Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)
ACL 2026 Industry Track: Overview (2026.acl-industry)
Copied to clipboard
| Challenge: | 153 papers were selected for presentation at the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026). |
| Approach: | the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) organised a dedicated industry track. authors acknowledge the challenges in adapting language technologies for building novel and robust. |
| Outcome: | the industry track attracted 532 papers at the 64th Annual Meeting of the Association for Computational Linguistics . the submissions can be grouped into six different clusters: 1. RAG systems & enterprise knowledge AI; 2. agentic systems and workflows; 3. Language technologies and their applications are an integral and critical part of our daily lives. |
Smarter, not Bigger: Fine-Tuned RAG-Enhanced LLMs for Automotive Hardware-in-the-Loop Testing (2026.acl-industry)
Copied to clipboard
| Challenge: | Hardware-in-the-Loop (HIL) testing is essential for automotive validation but suffers from fragmented and underutilized test artifacts. |
| Approach: | They propose to integrate semantic retrieval with domain-adapted large language models to support test engineers in real-world HIL workflows. |
| Outcome: | The proposed system improves perceived helpfulness, truthfulness, and satisfaction over general-purpose LLMs. |
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)
Copied to clipboard
Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He
| Challenge: | Document images are characterized by higher resolutions, denser content, and more complex structural layouts. |
| Approach: | They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition. |
| Outcome: | The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead. |
Leveraging Generative AI for Extracting Business Requirements from Legacy COBOL and PL/I Code (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing pipelines for extracting business requirements from legacy systems are difficult because they are scattered across interdependent programs and data definitions. |
| Approach: | They propose an LLM-augmented reverse-engineering pipeline that provides deterministic parsing and schema-constrainedLLM generation with bidirectional traceability. |
| Outcome: | The proposed pipeline achieves 93% agreement with expert-authored business rules and reduces documentation effort by approximately 70% on 3.4M lines across workloads. |
Is Agentic RAG worth it? An experimental comparison of RAG approaches (2026.acl-industry)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) systems have several limitations, including noisy or suboptimal retrieval, misuse of retrieval for out-of-scope queries, weak query–document matching, and variability or cost associated with the generator. |
| Approach: | They propose to use a "Enhanced" RAG to address weaknesses in the workflow . they propose to orchestrate the entire process, deciding which actions to perform, when to perform them, and whether to iterate . |
| Outcome: | The proposed models address shortcomings in the RAG workflow, and provide practical insights into the trade-offs between them. |
Improving Hate Speech Detection by Fusing Textual and User Interaction Representations in Online Communities (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing studies on toxic content in online communities are limited by the scarcity of data that align textual content with comprehensive social interactions. |
| Approach: | They propose a user-aware hate speech detection framework that effectively fuses textual semantics with social interaction representations to provide pragmatic context for disambiguation. |
| Outcome: | The proposed framework outperforms strong text-only baselines by over 3.6%, validating the critical role of social context in enhancing detection accuracy. |
TeachMaster: Generative Teaching via Code (2026.acl-industry)
Copied to clipboard
Yuheng Wang, Runde Yang, Lin Wu, Jie Zhang, Jingru Fan, Tianle Zhou, Ruoyu Fu, Huatao Li, Ruijie Shi, Siheng Chen, Weinan E, Chen Qian
| Challenge: | Existing methods for creating video content are limited by high costs and slow update cycles. |
| Approach: | They propose a paradigm shifting educators from manual creators to high-level directors who focus on pedagogical intents while agents handle execution. |
| Outcome: | The proposed framework reduces production costs to 0.3% of traditional course videos and provides a robust solution for scalable education. |
ARGUS: Policy-Adaptive Ad Governance via Evolving Reinforcement with Adversarial Umpiring (2026.acl-industry)
Copied to clipboard
Deyi Ji, Junyu Lu, Xuanyi Liu, Liqun Liu, Hailong Zhang, Peng Shu, Huan Yu, Jie Jiang, Tianrun Chen, Lanyun Zhu
| Challenge: | Existing regulatory policies create label inconsistencies and reasoning ambiguities in historical datasets. |
| Approach: | They propose a policy-adaptive governance system that enables evolving reinforcement through multi-agent adversarial umpiring. |
| Outcome: | The proposed system outperforms fine-tuning baselines on industrial and public datasets . it enables evolving reinforcement through multi-agent adversarial umpiring . |
Synthetic Text Detection in the Age of Large Language Models: Watermark vs. Automatic Detection (2026.acl-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are ubiquitous and capable of generating long coherent texts that look almost indistinguishable from human-written texts. |
| Approach: | They propose to use watermark and automatic detection to detect synthetic texts generated from Large Language Models (LLMs) they evaluate six different models, six different watermark techniques and two different automatic detectors for different levels of syntactic changes. |
| Outcome: | The proposed methods outperform on unperturbed and perturbed datasets on six different sizes of Qwen2.5 models, six watermark techniques and detectors, and two automatic detectors. |
R³A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing approaches to query–document relevance assessment are limited . ambiguous user intent and asymmetric relevance are challenges for RAG platforms . |
| Approach: | They propose a decomposed reasoning model for relevance assessment that decomposes query intent into intent inference and evidence grounding. |
| Outcome: | The proposed model outperforms strong baselines on offline benchmarks and achieves significant gains in large-scale online A/B testing. |
HAD: HAllucination Detection Language Models Based on a Comprehensive Hallucination Taxonomy (2026.acl-industry)
Copied to clipboard
| Challenge: | relying on large language models for information has raised concerns about reliability and accuracy of outputs. |
| Approach: | They propose a hallucination taxonomy with 11 categories for various NLG tasks and propose HAllucination Detection models which integrate hallucinism detection, span-level identification, and correction into a single inference process. |
| Outcome: | The proposed models outperform baselines on HaluEval, FactCHD, and FaithBench, confirming their robustness and versatility. |
DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting (2026.acl-industry)
Copied to clipboard
Md Mofijul Islam, Md Sirajus Salekin, Nivedha Balakrishnan, Vincil C. Bishop III, Niharika Jain, Spencer Romo, Bob Strahan, Boyi Xie, Diego A. Socolinsky
| Challenge: | Document understanding in real-world applications often requires processing heterogeneous, multi-page document packets containing multiple documents stitched together. |
| Approach: | They propose to use document packet splitting to improve document understanding in real-world applications. |
| Outcome: | The proposed datasets and evaluation metrics provide a systematic framework for advancing document understanding capabilities essential for legal, financial, healthcare, and other document-intensive domains. |
TaoType: Predicting Fine-Grained Typing Intent for Faster Search (2026.acl-industry)
Copied to clipboard
| Challenge: | Large-scale industrial ranking systems operate under stringent real-time performance requirements. |
| Approach: | They propose a client-side framework that determines whether a user’s query is complete at each typing . this method leverages client-based typing behavior for real-time early prediction . |
| Outcome: | The proposed framework achieves offline precision/recall/accuracy of 0.7936/0.8196/0.7742 and decreases online response time by 640.5193.65 milliseconds. |
Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation (2026.acl-industry)
Copied to clipboard
Bhaktipriya Radharapu, Eshika Saxena, Kenneth Li, Chenxi Whitehouse, Adina Williams, Nicola Cancedda
| Challenge: | Existing methods for obtaining well-calibrated uncertainty estimates are poorly calibrated or computationally expensive. |
| Approach: | They propose a linear probe that provides calibrated uncertainty estimates from reasoning judges’ hidden states, requiring no additional model training. |
| Outcome: | The proposed method achieves superior calibration compared to existing methods with x computational savings, generalizes robustly to unseen evaluation domains, and delivers higher accuracy on high-confidence predictions. |
Detecting AI-Generated Content on Social Media with Multi-modal Language Models (2026.acl-industry)
Copied to clipboard
Chenyang Yang, Shen Yan, Yibo Yang, Litao Hu, Yuchen Liu, Yuan Zeng, Hanchao Yu, Yinan Zhu, Sumedha Singla, Brian Vanover, Huijun Qian, Zihao Wang, Fujun Liu, Aashu Singh, Jianyu Wang, Xuewen Zhang
| Challenge: | Existing methods for AI-generated content detection face poor generalization to newer models, reliance on single modalities, and lack of interpretable explanations. |
| Approach: | They propose a model that curates diverse social media data and trains a vision-language model for detection and explanation. |
| Outcome: | The proposed model achieves state-of-the-art detection performance on public benchmarks and observes positive downstream impacts on user engagement. |
IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters (2026.acl-industry)
Copied to clipboard
Hongwei Zheng, Weiqi Wu, Zhengjia Wang, Guanyu Jiang, Haoming Li, Tianyu Wu, Yongchun Zhu, Jingwu Chen, Feng Zhang
| Challenge: | Existing efforts focus on activation within ongoing dialogues, while overlooking a key real-world bottleneck. |
| Approach: | They propose a conversation starter generation system that generates personalized starters to guide users into conversation without explicit user intent. |
| Outcome: | The proposed system improves user active days by +1.84 and click-through rate by +94.25 and has been deployed in production. |
Motivating Next-Gen Accelerators with Flexible N:M Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches (2026.acl-industry)
Copied to clipboard
Shirin Alanova, Kristina Kazistova, Ekaterina Galaeva, Alina Kostromina, Vladimir Smirnov, Redko Dmitry, Alexey Dontsov, Maxim Zhelnin, Evgeny Burnaev, Egor Shvetsov
| Challenge: | Recent studies show that sparsification is not supported in large language models. |
| Approach: | They propose to use activation pruning to accelerate large language models with sparsification . they compare activation pruners with weight pruner and activater pruning with activation . |
| Outcome: | The proposed approach outperforms weight pruning at matched sparsity levels. |
Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing high-quality conversational data is limited for full-duplex models . overlapping and backchanneling are a challenge for most systems . |
| Approach: | They propose a robust and scalable open-source data processing pipeline for full-duplex models. |
| Outcome: | The proposed pipeline can listen and speak simultaneously, supporting more fluid and human-like interaction. |
Proximity-Based Multi-Turn Optimization: Practical Credit Assignment for LLM Agent Training (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing group-based policy optimization methods rely on statistical deviation within discrete batches, misallocating credit when task difficulty fluctuates. |
| Approach: | They propose a framework for multi-turn LLM agents that integrates global context . they propose GRPO, which integrates success-rate-aware modulation and proximity-based soft aggregation . |
| Outcome: | The proposed framework yields performance gains over existing baselines with negligible computational cost. |
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. |
Policy Compliance of User Requests in Natural Language for AI Systems (2026.acl-industry)
Copied to clipboard
| Challenge: | In industrial settings, powerful large language models are becoming more common. |
| Approach: | They propose a benchmark to evaluate the performance of various large language models on policy compliance assessment under different solution methods. |
| Outcome: | The proposed benchmark compares model performance with other models and solution methods in industrial applications. |
Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach (2026.acl-industry)
Copied to clipboard
| Challenge: | Literary translation requires balancing expression fluency with literary effect due to the scarcity of high-quality training data and the difficulty of capturing nuanced quality trade-offs. |
| Approach: | They propose a multi-aspect iterative refinement framework that generates high-quality translation references and preference data through specialized LLM translators. |
| Outcome: | The proposed models outperform the ground truth for SFT by 8.65 CEA100 points while leveraging an explicit reward model for GRPO yields an additional 1.51 point improvement. |
SSR-A: Spatial- and Semantic-Aware Instructions and Curriculum Reinforcement for Advertisement Compliant Rectification (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing methods to fix non-compliant images suffer from over-editing, destroying original intent and perceptual similarity. |
| Approach: | They propose a framework for the minimalist rectification of non-compliant image ads. |
| Outcome: | The proposed framework outperforms state-of-the-art baselines in both compliance and preservation of visual and commercial consistency. |
ℛ3: Advertisement Compliance ℛectification via Group-ℛelative Experience Extractor and Curriculum ℛeinforcement (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing methods of content moderation are infeasible due to over-editing and compromise the advertiser’s original semantic intent. |
| Approach: | They propose a framework to harmonize compliance with original intent preservation that integrates a data-driven framework and a curriculum to enforce compliance while maximizing semantic consistency. |
| Outcome: | The proposed framework outperforms state-of-the-art baselines on industrial datasets and on online A/B testing on industrial video. |
GrocLM: Grocery Category Recommendation in E-Commerce with Large Language Models (2026.acl-industry)
Copied to clipboard
| Challenge: | a growing number of online grocery shoppers are using category-level recommendation systems . traditional item-level methods face scalability and accuracy challenges . |
| Approach: | a new language model is developed to encode cyclical purchasing patterns into model parameters . the model is scalable and more business-aligned than traditional item-level methods . |
| Outcome: | a new language model outperforms standard methods in a live production environment . the proposed model achieves a 7.5% relative improvement in cart-adds per impression . |
DeepResearch Retail: Benchmarking Tool-Augmented Deep Research in the E-Commerce Domain (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing DR systems are largely web-centric and do not incorporate structured, domain-specific, and personalized information accessible through internal API tools. |
| Approach: | They propose a framework grounded in real-world e-commerce data for assessing Deep Research with tools in realistic commercial settings. |
| Outcome: | The proposed framework evaluates factual faithfulness and multidimensional response quality when reasoning over heterogeneous web and internal data sources. |
GeoGround: Uncertainty-Weighted Multi-Task Learning for Geo-Alignment and Address Defect Detection (2026.acl-industry)
Copied to clipboard
| Challenge: | Address intelligence in e-commerce requires precise geocoding and proactive defect detection under strict sub-50 ms latency constraints. |
| Approach: | They propose a multi-task learning framework that jointly models coordinate grounding and address defect detection. |
| Outcome: | The proposed model achieves 5.86 gains in address defect detection precision and 4.86 improvements in location prediction accuracy over strong encoder baselines while remaining 75 more efficient than decoder LLMs such as Qwen2-1.5B. |
