Papers with industrial applications
Mixture of Heterogeneous Grouped Experts for Language Modeling (2026.acl-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) based on Mixture-of-Experts (MoE) enforce uniform expert sizes, creating a rigidity that fails to align computational costs with varying token-level complexity. |
| Approach: | They propose a mixture of heterogeneous grouped experts (MoHGE) that allows for flexible, resource-aware expert combinations. |
| Outcome: | The proposed model matches the performance of existing Mixture-of-Experts architectures while maintaining balanced GPU utilization. |
LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Large language models (LLMs) struggle with factual accuracy in knowledge-intensive domains like healthcare. |
| Approach: | They propose a framework for improving LLM factuality in medical question answering . RAFE, Fact-Check-then-RAG and Learning from Fact Check are components . |
| Outcome: | Experimental results show that LEAF outperforms Factcheck-GPT in detecting inaccuracies and corrects errors without labeling . the framework provides a scalable solution for industrial applications requiring high factuality scores. |
CarMem: Enhancing Long-Term Memory in LLM Voice Assistants through Category-Bounding (2025.coling-industry)
Copied to clipboard
| 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. |
LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questions (2025.acl-industry)
Copied to clipboard
| Challenge: | Anomaly Detection (AD) focuses on detecting samples that differ from the standard pattern, making it vital for quality control and process optimization. |
| Approach: | They propose a framework that provides industrial operators with explanations for logical anomalies by compiling automatically generated questions into a checklist and collecting responses. |
| Outcome: | The proposed framework achieves state-of-the-art (SOTA) Logical AD performance on public benchmarks, MVTec LOCO AD, with an AUROC of 87.6% and an F1-max of 88.0% along with the explanations of anomalies. |
Transfer Learning for Context-Aware Question Matching in Information-seeking Conversations in E-commerce (P18-2)
Copied to clipboard
| Challenge: | Recent researches focus on deep learning and reinforcement learning for multi-turn information seeking conversation systems. |
| Approach: | They propose an efficient and effective multi-turn conversation model based on convolutional neural networks and extend it to adapt the knowledge learned from a resource-rich domain to enhance the performance. |
| Outcome: | The proposed model performs better than the existing model on an industrial chatbot called AliMe Assist. |
Predicting ICU Length of Stay for Patients using Latent Categorization of Health Conditions (2025.naacl-industry)
Copied to clipboard
| Challenge: | Traditional approaches to predicting the duration of a patient's stay in an Intensive Care Unit (ICU) rely on structured clinical data, but recent advances in language models offer significant potential to utilize unstructured text data for ICU length-of-stay (LoS) predictions. |
| Approach: | They propose a method for analyzing nursing notes to predict ICU length-of-stay of patients. |
| Outcome: | The proposed model outperforms baseline models on the MIMIC-III dataset and shows that it significantly outperformed existing models. |
SaFER: A Robust and Efficient Framework for Fine-tuning BERT-based Classifier with Noisy Labels (2023.acl-industry)
Copied to clipboard
| Challenge: | Existing noise-handling methods could not improve performance of BERT on noisy datasets . existing methods could only improve performance on noisy data, authors say . |
| Approach: | They propose a fine-tuning framework for BERT-based text classifiers that combats label noises without access to clean data for training or validation. |
| Outcome: | The proposed framework achieves superior performance on multiple text classification benchmarks. |
Developing Prefix-Tuning Models for Hierarchical Text Classification (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Hierarchical text classification (HTC) is a key task in many industrial applications. Pre-trained Language Models (PLMs) have become dominant for most natural language processing (NLP) tasks. |
| Approach: | They investigate how prefix tuning can improve hierarchical text classification . prefix-tuning model only needs less than 1% of parameters to achieve performance . |
| Outcome: | The proposed model can achieve comparable performance to regular full fine-tuning. |
More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Despite various proposed data construction methods, their practical utility in real-world pipelines remains underexplored. |
| Approach: | They conduct a comprehensive analysis of open-source datasets and data synthesis techniques for mathematical reasoning under a unified pipeline designed to mirror training and deployment scenarios. |
| Outcome: | The proposed pipelines mirror training and deployment scenarios and are suitable for industrial applications. |
Zero-Shot-BERT-Adapters: a Zero-Shot Pipeline for Unknown Intent Detection (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Intent discovery remains a crucial task in natural language processing . identifying novel, unseen intents remains one of the biggest challenges in this field . |
