA by 1.6% and 2.1% respectively.

Deploying Multi-task Online Server with Large Language Model (2025.coling-industry)

Copied to clipboard

Yincen Qu, Hengyue Liu, Kun Wang, Xiangying Dai, Xiaoou Lu, Hui Zhou, Chao Ma

LLM-Friendly Knowledge Representation for Customer Support (2025.coling-industry)

Challenge:	In the industry, numerous natural language processing tasks are deployed online . traditional approaches tackle each task separately by its own network and pipeline .
Approach:	They propose a three-stage multi-task learning framework for large language models . it involves task filtering, fine-tuning on high-resource tasks, and finally fine- tuning on all tasks .
Outcome:	The proposed framework reduces up to 90% of overhead while reducing latency and resource usage.

Copied to clipboard

Hanchen Su, Wei Luo, Yashar Mehdad, Wei Han, Elaine Liu, Wayne Zhang, Mia Zhao, Joy Zhang

Leveraging Multilingual Models for Robust Grammatical Error Correction Across Low-Resource Languages (2025.coling-industry)

Challenge:	a new approach to customer support is proposed to integrate large language models with a framework designed to navigate the complexities of Airbnb customer support operations.
Approach:	They propose a method for integrating Large Language Models with a framework designed to navigate the complexities of Airbnb customer support operations.
Outcome:	The proposed approach is cost-effective and improves customer support performance . it also allows human agents to focus on more complex issues, the authors show .

Copied to clipboard

Divesh Ramesh Kubal, Apurva Shrikant Nagvenkar

A Simple yet Efficient Prompt Compression Method for Text Classification Data Annotation Using LLM (2025.coling-industry)

Challenge:	Grammatical error correction (GEC) is a critical task in natural language processing . most approaches create language-specific models, limiting their multilingual applicability.
Approach:	They propose a multilingual transformer model to build a unified GEC system with a focus on low-resource languages.
Outcome:	The proposed system has been implemented in the Spanish language and shows acceptance rate of 88.2% . the proposed system is highly efficient and scalable, with a focus on low-resource languages.

Copied to clipboard

Yiran Xie, Debin Xiao, Ping Wang, Shuming Liu

AMAN: Agent for Mentoring and Assisting Newbies in MMORPG (2025.coling-industry)

Challenge:	Existing methods to improve the accuracy of large language models (LLMs) are often impractical due to high costs and time consumption.
Approach:	They propose a method that uses keyword extraction to reduce prompt tokens in text annotation tasks.
Outcome:	The proposed method reduces prompt tokens while maintaining high accuracy.

Copied to clipboard

Jeehyun Lee, Seung-Moo Yang, Won Ik Cho

KARRIEREWEGE: A large scale Career Path Prediction Dataset (2025.coling-industry)

Challenge:	AMAN is a chatbot designed to help novice gamers learn the gameplay mechanics of online games.
Approach:	They propose a model that functions as a human-like chat buddy that interacts with users in a friendly manner while providing substantive informational depth.
Outcome:	The proposed model integrates continual pre-training with a sequence of online resources and instruction tuning on curated dialogues.

Copied to clipboard

Elena Senger, Yuri Campbell, Rob van der Goot, Barbara Plank

Challenge:	Career path prediction is a growing field, but available data and tools are limited.
Approach:	They propose Karrierewege, a publicly available career path prediction dataset . it combines career path data with ESCO taxonomy to provide valuable resource .
Outcome:	The career path prediction dataset Karrierewege surpasses existing datasets . the dataset is based on the ESCO taxonomy, which provides a common language for occupations and skills .

Transforming Code Understanding: Clustering-Based Retrieval for Improved Summarization in Domain-Specific Languages (2025.coling-industry)

Copied to clipboard

Baban Gain, Dibyanayan Bandyopadhyay, Samrat Mukherjee, Aryan Sahoo, Saswati Dana, Palanivel Kodeswaran, Sayandeep Sen, Asif Ekbal, Dinesh Garg

Information Extraction & Text Mining

Challenge:	Existing natural language summaries of domain-specific languages are limited due to their recency and complexity.
Approach:	They propose a clustering-based technique to retrieve in-context examples that are semantically closer to the test example and propose eBPF prompt generation technique that yields superior-quality code summary generation.
Outcome:	The proposed method improves the eBPF code summarization accuracy by 12.9 BLEU points over other prompting techniques.