Pre-Deployment Advertisement Ranking under Data Scarcity via Context-Aware Criteria Generation with VLMs (2026.acl-industry)
Copied to clipboard
Kyungho Kim, Yeonje Choi, Gyurim Hwang, Sejin Chung, Hongseok Lee, Myeong Ho Song, Yeongho Kim, Sunwoo Kim, Jongha Lee, Juyeon Kim, Kijung Shin
| Challenge: | Existing VLMs perform well on general multimodal tasks, but limited labeled data makes them difficult to apply to real-world business decisions. |
| Approach: | They propose a new task that aims to rank ads for a target brand prior to deployment . they propose 'brand-specific ad ranking' which uses brand-specific effectiveness . |
| Outcome: | The proposed task outperforms baselines on 10 brands on real-world advertising data. |
Agent-Ops: A Multi-Agent Orchestration Framework for End-to-End SOP Automation in E-Commerce Operations (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing Large Language Models fail to execute multistep operational workflows requiring precise procedural adherence. |
| Approach: | They propose an end-to-end multi-agent framework automating Standard Operating Procedures in e-commerce. |
| Outcome: | The proposed framework achieves 85-97% accuracy and a 94.2% execution consistency in e-commerce . it is based on a human-AI framework that transforms ambiguous documentation into automation-ready specifications . |
Reason-Code: Reliable Code Generation via Test-Driven Monte Carlo Tree Search (2026.acl-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are widely used for code generation, but their performance degrades on complex tasks. |
| Approach: | They propose an inference-time framework that formulates code generation as a search process guided by execution feedback. |
| Outcome: | The proposed framework improves reliability without paying full cost of additional sampling under strict latency budgets. |
Optimizing Retrieval-Augmented Generation for E-Commerce How-To Assistance (2026.acl-industry)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have significantly improved Retrieval-Augmented Generation (RAG), enabling assistants that can reliably ground responses in external knowledge sources while maintaining high-quality natural language interaction. |
| Approach: | They propose a RAG-based How-To Assistant that groundes responses in a proprietary knowledge base to provide personalized customer support. |
| Outcome: | The proposed assistant can ground responses in a proprietary knowledge base while maintaining high-quality natural language interaction. |
UNIVID: Unified Vision-Language Model for Video Moderation (2026.acl-industry)
Copied to clipboard
Kejuan Yang, Yizhuo Zhang, Mingyuan Du, Yue Zhang, Dixin Zheng, Kaili Zhao, Yang Xiao, Hanzhong Liang, Kenan Xiao
| Challenge: | Existing video moderation systems rely on fragmented black-box classification models that are difficult to maintain and lack transparency. |
| Approach: | They propose a Unified Vision-Language model for Video Moderation that generates policy-aware captions that serve as an interpretable intermediate representation. |
| Outcome: | The proposed model reduces violation leakage and overkill rate by 42.7% while reducing maintenance costs. |
Learning from Textual Radiology Reports: A Benchmark Dataset for Coronary CT Angiography (2026.acl-industry)
Copied to clipboard
Sudharshan Balaji, Zhiyu Liu, Zhengyuan Jiang, Shuo Lei, Yimin Chen, Yang Xiao, Shone O. Almeida, Mathew Joseph Karivelil, Christopher Malanga, Ning Wang
| Challenge: | CCTA reports provide an assessment of coronary disease severity to guide patient management. |
| Approach: | They propose a pipeline that decouples structuring from classification by an LLM-based parser . CCTA-RADS is the largest publicly available dataset of CCDA reports . |
| Outcome: | The proposed approach improves the F1-score by 6%-13% compared with direct methods. |
Teaching LLM to be Persuasive: Reward-Enhanced Policy Optimization for Alignment from Heterogeneous Rewards (2026.acl-industry)
Copied to clipboard
| Challenge: | a large language model (LLM) is used as a business development agent for persuasive price negotiation in online travel agencies. |
| Approach: | They propose a reward-enhancing policy optimization method that integrates three complementary reward sources-a preference-trained reward model and an LLM-as-a-judge. |
| Outcome: | The proposed method improves average dialogue rating to 4.63 (+0.33 over GRPO) and raises share of conversations with at least one excellent response to 66.67% (+23.34 pp over grepo). |
NEST: Nested Evidence Survival for Retrieval (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing approaches to retrieval-augmented generation (RAG) rely on rigid heuristics or computational overhead. |
| Approach: | They propose a lightweight, training-free RAG framework that separates recall amplification from precision selection. |
| Outcome: | Evaluated on WebQuestions, HotpotQA and internalQA benchmarks, NEST outperforms strong adaptive RAG baselines. |
Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training (2026.acl-industry)
Copied to clipboard
Tianle Xia, Ming Xu, Lingxiang Hu, Yiding Sun, Wenwei Li, Linfang Shang, Liqun Liu, Peng Shu, Huan Yu, Jie Jiang
| Challenge: | Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, yet traditional singleround retrieval struggles with complex multistep reasoning. |
| Approach: | They propose a framework that introduces path-centric reward shaping for agentic RAG training. |
| Outcome: | The proposed framework improves on existing methods with an average accuracy gain of 7.7 points. |
AgenticQwen: Training Small Agentic Language Models with Dual Data Flywheels for Industrial-Scale Tool Use (2026.acl-industry)
Copied to clipboard
| Challenge: | Modern industrial applications increasingly demand language models capable of multi-step reasoning and tool use in real-world settings. |
| Approach: | They propose a model family that trains via multi-round reinforcement learning on synthetic data and open-source data. |
| Outcome: | The proposed model train on synthetic and open-source data achieves strong performance on multiple agentic benchmarks and in an industrial agent system. |
From Short Video to Clickable Search: RLVR-Enabled Listwise Query Suggestion with Retrieval-Augmented Context (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing methods to generate short-video bottom-bar queries are largely retrieval-based. |
| Approach: | They propose to reformulate the task as one-shot list generation, producing multiple queries per video . they also build multi-query ground truth from exposure and CTR logs, and redesign offline evaluation . |
| Outcome: | The proposed system yields strong offline and online improvements . it is deployed on Kuaishou to serve hundreds of millions of users daily . |
Small Agents, Big Gains: Journey-Aware and Critic-Guided Simulation for Long-Horizon Shopping Dialogues (2026.acl-industry)
Copied to clipboard
| Challenge: | e-commerce assistants must support inspiration, comparison, and tool-grounded fact-checking . lack of data-coverage and verification problem hampers efficient, deployable models . eaa: "training trajectories must cover diverse user workflows with high fidelity" |
| Approach: | They propose a system that synthesizes diverse, faithful, and policy-aligned shopping trajectories . a small model can significantly outperform same-size baselines and surpass a large-model baseline . |
| Outcome: | The proposed model outperforms existing models and surpasses large models with 8 higher inference throughput. |
Progressive Fine-Tuning for Cost-Effective Structured Attribute Generation in E-commerce (2026.acl-industry)
Copied to clipboard
| Challenge: | Large language models excel at structured information generation but face cost and latency challenges when deployed at scale in user-facing products. |
| Approach: | They propose a parameter efficient supervised fine-tuning pipeline for adapting a small language model to structured attribute generation in e-commerce product listing. |
| Outcome: | The proposed model reduces inference costs by 98% and latency by 70% on a large-scale product listing service while preserving an 86.4% user acceptance rate. |
Grounded Multimodal In-Context Learning for Product Weight Estimation at Scale in E-commerce (2026.acl-industry)
Copied to clipboard
| Challenge: | a large number of e-commerce platforms require manual verification and specialized hardware. |