| Approach: | They propose a multi-language approach to intent discovery using Adapters and a Transformer architecture. |
| Outcome: | The proposed pipeline outperforms baselines in two zero-shot settings for intent classification and unseen intent discovery. |
Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling (2025.emnlp-industry)
Copied to clipboard
Xiaoyu Liu, Di Liang, Hongyu Shan, Peiyang Liu, Yonghao Liu, Muling Wu, Yuntao Li, Xianjie Wu, Li Miao, Jiangrong Shen, Minlong Peng
| Challenge: | Generative RMs (GRMs) lack contextual and background information during inference, leading to incomplete evaluations. |
| Approach: | They propose a modular and interpretable framework that integrates side-branch models as auxiliary feature generators. |
| Outcome: | The proposed framework outperforms scalar and saline reward models in robustness and alignment with human preferences. |
RAG4ITOps: A Supervised Fine-Tunable and Comprehensive RAG Framework for IT Operations and Maintenance (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have improved the open-domain QA’s performance, but how to efficiently handle enterprise-exclusive corpora and build domain-specific QA systems are still not studied for industrial applications. |
| Approach: | They propose a general and comprehensive framework based on Retrieval Augmented Generation (RAG) and facilitate the whole business process of establishing QA systems for IT operations and maintenance. |
| Outcome: | The proposed framework achieves superior results on two kinds of QA tasks. |
PromptSculptor: Multi-Agent Based Text-to-Image Prompt Optimization (2025.emnlp-demos)
Copied to clipboard
| Challenge: | PromptSculptor automates the iterative prompt optimization process for Text-to-Image models . previous work focused on generating detailed, high-quality prompts based on user feedback . |
| Approach: | They propose a framework that decomposes a task into four specialized agents . they use Chain-of-Thought reasoning to transform a short, vague user prompt into a comprehensive, refined prompt. |
| Outcome: | The proposed framework significantly improves output quality and reduces iterations needed for user satisfaction. |
MICE: Mixture of Image Captioning Experts Augmented e-Commerce Product Attribute Value Extraction (2025.acl-industry)
Copied to clipboard
| Challenge: | Existing visual attribute value extraction methods rely on product images and textual information, which can be ambiguous, inaccurate, or unavailable. |
| Approach: | They propose a framework that leverages a curated pool of image captioning models to generate accurate captions from product images. |
| Outcome: | The proposed framework significantly improves state-of-the-art large multimodal models in zero-shot and fine-tuning settings. |
InstaJudge: Aligning Judgment Bias of LLM-as-Judge with Humans in Industry Applications (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Automated evaluation using LLM-as-Judge is a viable alternative to human evaluation, but misalignment of judgment biases between humans and LLMs hinders its use in real-world applications. |
| Approach: | They propose an LLM-as-Judge library that improves alignments of judgment biases through automatic prompt optimization. |
| Outcome: | The proposed library outperforms existing LLM-as-Judge libraries by a large margin while being more cost efficient. |
Time-LlaMA: Adapting Large Language Models for Time Series Modeling via Dynamic Low-rank Adaptation (2025.acl-srw)
Copied to clipboard
| Challenge: | Recent studies have demonstrated that large language models possess robust pattern recognition and semantic understanding capabilities over time series data. |
| Approach: | They propose a time series model that converts time series input into token embeddings and aligns time sequence embeddables with text prompts. |
| Outcome: | The proposed framework achieves the state-of-the-art (SOTA) performance and has potentials for wide industrial usages. |
Quantifying the Impact of Structured Output Format on Large Language Models through Causal Inference (2026.findings-eacl)
Copied to clipboard
| Challenge: | Prior studies have examined the impact of structured output on LLMs’ generation quality, often presenting one-way findings. |
| Approach: | They propose to derive five potential causal structures characterizing the influence of structured output on LLMs’ generation using one assumed and two guaranteed constraints. |
| Outcome: | The proposed pipeline can be extended to other modules and is not limited to structured output but can be used in industrial applications. |
Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems (2025.emnlp-industry)
Copied to clipboard
Kayhan Behdin, Ata Fatahibaarzi, Qingquan Song, Yun Dai, Aman Gupta, Zhipeng Wang, Hejian Sang, Shao Tang, Gregory Dexter, Sirou Zhu, Siyu Zhu, Tejas Dharamsi, Vignesh Kothapalli, Zhoutong Fu, Yihan Cao, Pin-Lun Hsu, Fedor Borisyuk, Natesh S. Pillai, Luke Simon, Rahul Mazumder
| Challenge: | Large language models (LLMs) have demonstrated remarkable performance across a wide range of industrial applications. |
| Approach: | They propose two techniques for training and deploying small language models that deliver high performance for a variety of industry use cases. |
| Outcome: | The proposed techniques retain much of the quality of larger models while reducing training/serving costs and latency. |