Is my Meeting Summary Good? Estimating Quality with a Multi-LLM Evaluator (2025.coling-industry)

Copied to clipboard

Frederic Thomas Kirstein, Terry Lima Ruas, Bela Gipp

Challenge:	Established metrics such as ROUGE and BERTScore have a relatively low correlation with human judgments and fail to capture nuanced errors.
Approach:	They propose a framework that uses a three-step assessment of individual error types, multi-agent discussion for decision refinement, and feedback-based self-training to refine error definition understanding and alignment with human judgment.
Outcome:	The proposed framework achieves high correlation with human judgment and a consistent rating and adaptability to custom error guidelines.

Learning to Rewrite Negation Queries in Product Search (2025.coling-industry)

Copied to clipboard

Mengtian Guo, Mutasem Al-Darabsah, Choon Hui Teo, Jonathan May, Tarun Agarwal, Rahul Bhagat

Text Generation

Challenge:	Negations in product search are often used to articulate unwanted product features or components.
Approach:	They propose a query rewriting approach to enhance product search performance . they use large language models to extract query reawrites from product text . their results pave the way for further research on enhancing search performance of queries with negations .
Outcome:	The proposed approach improves search performance by 3.17% for queries with negations.

LAW: Legal Agentic Workflows for Custody and Fund Services Contracts (2025.coling-industry)

Copied to clipboard

William Watson, Nicole Cho, Nishan Srishankar, Zhen Zeng, Lucas Cecchi, Daniel Scott, Suchetha Siddagangappa, Rachneet Kaur, Tucker Balch, Manuela Veloso

UR2N: Unified Retriever and ReraNker (2025.coling-industry)

Challenge:	Currently, there are limited resources available to build a legal domain-specific Large Language Model (LLM) however, legal contracts are highly varied not only in terms of semantics but also accessibility.
Approach:	They propose a Large Language Model (LLM) that integrates multiple specialized agents and text agents to respond to user queries.
Outcome:	The proposed model outperforms the baseline model in complex tasks such as calculating a contract’s termination date by 92.9% points.

Copied to clipboard

Riyaz Ahmad Bhat, Jaydeep Sen, Rudra Murthy, Vignesh P

An Automatic Method to Estimate Correctness of RAG (2025.coling-industry)

Challenge:	XTR-style retrieval on top of trained Mono-T5 reranker is suboptimal for two-stage retrieval, arguing that it is sub-optimal.
Approach:	They propose a unified encoder-decoder architecture with a novel training regimen which enables the encoder representation to be used for retrieval and the decoder for re-ranking within a single unified model.
Outcome:	The proposed architecture outperforms ColBERT, XTR, and even serves as a superior reranker compared to the Mono-T5 re-ranker.

Copied to clipboard

Chi Zhang, Vivek V. Datla, Aditya Shrivastava, Alfy Samuel, Zhiqi Huang, Anoop Kumar, Daben Liu

Challenge:	Existing methods to assess the correctness of RAG models fail to capture the model’s internal state during answer generation.
Approach:	They propose a method to predict the correctness of RAG models by modeling the model’s uncertainty on quantified perturbations of input.
Outcome:	Extensive experiments across multiple large language models show that the proposed approach quantifies RAG robustness by aligning predictions with ground truth with a MSE 0.002 while offering flexibility for diverse qualitative metrics.

DaCoM: Strategies to Construct Domain-specific Low-resource Language Machine Translation Dataset (2025.coling-industry)

Copied to clipboard

Junghoon Kang, Keunjoo Tak, Joungsu Choi, Myunghyun Kim, Junyoung Jang, Youjin Kang

Text Generation

Challenge:	Existing models for low-resource languages struggle with domain-specific terms and lack of expert annotators for dataset creation.
Approach:	They propose a method for collecting low-resource language pairs from industrial domains using a large language model and neural machine translation framework.
Outcome:	The proposed model performs poorly on DaCoM-created datasets with up to 53.7 BLEURT points difference depending on domain inclusion.

ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild (2025.coling-industry)

Copied to clipboard

Ahmed Masry, Megh Thakkar, Aayush Bajaj, Aaryaman Kartha, Enamul Hoque, Shafiq Joty

LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks (2025.coling-industry)

Challenge:	Existing methods for chart understanding and reasoning are weakly aligned and rely on underlying data tables.
Approach:	They propose a chart-based understanding and reasoning model that is trained on instruction-tuning data generated directly from chart images.
Outcome:	The proposed model achieves state-of-the-art results across 5 benchmarks spanning chart summarization, question answering, and fact-checking.