| Approach: | They propose a multimodal weight estimation framework that uses category-specific exemplars to infer discretized weight buckets. |
| Outcome: | The proposed approach outperforms strong multimodal KNN baselines in accuracy and near-bucket reliability. |
Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA (2026.acl-industry)
Copied to clipboard
Wenwei Li, Ming Xu, Tianle Xia, Lingxiang Hu, Yiding Sun, Linfang Shang, Liqun Liu, Peng Shu, Huan Yu, Jie Jiang
| Challenge: | Existing methods for QA in industrial environments are inherently relational and often updated. |
| Approach: | They propose a framework that optimizes retrieval and generation through two components: Graph-aware Retrieval and evidence-constrained reinforcement learning. |
| Outcome: | Experiments on an internal advertising QA dataset show consistent gains across expert-judged dimensions including accuracy, completeness, safety, and URL validity. |
A Unified Framework for Modeling Heterogeneous Financial Data via Dual-Granularity Prompting (2026.acl-industry)
Copied to clipboard
| Challenge: | Recent industrial credit scoring models rely heavily on manually tuned statistical learning methods due to the complexity of heterogeneous financial data and the challenge of modeling evolving creditworthiness. |
| Approach: | They propose a framework that reformulates credit scoring as a multi-scale sequential learning problem. |
| Outcome: | FinLangNet improves KS and bad debt rate by 6.3 pp in real world deployments. |
DuIVRS-2: An LLM-based Interactive Voice Response System for Large-scale POI Attribute Acquisition (2026.acl-industry)
Copied to clipboard
| Challenge: | Accurate Point of Interest (POI) attribute acquisition is essential for location-based services, yet traditional IVR systems suffer from error accumulation and high maintenance overhead. |
| Approach: | They propose a large language model-based framework for large-scale POI attribute acquisition at Baidu Maps. |
| Outcome: | The proposed framework outperforms existing IVR systems in 83.9% task success rate while maintaining a low reaction time of 130ms. |
SAJA: A Simple Approach to Judge Alignment for LLM-as-a-Judge (2026.acl-industry)
Copied to clipboard
| Challenge: | Current approaches to evaluate text at scale require multiple calls and per-dataset prompt tuning. |
| Approach: | They propose a model-agnostic approach to evaluate judge alignment that uses a lightweight calibration head. |
| Outcome: | a new model with SAJA matches more complex systems across four evaluation paradigms . it outperforms uncalibrated models on MT-Bench pairwise preference and competitive performance on five classification benchmarks compared to uncalibred models . |
ColorBrowserAgent: Complex Long-Horizon Browser Agent with Adaptive Knowledge Evolution (2026.acl-industry)
Copied to clipboard
Jihong Wang, Jiamu Zhou, Weiming Zhang, Teng Wang, Weiwen Liu, Zhuosheng Zhang, Xingyu Lou, Weinan Zhang, Huarong Deng, Jun Wang
| Challenge: | Xue et al., 2025): deploying autonomous web agents in production remains difficult due to site heterogeneity and long-horizon instability. |
| Approach: | They propose a knowledge-evolving agent that can be used to automate web workflows . they use human-in-the-loop knowledge adaptation and knowledge-aligned progressive summarization . |
| Outcome: | Experiments on WebArena, WebChoreAren and industrial deployment show it outperforms baselines. |
ClinDet-Bench: Beyond Abstention, Evaluating Judgment Determinability of LLMs in Clinical Decision-Making (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing medical benchmarks are insufficient to evaluate LLMs under incomplete information. |
| Approach: | They develop a benchmark that decomposes incomplete information into determinable and undeterminable conditions. |
| Outcome: | a clinical scoring system can decompose incomplete information into determinable and undeterminable conditions. a new benchmark, ClinDet-Bench, can evaluate determinability under incomplete information. |
AIDA-SEAT: Towards Reliable AI Doctor Assistant via State-Evaluation-Action Tree Enhanced LLMs in Online Hospital (2026.acl-industry)
Copied to clipboard
Lianxin Sun, Xiaoying Ying, Guangya Yu, Weiyan Zhang, Chenhao Guan, Hao He, Mingxi Shang, Jianhua Li, ChunMing Wang, Tong Ruan
| Challenge: | Existing systems rely on large language models or retrieval-augmented generation (RAG) but these methods lack the explicit logical pathways essential for multi-step reasoning. |
| Approach: | They propose an AIDA-SEAT framework to provide reliable clinical decision-making support by transforming and modifying medical documents and doctors' state-evaluation-action trees. |
| Outcome: | The proposed framework achieves 1.01% higher than current state-of-the-art (SOTA) baselines across five departments, including common RAG-based methods. |
IndustryAssetEQA: A Neurosymbolic Operational Intelligence System for Embodied Question Answering in Industrial Asset Maintenance (2026.acl-industry)
Copied to clipboard
| Challenge: | Industrial maintenance assistants produce generic explanations that are weakly grounded in telemetry and omit verifiable provenance. |
| Approach: | They propose a neurosymbolic operational intelligence system that combines episode-centric telemetry representations with a Failure Mode and Effects Analysis Knowledge Graph to enable Embodied Question Answering over industrial assets. |
| Outcome: | The proposed system improves structural validity by up to +0.51, counterfactual accuracy by up . to +0.47, and explanation entailment by +0.64, while reducing severe expert-rated overclaims from 28% to 2%. |
Evidence-Driven Reasoning for Industrial Maintenance Using Heterogeneous Data (2026.acl-industry)
Copied to clipboard
Fearghal O’Donncha, Nianjun Zhou, Natalia Martinez, James T Rayfield, Fenno F. Heath III, Abigail Langbridge, Roman Vaculin
| Challenge: | Existing maintenance systems do not support conditional reasoning, argues a new study . large language models (LLMs) offer flexible reasoning, but naively applying generative models introduces risks, he says . |
| Approach: | They propose a maintenance language-based reasoning framework that constrains reasoning through deterministic evidence construction and structured failure knowledge. |
| Outcome: | The proposed framework produces evidence-grounded explanations and advisory actions under heterogeneous data, a study shows . it constrains reasoning through deterministic evidence construction and structured failure knowledge, and applies a rule-based verification loop to suppress unsupported conclusions. |
MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment (2026.acl-industry)
Copied to clipboard
Hanxian Huang, Igor Fedorov, Andrey Gromov, Bernard Beckerman, Naveen Suda, David Eriksson, Maximilian Balandat, Rylan Conway, Patrick Huber, Chinnadhurai Sankar, Ayushi Dalmia, Zechun Liu, Lemeng Wu, Tarek Elgamal, Adithya Sagar, Vikas Chandra, Raghuraman Krishnamoorthi
| Challenge: | MobileLLM-Flash is a family of foundation models for efficient on-device use with strong capabilities. |
| Approach: | They propose a method for designing on-device large language models under mobile latency constraints using hardware-in-the-loop architecture search. |
| Outcome: | The proposed model is amenable to industry-scale deployment and is compatible with mobile runtimes like Executorch. |
LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference (2026.acl-industry)
Copied to clipboard
Shashank Kapadia, Deep Narayan Mishra, Sujal Reddy Alugubelli, Haoan Wang, Saipraveen Vabbilisetty, Rishi Bhatia, Anupriya Sharma
| Challenge: | Layer-aligned distillation and convergence-based early exit are dominant computational efficiency paradigms for transformer inference. |
| Approach: | They propose a training objective that aligns intermediate student layers to teacher representations and reconciles this incompatibility with standard distillation. |
| Outcome: | The proposed model achieves 1.61 measured wall-clock speedup with 91.9% of samples exiting by layer 7 and 1.80 theoretical layer reduction, where standard distilled models achieve zero effective speedup. |
Think Like You Execute: Verifiable Chain of Thought from Program Traces (2026.acl-industry)
Copied to clipboard
Shailja Thakur, Vaibhav Saxena, Rohan Kulkarni, Shivdeep Singh, Parameswaran Selvam, Hiroshi Kanayama, Hima Patel