LLMInit: A Free Lunch from Large Language Models for Selective Initialization of Recommendation (2025.emnlp-industry)
Copied to clipboard
Weizhi Zhang, Liangwei Yang, Wooseong Yang, Henry Peng Zou, Yuqing Liu, Ke Xu, Sourav Medya, Philip S. Yu
| Challenge: | Existing algorithms for collaborative filtering are limited by their computational demands and latency. |
| Approach: | They propose a framework to integrate pre-trained LLM embeddings into CF models through selective initialization strategies. |
| Outcome: | The proposed framework improves recommendation performance while maintaining low computational costs. |
Sudachi: a Japanese Tokenizer for Business (L18-1)
Copied to clipboard
| Challenge: | Lack of token unit compatibility is one of the critical problems of Japanese language resources. |
| Approach: | They develop a Japanese tokenizer called Sudachi and its accompanying dictionary . they use multi-granular output and normalization of notation variations to improve tokenization . |
| Outcome: | The proposed tokenizer and dictionary improve tokenization in Japanese for business use. |
QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory (2025.findings-emnlp)
Copied to clipboard
Yihang Wang, Xu Huang, Bowen Tian, Yueyang Su, Lei Yu, Huaming Liao, Yixing Fan, Jiafeng Guo, Xueqi Cheng
| Challenge: | Existing methods for compressing context by removing redundant tokens are inconsistent with the objective of retaining the most important tokens when conditioning on a given query. |
| Approach: | They propose a method that uses information bottleneck theory to compress context . they propose to remove redundant tokens using metrics such as self-information or perplexity . |
| Outcome: | The proposed method achieves a 25% increase in compression rate compared to the state-of-the-art . |
RECAL: Sample-Relation Guided Confidence Calibration over Tabular Data (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Various machine learning methods for tabular data lack accurate confidence estimation, which is needed for high-risk sensitive applications such as credit modeling and financial fraud detection. |
| Approach: | They propose a general post-training confidence calibration framework to calibrate the confidence of current machine learning models by employing graph neural networks to model the relationships between different samples. |
| Outcome: | The proposed framework improves the confidence estimation on tabular datasets by using graph neural networks to model the relationships between different samples. |
Making Parameter-efficient Tuning More Efficient: A Unified Framework for Classification Tasks (2022.coling-1)
Copied to clipboard
Xin Zhou, Ruotian Ma, Yicheng Zou, Xuanting Chen, Tao Gui, Qi Zhang, Xuanjing Huang, Rui Xie, Wei Wu
| Challenge: | Large pre-trained language models (PLMs) have demonstrated superior performance in industrial applications. |
| Approach: | They propose a framework that re-uses existing parameter-efficient methods with a unified classifier. |
| Outcome: | The proposed framework improves the efficiency of existing parameter-efficient methods with a unified classifier. |
Reinforced Active Learning for Low-Resource, Domain-Specific, Multi-Label Text Classification (2023.findings-acl)
Copied to clipboard
| Challenge: | Modern text classification systems achieve excellent accuracy across tasks and corpora. |
| Approach: | They propose a Reinforcement Learning policy that uses many different aspects of the data and task to select the most informative unlabeled subset dynamically over the course of the AL procedure. |
| Outcome: | The proposed framework outperforms baselines on four complex multi-class, multi-label text classification datasets. |
StyleKQC: A Style-Variant Paraphrase Corpus for Korean Questions and Commands (2022.lrec-1)
Copied to clipboard
| Challenge: | Especially for questions and commands, style-variant paraphrasing can be crucial in tone and manner. |
| Approach: | They propose a corpus construction scheme that considers intent and formality of directives in Korean language. |
| Outcome: | The proposed method is validated by a corpus construction scheme on Korean topics. |
Fine-Tuned Thoughts: Leveraging Chain-of-Thought Reasoning for Industrial Asset Health Monitoring (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Small Language Models (SLMs) are becoming increasingly popular in specialized fields such as industrial applications. |
| Approach: | They propose a framework which transfers reasoning capabilities via Chain-of-Thought distillation from Large Language Models (LLMs) to smaller, more efficient models (SLMs) |
| Outcome: | The proposed framework outperforms the base models in Industry 4.0 by a significant margin. |
T2R-BENCH: A Benchmark for Real World Table-to-Report Task (2025.emnlp-main)
Copied to clipboard
Jie Zhang, Changzai Pan, Sishi Xiong, Kaiwen Wei, Yu Zhao, Xiangyu Li, Jiaxin Peng, Xiaoyan Gu, Jian Yang, Wenhan Chang, Zhenhe Wu, Jiang Zhong, Shuangyong Song, Xuelong Li
| Challenge: | Existing table benchmarks lack the capacity to adequately assess the practical application of table reasoning in industrial applications. |
| Approach: | They propose a bilingual table-to-report task and a table-based benchmark to assess the quality of table reasoning. |
| Outcome: | The proposed task is based on a bilingual benchmark with 457 industrial tables and evaluation criteria to measure the quality of report generation. |