Copied to clipboard

Akshara Prabhakar, Yuanzhi Li, Karthik Narasimhan, Sham Kakade, Eran Malach, Samy Jelassi

Numerical Reasoning

Challenge:	Low-Rank Adaptation (LoRA) is a popular technique for parameter-efficient fine-tuning of Large Language Models.
Approach:	They propose to combine LoRA modules to achieve skill composition . they propose to use concatenation of LoRAs to optimize weights for different LoRA training .
Outcome:	The proposed model outperforms existing models and data- merging techniques on math-word problems and domain-specialized corpora.

Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code (2025.coling-industry)

Copied to clipboard

Taishi Nakamura, Mayank Mishra, Simone Tedeschi, Yekun Chai, Jason T. Stillerman, Felix Friedrich, Prateek Yadav, Tanmay Laud, Vu Minh Chien, Terry Yue Zhuo, Diganta Misra, Ben Bogin, Xuan-Son Vu, Marzena Karpinska, Arnav Varma Dantuluri, Wojciech Kusa, Tommaso Furlanello, Rio Yokota, Niklas Muennighoff, Suhas Pai, Tosin Adewumi, Veronika Laippala, Xiaozhe Yao, Adalberto Barbosa Junior, Aleksandr Drozd, Jordan Clive, Kshitij Gupta, Liangyu Chen, Qi Sun, Ken Tsui, Nour Moustafa-Fahmy, Nicolo Monti, Tai Dang, Ziyang Luo, Tien-Tung Bui, Roberto Navigli, Virendra Mehta, Matthew Blumberg, Victor May, Hiep Nguyen, Sampo Pyysalo

UCTG: A Unified Controllable Text Generation Framework for Query Auto-Completion (2025.coling-industry)

Challenge:	Pretrained language models are integral part of AI applications, but their high computational cost limits accessibility.
Approach:	They evaluate Aurora-M, a 15B parameter multilingual open-source model trained on English, Finnish, Hindi, Japanese, Vietnamese, and code.
Outcome:	The proposed model outperforms existing models on English, Finnish, Hindi, Japanese, Vietnamese, and code.

Copied to clipboard

Zhipeng Li, Shuang Zheng, Jiaping Xiao, Xianneng Li, Lei Wang

Low-Resource NLP

Challenge:	Existing approaches to control text generation (CTG) are essentially challenging to adapt to various control objectives and constraints, which results in mixed success.
Approach:	They propose a unified controllable text generation framework which integrates a control module, a prompt module, and a generation module.
Outcome:	The proposed framework significantly improves query accuracy and coherence in tasks with different objectives and constraints.

Lightweight Safety Guardrails Using Fine-tuned BERT Embeddings (2025.coling-industry)

Copied to clipboard

Aaron Zheng, Mansi Rana, Andreas Stolcke

Zero-shot Slot Filling in the Age of LLMs for Dialogue Systems (2025.coling-industry)

Challenge:	Existing approaches to filter out inappropriate user prompts or system outputs have been successful, but using fine-tuned LLMs as guardrails introduces increased latency and higher maintenance costs.
Approach:	They propose to fine-tune a lightweight architecture that reduces the model size from LlamaGuard’s 7 billion parameters to approximately 67 million parameters.
Outcome:	Sentence-BERT reduces the model size from 7 billion parameters to approximately 67 million while maintaining comparable performance on the AEGIS safety benchmark.

Copied to clipboard

Mansi Rana, Kadri Hacioglu, Sindhuja Gopalan, Maragathamani Boothalingam

LionGuard: A Contextualized Moderation Classifier to Tackle Localized Unsafe Content (2025.coling-industry)

Challenge:	Existing methods for zero-shot slot filling focus on text data, overlooking conversational data.
Approach:	They propose a method for automatic data annotation with slot induction and black-box knowledge distillation from a teacher LLM to a smaller model.
Outcome:	The proposed method outperforms existing models on internal datasets by 26% relative increase in F1 score.

Copied to clipboard

Jessica Foo, Shaun Khoo

Text Classification

Challenge:	Existing moderation classes that perform well on English may not perform well in Singlish.
Approach:	They propose a Singapore-contextualized moderation classifier that can guard against unsafe LLM usage.
Outcome:	The proposed class outperforms existing modes on Singlish data by 14% and up to 51%.

REVerSum: A Multi-staged Retrieval-Augmented Generation Method to Enhance Wikipedia Tail Biographies through Personal Narratives (2025.coling-industry)

Copied to clipboard

Sayantan Adak, Pauras Mangesh Meher, Paramita Das, Animesh Mukherjee

RE-FIN: Retrieval-based Enrichment for Financial data (2025.coling-industry)

Challenge:	Creating new articles and editing older ones is expensive and time-consuming.
Approach:	They propose a multi-staged retrieval-augmented generation technique to leverage personal narratives to enhance Wikipedia’s B and C category biography articles.
Outcome:	The proposed approach outperforms the best performing baseline by 17% in terms of integrability to the original Wikipedia article and 28.5% in terms informativeness.