| Challenge: | Current synthetic Chain-of-Thought (CoT) training data often consists of plausible-sounding explanations generated by teacher models, not verifiable accounts of actual program behavior. |
| Approach: | They propose to ground CoT generation directly in program execution traces to improve reasoning capabilities. |
| Outcome: | The proposed pipeline improves performance on live code benchmarks and on cruxEval-output and cruxeval-input. |
From Relevance to Authority: Authority-aware Generative Retrieval in Web Search Engines (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing methods that optimize for relevance overlook document trustworthiness . Generative information retrieval (GenIR) is a promising paradigm for retrieval tasks . |
| Approach: | They propose an Authority-aware Generative Retriever (AuthGR) that incorporates authority into GenIR. |
| Outcome: | The proposed framework improves authority and accuracy in real-world user engagement and reliability. |
Enhancing Online Recruitment with Category-Aware MoE and LLM-based Data Augmentation (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing methods to measure the matching degree of a job and a candidate face several challenges, such as low-quality job descriptions and similar candidate-job pairs. |
| Approach: | They propose a large language model-based method that polishes and rewrites low-quality job descriptions by leveraging chain-of-thought prompts and category-aware Mixture of Experts (MoE) module incorporates category embeddings to dynamically assign weights to the experts and learns more distinguishable patterns for similar candidate-job pairs. |
| Outcome: | The proposed method surpasses existing methods by 2.40% in AUC and 7.46% in GAUC and boosts click-through conversion rate (CTCVR) by 19.4% in online tests, saving millions of CNY in external headhunting expenses. |
EfficientTool: A Cost-Effective Aligning Framework for Tool-Conditioned Agents in SME Scenarios (2026.acl-industry)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly adopted in downstream industries, yet aligning proprietary agents remains challenging. |
| Approach: | They propose a cost-effective, tool-conditioned alignment framework that forms a closed loop over data collection, iterative training, and deployment-oriented evaluation. |
| Outcome: | The proposed framework effectively aligns model in SME scenarios while preserving general tool-calling capability. |
Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats (2026.acl-industry)
Copied to clipboard
Pengxiang Zhao, Hui-Ling Zhen, Xing Li, Han Bao, Weizhe Lin, Zhiyuan Yang, Yu Zi Wei, Xin Wang, Mingxuan Yuan, Xianzhi Yu, Zhenhua Dong
| Challenge: | Low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency. |
| Approach: | They evaluate HiFloat (HiF8 and HiF4), a family of floating-point formats tailored for Ascend NPUs. |
| Outcome: | The proposed formats excel with high-variance data and are compatible with state-of-the-art quantization frameworks. |
Securing the Tool Layer: A Threat Taxonomy and Runtime Defense Framework for Model Context Protocol Deployments (2026.acl-industry)
Copied to clipboard
| Challenge: | Model Context Protocol (MCP) is the dominant standard for connecting large language models to external tools, databases, and services. |
| Approach: | They propose a runtime security framework that performs real-time validation of MCP tool calls and responses. |
| Outcome: | The proposed framework reduces attack success rates from 74% to under 9% for tool poisoning and from 47% to under6% for indirect prompt injection via tool responses. |
Enhancing Job Evaluation with Data Augmentation and Text Classification (2026.acl-industry)
Copied to clipboard
| Challenge: | Recruiters rely on job titles, role descriptions, and responsibility levels to determine job grades and salary structures. |
| Approach: | They propose to semi-automate job evaluation by fine-tuning a RoBERTa model for classification and using Gemini to generate synthetic job descriptions for rare job titles. |
| Outcome: | The proposed method improves job evaluation by boosting consistency and speeding up workflows. |
When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation (2026.acl-industry)
Copied to clipboard
Lin Sun, null Wangdexian, Jingang Huang, Linglin Zhang, Change Jia, Zhengwei Cheng, Xiangzheng Zhang
| Challenge: | Existing OCR benchmarks rely on character-level metrics to measure downstream performance . high OCR accuracy does not translate into strong downstream performance, authors say . |
| Approach: | They propose an OCR benchmark for industrial RAG systems that measures character-level metrics . they find that high OCR accuracy does not translate into strong downstream RAG performance . |
| Outcome: | The proposed benchmark shows that high OCR accuracy does not translate into strong downstream performance . structural and semantic errors can cause substantial retrieval failures even when WER/CER remains low. |
Aggregate vs. Personalized Judges in Business Idea Evaluation: Evidence from Expert Disagreement (2026.acl-industry)
Copied to clipboard
Wataru Hirota, Tomoki Taniguchi, Tomoko Ohkuma, Kosuke Takahashi, Takahiro Omi, Kosuke Arima, Takuto Asakura, Chung-Chi Chen, Tatsuya Ishigaki
| Challenge: | Large language models (LLMs) make it easy to generate large numbers of product ideas. |
| Approach: | They propose to use a dataset of 3,000 individual scores across 300 patent-grounded product ideas to assess whether an automatic judge approximates an aggregate consensus. |
| Outcome: | The proposed model evaluators disagree on fine-grained ordinal scores, suggesting structured heterogeneity rather than random noise. |
Memory-Efficient Structured Backpropagation for On-Device LLM Fine-Tuning (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing approaches for fine-tuning large language models require a trade-off between exact gradients with high memory and low memory with noisy estimates (MeZO). |
| Approach: | They propose a method which derivates gradients from LoRA's low-rank structure and manually deriving backward passes to exploit the low-level structure. |
| Outcome: | The proposed method reduces peak memory from 361MB to 136MB for Qwen2.5-0.5B, enabling fine-tuning scenarios previously infeasible on memory-constrained devices. |
Multi-Agent Orchestration for Terminology-Constrained Machine Translation in Industrial Localization (2026.acl-industry)
Copied to clipboard
| Challenge: | Accurate terminology is a non-negotiable requirement in industrial localization processes. |
| Approach: | They propose a multi-agent LLM pipeline that orchestrates four specialized agents for terminology-constrained machine translation. |
| Outcome: | The proposed system achieves 99.4% average accuracy while outperforming other systems on the WMT25 Terminology Translation benchmark. |
TrendPulse: A Simple yet Efficient Framework for Capturing Viral E-Commerce Spikes via LLM-Driven Contextualization (2026.acl-industry)
Copied to clipboard
| Challenge: | Modern e-commerce platforms mostly depend on reactive discovery, where products surface only after users search for them. |
| Approach: | They propose a framework that identifies regional search momentum and leverages Large Language Model to transform spikes into semantic trends. |
| Outcome: | The proposed framework shows consistent improvements across multiple business metrics and overall user experience. |
ACRM: Multi-Agent Trajectory Learning for Automated Credit Risk Model Refreshing in Production (2026.acl-industry)
Copied to clipboard
Liangzu Liu, Mengzhe Ruan, Xiaotian Chen, null HaonanChen, null XudongNiu, Wendi Yuan, null YuechenLi, Yang Liu, Guanjun Wang
| Challenge: | Credit risk models suffer from rapid performance decay due to distribution shifts, requiring frequent updates to meet strict operational guardrails. |
| Approach: | They propose a multi-agent framework that treats model refreshing as a learnable trajectory of agent interactions. |
| Outcome: | The proposed framework reduces the average model refresh cycle from weeks to 1.1 days and iteration rounds by 65% while maintaining superior stability metrics. |
From 2:4 to 8:16 sparsity patterns in LLMs for Outliers and Weights with Variance Correction (2026.acl-industry)
Copied to clipboard
Egor Maximov, Yulia Kuzkina, Egor Shvetsov, Azamat Kanametov, Aleksandr Prutko, Maxim Zhelnin, Aleksei Goncharov
| Challenge: | Quantization and sparsification are important for large language models, but they struggle to meet performance thresholds due to limited flexibility and sensitivity to outlier weights. |
| Approach: | They propose to use 8:16 semi-structured sparsity to surpass performance thresholds . they also show that structured sparsification for outliers is competitive with unstructured approaches . |
| Outcome: | The proposed method surpasses the Performance Threshold, compared to 2:4 sparsity, and offers greater flexibility with minimal storage overhead. |
An Efficient Framework for Whole-Page Reranking via Single-Modal Supervision (2026.acl-industry)
Copied to clipboard
Zishuai Zhang, Sihao Yu, null Xiewenyi, Ying Nie, Junfeng Wang, Zhiming Zheng, Dawei Yin, Hainan Zhang
| Challenge: | Existing whole-page reranking methods require large-scale expert annotations to achieve high-quality results. |
| Approach: | They propose a whole-page reranking framework that converts single-modal rankers into page-level guidance by constructing budget-aware candidates for cross-modal annotations and distilling intra-modality preferences to align relevance scales across modalities. |
| Outcome: | The proposed framework reduces annotation costs by 70-90% while outperforming fully-annotated reranking baselines. |
LLM as a Risk Manager: LLM Semantic Filtering for Lead–Lag Trading in Prediction Markets (2026.acl-industry)
Copied to clipboard
Sumin Kim, Minjae Kim, Jihoon Kwon, Yoon Kim, Oscar Levy, Alejandro Lopez-Lira, Yongjae Lee, Chanyeol Choi
| Challenge: | Prediction markets provide a unique setting where event-level time series are directly tied to natural-language descriptions, yet discovering robust lead–lag relationships remains challenging due to spurious statistical correlations. |
| Approach: | They propose a statistical stage that uses Granger causality to identify candidate leader–follower pairs from market-implied probability time series and an LLM-based semantic stage that re-ranks these candidates by assessing whether the proposed direction admits a plausible economic transmission mechanism. |
| Outcome: | The proposed approach consistently outperforms the statistical baseline on Kalshi Economics markets. |
Diffusion-Pretrained Dense and Contextual Embeddings (2026.acl-industry)
Copied to clipboard
| Challenge: | pplx-embed uses diffusion-based pretraining to capture bidirectional context within passages. |
| Approach: | They propose a family of multilingual embedding models that leverage bidirectional attention through diffusion-based pretraining to capture bidirectional context within passages. |
| Outcome: | The proposed models achieve competitive performance on the MTEB(Multilingual, v2), MTEF(Code), BERGEN, and ToolRet retrieval benchmarks while pplx-embed-context-v1 sets new records on the ConTEB benchmark. |
Actionable Interpretability for Churn Classification: A Text Bottleneck Model Case Study at a Major Telecom Provider (2026.acl-industry)
Copied to clipboard
| Challenge: | Managing customer churn is vital for subscription-based businesses . large language models (LLMs) can automate the classification of chursn-intent at scale . lack of transparency forces a difficult choice between automated systems and manual review . |
| Approach: | They propose to use text bottleneck models to classify customer churn in subscription-based businesses . they show that the model can be used to bridge the perceived trade-off between interpretability andpredictive performance . |
| Outcome: | The proposed model performs competitively with black-box baselines and an interactive dashboard. |
Decoding Text Spans for Efficient and Accurate Named-Entity Recognition (2026.acl-industry)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is a key component in industrial information extraction pipelines, where systems must satisfy strict latency and throughput constraints in addition to strong accuracy. |
| Approach: | They propose a span-based NER framework that can be used to compute span representations at the final transformer stage, avoiding redundant computation in earlier layers. |
| Outcome: | The proposed framework matches competitive baselines while improving throughput and reducing computational cost. |
EVE: A Domain-Specific LLM Framework for Earth Intelligence (2026.acl-industry)
Copied to clipboard
Àlex R. Atrio, Antonio Lopez, Jino Rohit, Yassine El Ouahidi, Marcello Politi, Vijayasri Iyer, Umar Jamil, Sébastien Bratières, Nicolas Longépé
| Challenge: | Earth Virtual Expert (EVE) is the first open-source, end-to-end initiative for developing and deploying domain-specialized LLMs for Earth Intelligence. |
| Approach: | They introduce Earth Virtual Expert, an open-source initiative for developing and deploying domain-specialized LLMs for Earth Intelligence. |
| Outcome: | The proposed model outperforms existing models on Earth Observation and Earth Sciences benchmarks while maintaining general capabilities. |
Hemolix.TabGen: Optimized Table Generation from Documents (2026.acl-industry)
Copied to clipboard
| Challenge: | Modern Data Lakes contain vast and heterogeneous document collections, making table generation difficult. |
| Approach: | They propose a scalable LLM-based table generation system that comprehends documents and generates Bi-dimensional tables based on the entire document content. |
| Outcome: | The proposed system generates bi-dimensional tables from documents across multiple domains. |
Harmonizing Dense and Sparse Signals in Multi-turn RL: Dual-Horizon Credit Assignment for Industrial Sales Agents (2026.acl-industry)
Copied to clipboard
| Challenge: | Large language models for industrial sales require balancing long-term commercial objectives with immediate linguistic constraints such as fluency and compliance. |
| Approach: | They propose a framework that disentangles optimization across time scales by normalizing advantages from turn-level and session-level rewards before fusion. |
| Outcome: | The proposed framework outperforms the state-of-the-art GRPO model in conversion rate and identity detection rate. |
Know What You See: Grounded localization of product components (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing object detectors treat components as isolated objects, ignoring their structure . a new method, Know What You See, uses textual knowledge to localize components . |
| Approach: | a new method localizes components by grounding them using a textual knowledge base . KWYS improves component localization accuracy by 11% and reduces component hallucinations by 25% . |
| Outcome: | a new method improves component localization accuracy and reduces component hallucinations . the proposed method improve on 1,000 product images across 5 diverse categories . |
SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs (2026.acl-industry)
Copied to clipboard
Prateek Chaturvedi, Yuqicheng Zhu, Hongkuan Zhou, Dongzhuoran Zhou, Yunjie He, Steffen Staab, Fei Du, Jie Tang, Evgeny Kharlamov
| Challenge: | Existing agentic approaches for Knowledge Graph-based Retrieval-Augmented Generation fail to generalize to real-world enterprise Knowledge graphs (KGs) dense, schema-driven, and operationally constrained, requiring a training-free framework. |
| Approach: | They propose a training-free framework that integrates structured planning with controlled iterative reasoning by injecting schema-conditioned structural priors and enforcing schemas during multi-hop reasoning. |
| Outcome: | The proposed framework significantly improves on a real-world enterprise-oriented benchmark constructed from a Configuration Management DataBase (CMDB). |
FROST: Factual Reasoning via Optimized Stochastic Trajectories in Large Language Models during Inference (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing mitigation strategies are needed to improve large language models' reliability and efficiency. |
| Approach: | They propose an inference-time framework that balances exploration andexploitation without additional training or context augmentation. |
| Outcome: | FROST achieves 2–5 percentage point improvements over standard chain-of-thoughtprompting and reduces unsupported outputs by 40% relative to Standard CoT. |
SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction (2026.acl-industry)
Copied to clipboard
| Challenge: | Structured information extraction (IE) pairs values from unstructured text with schema-defined keys. |
| Approach: | They propose a retrieval-augmented generation framework that prunes the output schema space for schema-conditioned information extraction tasks by leveraging schema metadata and few-shot examples. |