Copied to clipboard

Lorenzo Malandri, Fabio Mercorio, Mario Mezzanzanica, Filippo Pallucchini

SCV: Light and Effective Multi-Vector Retrieval with Sequence Compressive Vectors (2025.coling-industry)

Challenge:	Financial sentiment analysis (FSA) is a powerful tool to support business decision-making and perform financial forecasting.
Approach:	They propose a system that retrieves information from a knowledge base to enrich financial sentences, making them more knowledge-dense and explicit.
Outcome:	The proposed system generates propositions from the knowledge base and employs Retrieval-Augmented Generation (RAG) to augment the original text with relevant information.

Copied to clipboard

Cheoneum Park, Seohyeong Jeong, Minsang Kim, KyungTae Lim, Yong-Hun Lee

Efficient Vocabulary Reduction for Small Language Models (2025.coling-industry)

Challenge:	Recent advances in language models (LMs) have driven progress in information retrieval (IR), effectively extracting semantically relevant information.
Approach:	They propose a multi-vector retrieval framework with sequence compression vectors and a coarse-to-fine vector search framework that uses span compressive vectors to score documents.
Outcome:	The proposed approach achieves the fastest latency compared to other state-of-the-art models and can obtain competitive performance on both in-domain and out-of domain benchmark datasets.

Copied to clipboard

Yuta Nozaki, Dai Nakashima, Ryo Sato, Naoki Asaba

Towards Boosting LLMs-driven Relevance Modeling with Progressive Retrieved Behavior-augmented Prompting (2025.coling-industry)

Challenge:	Large language models (LLMs) have high computational costs and energy consumption, making their deployment in industrial settings difficult.
Approach:	They propose a small language model that compresses the embedding layer and reduces model size without significant loss of performance.
Outcome:	The proposed model reduces the embedding layer while maintaining performance while improving accuracy and performance.

Copied to clipboard

Zeyuan Chen, Haiyan Wu, Kaixin Wu, Wei Chen, Mingjie Zhong, Jia Xu, Zhongyi Liu, Wei Zhang

LLM ContextBridge: A Hybrid Approach for Intent and Dialogue Understanding in IVSR (2025.coling-industry)

Challenge:	Existing approaches to relevance modeling have lacked generalization and accuracy . recent studies have focused on capturing the semantic relationships between queries and items .
Approach:	They propose a framework that integrates world knowledge stored in LLMs with specialized domain knowledge represented by user behavior data for promising performance.
Outcome:	The proposed framework can handle full-scale search traffics of Alipay with acceptable cost and latency.

Copied to clipboard

Changwoo Chun, Daniel Rim, Juhee Park

Neural Document Segmentation Using Weighted Sliding Windows with Transformer Encoders (2025.coling-industry)

Challenge:	In-vehicle speech recognition systems struggle with interpreting user intent accurately due to limitations in contextual understanding and ambiguity resolution.
Approach:	They propose a hybrid architecture that integrates Pretrained Language Model-based intent classification with Large Language Models to enhance both command recognition and dialogue management.
Outcome:	The proposed architecture improves recognition accuracy and user experience in multi-turn dialogues.

Copied to clipboard

Saeed Abbasi, Aijun An, Heidar Davoudi, Ron Di Carlantonio, Gary Farmaner

RecStream: Graph-aware Stream Management for Concurrent Recommendation Model Online Serving (2025.coling-industry)

Challenge:	Using overlapping text sequences and position-aware weighting, we achieve up to a 10% increase in segmentation F1 score compared to existing methods.
Approach:	They propose a Transformer-based method for document segmentation that utilizes overlapping text sequences with a unique position-aware weighting mechanism to enhance segmentation accuracy.
Outcome:	The proposed method achieves up to 10% increase in segmentation F1 score compared to existing methods and improves quality of generated responses by 5% while achieving four times greater efficiency.

Copied to clipboard

Shuxi Guo, Qi Qi, Haifeng Sun, Jianxin Liao, Jingyu Wang

Structured Data in NLP

Challenge:	Existing systems that use recommendation models perform poorly under highly concurrent scenarios.
Approach:	They propose a system that optimizes stream configurations based on model characteristics and concurrency levels.
Outcome:	The proposed system outperforms existing methods under high concurrency scenarios.

Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models (2025.coling-industry)

Copied to clipboard

Wenting Tan, Dongxiao Chen, Jieting Xue, Zihao Wang, Taijie Chen