| Outcome: | The proposed framework can achieve up to 8.8% increase in micro-F1, 47% reduction in latency, and 48% reduction in token costs on real-world healthcare and e-commerce datasets. |
DQA: Diagnostic Question Answering for IT Support (2026.acl-industry)
Copied to clipboard
Vishaal Kapoor, Mariam Dundua, Evren Yortucboylu, Sarthak Ahuja, Neda Kordjazi, Yiming Li, Vaibhavi padala, Derek Ho, Jennifer Whitted, Rebecca Steinert
| Challenge: | a diagnostic question-answering framework maintains persistent diagnostic state and aggregates retrieved cases at the level of root causes rather than individual documents. |
| Approach: | They propose a diagnostic question-answering framework that maintains persistent diagnostic state . it aggregates retrieved cases at the level of root causes rather than individual documents . |
| Outcome: | The framework achieves a 78.7% success rate under trajectory-level success criterion compared to a multi-turn RAG baseline . the framework reduces average turns from 8.4 to 3.9, compared with a single-turn baseline crim. |
Agentic Economic Modeling (2026.acl-industry)
Copied to clipboard
| Challenge: | AEM is a framework that aligns synthetic LLM choices with small-sample human evidence for reliable econometric inference. |
| Approach: | They introduce a framework that aligns synthetic LLM choices with small-sample human evidence for reliable econometric inference. |
| Outcome: | The proposed framework improves RCT efficiency and establishes a foundation method for LLM-based counterfactual generation. |
Robust Explanations for User Trust in Enterprise NLP Systems (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing studies on explanation stability under real user noise are limited . decoder LLMs produce significantly more stable explanations than encoder baselines . |
| Approach: | They propose a black-box robustness evaluation framework for token-level explanations based on leave-one-out occlusion . they propose to operationalize explanation robustness with top-token flip rate under realistic perturbations at multiple severity levels . |
| Outcome: | The proposed framework is compared with baseline models and encoder and decoder families. |
VEG: Verbal 𝜖-greedy for Semantic Exploration in Multi-Turn RL Agents (2026.acl-industry)
Copied to clipboard
Yongchang Hao, Jie Hao, Yongsheng Mei, Ze Ye, Junyi Chai, Bin Guo, Benjamin Z. Yao, Chenlei Guo, Lili Mou
| Challenge: | Standard RL approaches suffer from reward sparsity and mode-seeking behavior . lack of diversity hinders exploration necessary for optimal learning . |
| Approach: | They propose a framework that leverages external feedback as a dynamic control variable to explicitly balance exploration and exploitation within the semantic space. |
| Outcome: | Experiments on Tau Bench and SearchQA show that the proposed framework outperforms standard RL baselines. |
FlowHN: Adaptive Token Routing for Efficient Parallel Hybrid Networks (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing hybrids lack performance, latency, and cost-efficient scaling for production LLMs. |
| Approach: | They propose a deployment-oriented parallel hybrid architecture that enables deterministic conditional computation via FLOP-aware token circulation across attention and SSM branches. |
| Outcome: | FlowHN achieves 4 higher throughput and 15% higher MFU than current models while maintaining competitive accuracy on reasoning, coding, and long-context tasks. |
MemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detection (2026.acl-industry)
Copied to clipboard
| Challenge: | Traditional phishing website detection relies on static heuristics or reference lists, which lag behind rapidly evolving attacks. |
| Approach: | They propose a memory-augmented multi-modal LLM agent that leverages episodic memories to guide decisions on recurring and novel threats. |
| Outcome: | The proposed agent outperforms state-of-the-art phishing detection tools on two public datasets and improves recall by 20%. |
Adaptive Weighted Proxy Tuning: Efficient Gray-Box Steering for Image Captioning. (2026.acl-industry)
Copied to clipboard
| Challenge: | Proxy tuning is a decoding-time approach that fails to account for instance-specific variations in model certainty and domain shift. |
| Approach: | They propose a gray-box steering framework that dynamically modulates the logit contributions of a large base model, a fine-tuned expert, and an untune . |
| Outcome: | Adaptive Weighted Proxy Tuning achieves performance parity with fine-tuned models while remaining parameter-free. |
CLARITY: A Framework and Benchmark for Conversational Language Ambiguity and Unanswerability in Interactive NL2SQL Systems (2026.acl-industry)
Copied to clipboard
Tabinda Sarwar, Farhad Moghimifar, Cong Duy Vu Hoang, Xiaoxiao Ma, Shawn Chang Xu, Fahimeh Saleh, Poorya Zaremoodi, Avirup Sil, Katrin Kirchhoff
| Challenge: | Existing benchmarks assume a single source of ambiguity and rely on user interaction for resolution, overlooking realistic failure modes. |
| Approach: | They propose a framework for automatically generating an NL2SQL benchmark with multi-faceted ambiguities and diverse user behaviors. |
| Outcome: | The proposed framework transforms executable SQL into ambiguous queries with a conversational continuation and schema-level metadata. |
Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents (2026.acl-industry)
Copied to clipboard
Yun-Shiuan Chuang, Chaitanya Kulkarni, Alec M. Chiu, Avinash Thangali, Zijie Pan, Shivani Shekhar, Yirou Ge, Yixi Li, Uma Kona, Linsey Pang, Prakhar Mehrotra
| Challenge: | Existing agentic benchmarks rely on deterministic backends and are costly to build and iterate. |
| Approach: | They propose a framework that preserves final state-based evaluation without a deterministic database. |
| Outcome: | The proposed framework produces stable, model-differentiating rankings across families and inference-time reasoning efforts. |
Ada-RS: Adaptive Rejection Sampling for Selective Thinking (2026.acl-industry)
Copied to clipboard
Yirou Ge, Yixi Li, Alec M. Chiu, Shivani Shekhar, Zijie Pan, Avinash Thangali, Yun-Shiuan Chuang, Chaitanya Kulkarni, Uma Kona, Linsey Pang, Prakhar Mehrotra
| Challenge: | Large language models are increasingly being deployed in cost- and latency-sensitive settings . chain-of-thought improves reasoning, but it can waste tokens on simple requests . |
| Approach: | They introduce an algorithm-agnostic sample filtering framework for learning selective reasoning . they show that Ada-RS reduces average output tokens by 80% and reducing thinking rate by 5% . |
| Outcome: | The proposed framework reduces output tokens by 80% and thinking rate by 95% on a synthetic tool call-oriented e-commerce benchmark. |
IPS: In-Prompt Process Supervision for Short Video Content Moderation (2026.acl-industry)
Copied to clipboard
| Challenge: | Multimodal large language models (MLLMs) capture semantics of short video content but fail to account for policy-specific details. |
| Approach: | They propose a framework that integrates In-prompt Process Supervision into MLLMs . they propose sequential reasoning over ancillary questions during fine-tuning . |
| Outcome: | IPS outperforms baseline MLLMs on public and proprietary benchmarks . replacing human-annotated ancillary labels with MLML-generated ones results in performance degradation. |
RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking Services (2026.acl-industry)
Copied to clipboard
Fei zhao, Chonggang Lu, Haofu Qian, Fangcheng Shi, Zijie Meng, Jianzhao Huang, Zheyong Xie, Shaosheng Cao
| Challenge: | Social networking services (SNS) are critical infrastructure for global interaction . supervised fine-tuning (SFT) can improve in-domain performance, but it often induces a ”seesaw” trade-off with out-of-domain robustness . |
| Approach: | They propose an SNS-oriented LLM with a progressive, RL-prioritized post-training paradigm for fast and stable adaptation. |
| Outcome: | The proposed model improves over the previous 7B model by 2.41 on average . it also yields an 8.74 average gain over its Qwen3-4B base . |
How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel (2026.acl-industry)
Copied to clipboard
| Challenge: | Traditional industrial agents rely on modular workflows that fracture into a labyrinth of ad-hoc patches, leading to cascading errors and high latency. |
| Approach: | They propose a paradigm shift from external workflows to internalized knowledge representation that consolidates complex business logic and SOPs directly into the model’s parameters. |
| Outcome: | The proposed model breaks the impossible triangle of latency, accuracy, and complexity. |
FinRAG-12B: A Production-Validated Recipe for Grounded Question Answering in Banking (2026.acl-industry)
Copied to clipboard
| Challenge: | Large language models (LLMs) are rapidly being adopted across various domains, but adoption in the regulated banking industry is limited due to their tendency to hallucinate, exhibit over-agreeable behavior, and lack alignment with domain-specific knowledge and constraints. |
| Approach: | They propose a framework for training grounded domain-specific LLMs that optimizes answer quality, citation grounding, and calibrated refusal under real-world deployment constraints. |
| Outcome: | The proposed model outperforms GPT-4.1 on citation grounding and calibrated refusal under real-world deployment constraints. |
CascadeDebate: Multi-Agent Deliberation for Cost-Aware LLM Cascades (2026.acl-industry)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable proficiency across diverse benchmarks, spanning scientific question answering to medical diagnosis tasks. |
| Approach: | They propose to insert multi-agent deliberation directly at each tier’s escalation boundary to enable consensus-driven resolution of ambiguities internally without invoking higher-cost upgrades. |
| Outcome: | The proposed architecture outperforms strong single-model cascades and standalone multi-agent systems across five benchmarks spanning science, medicine, and general knowledge by up to 26.75%. |
SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing methods struggle with semantic ambiguity, homonyms, and complex linguistic structures, often trading accuracy for efficiency. |
| Approach: | They propose a Vietnamese fact-checking framework that integrates SER and TVC to achieve 78.97% strict accuracy. |
| Outcome: | The proposed framework achieves state-of-the-art accuracy with 78.97% strict accuracy on ISE-DSC01 and 80.82% on ViWikiFC while maintaining competitive accuracy. |
SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection (2026.acl-industry)
Copied to clipboard
Zhiyong Cao, Dunqiang Liu, Qi Dai, Haojun Xu, Huai Yuen Khor, Hao Wang, Huan He, Yafei Liu, Ke Ma, Ruqian Shi, Sicheng Zhou, Sijia Yao
| Challenge: | High-quality data in training proactive dialogue agents is scarce, despite fine-tuning and reinforcement learning . a recent study has shown that the effectiveness of supervised fine-touring is limited by the lack of high-quality, domain-specific training data. |
| Approach: | They propose a framework for training recruitment proactive dialogue agents using a high-fidelity user simulator and a multi-dimensional evaluation framework based on Chain-of-Intention. |
| Outcome: | The proposed framework outperforms existing simulator-based data selection strategies in a real-world recruitment scenario. |
ProductResearch: Training E-Commerce Deep Research Agents via Multi-Agent Synthetic Trajectory Distillation (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing LLM-based agents lack the interaction depth and contextual breadth required for complex product research. |
| Approach: | They propose a multi-agent framework that synthesizes high-fidelity tool-use trajectories for training robust e-commerce shopping agents. |
| Outcome: | The proposed framework synthesizes high-fidelity, long-horizon tool-use trajectories for training robust e-commerce shopping agents. |
ReList: A Multi-objective Reasoning Framework for Diversified Listwise Query Recommendation (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing methods for related search have limited semantic redundancy and wasted retrieval quota . generative retrieval approaches lack explicit reasoning, relying on superficial click-through rate rewards . |
| Approach: | They propose a framework that transforms related search into a reasoning-enhanced listwise generation task. |
| Outcome: | Experimental results show that ReList outperforms state-of-the-art methods in query diversity and user engagement. |
Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design (2026.acl-industry)
Copied to clipboard
| Challenge: | a novel extension of neural scaling laws to Mixture-of-Experts models is proposed . a ratio of expert-attention compute is crucial for efficient MoE models . |
| Approach: | They propose an extension of neural scaling laws to Mixture-of-Experts (MoE) models . they define the ratio r as the fraction of total FLOPs per token dedicated to expert and attention layers . |
| Outcome: | The proposed model can be tuned beyond size and data with the proposed model. |
A Multistage Extraction Pipeline for Long Scanned Financial Documents: An Empirical Study in Industrial KYC Workflows (2026.acl-industry)
Copied to clipboard
| Challenge: | Structured information extraction from long, multilingual scanned financial documents is a core requirement in industrial KYC and compliance workflows. |
| Approach: | They propose a framework for structured information extraction from long, multilingual scanned financial documents . they combine image preprocessing, multilinguistic OCR, hybrid page-level retrieval and VLMs . |
| Outcome: | The proposed pipeline outperforms direct PDF-to-VLM baselines on 120 production KYC documents. |
Effective Performance Measurement: Challenges and Opportunities in KPI Extraction from Earnings Calls (2026.acl-industry)
Copied to clipboard
Rasmus T. Aavang, Rasmus Tjalk-Bøggild, Alexandre Iolov, Giovanni Rizzi, Mike Zhang, Johannes Bjerva
| Challenge: | Earnings calls are a key source of financial information about public companies. extracting information from earnings calls is difficult. |
| Approach: | They propose to use LLMs to perform open-ended extraction from unstructured call transcripts to provide a baseline for this valuable domain through the consistent tracking of emergent KPIs. |
| Outcome: | The proposed method provides a baseline for this valuable domain through the consistent tracking of emergent KPIs. |
Structure-Guided Entity Resolution: Fine-Tuning LLMs for Robust Name Matching in Complex Linguistic Contexts (2026.acl-industry)
Copied to clipboard
| Challenge: | Variations in naming conventions, inconsistent transliteration across scripts, and frequent data entry errors make it difficult to unify user identities, an essential requirement for Know Your Customer (KYC) compliance. |
| Approach: | They propose a framework that fine-tunes an LLM through a two-phase curriculum to match person names across heterogeneous records. |
| Outcome: | The proposed framework outperforms GPT-4o and single-stage fine-tuning baselines in the Indian identity data. |
Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal Adjudication (2026.acl-industry)
Copied to clipboard
| Challenge: | Legal texts contain computational legal clauses that exceed the semantic complexity of the realworld activities they govern. |
| Approach: | They propose a neuro-symbolic approach to legal adjudication using an LLM . they use a typed graph intermediate representation to translate a legal text into a deterministic contract language . |
| Outcome: | The proposed system reduces compute costs by over 90% in high-volume workflows while satisfying auditability requirements. |
CI-Work: Benchmarking Contextual Integrity in Enterprise LLM Agents (2026.acl-industry)
Copied to clipboard
Wenjie Fu, Xiaoting Qin, Jue Zhang, Qingwei Lin, Lukas Wutschitz, Robert Sim, Saravan Rajmohan, Dongmei Zhang
| Challenge: | Enterprise LLM agents can dramatically improve workplace productivity, but their core capability, retrieving and using internal context to act on a user’s behalf, also creates new risks for sensitive information leakage. |
| Approach: | They propose a Contextual Integrity-grounded benchmark that simulates enterprise workflows across five information-flow directions and evaluates whether agents can convey *essential* content while withholding *sensitive* context in dense retrieval settings. |
| Outcome: | The proposed model demonstrates that privacy failures are prevalent in enterprise workflows and that higher task utility correlates with increased privacy violations. |
From Pixels to Policies: Reinforcing Spatial Reasoning in Language Models for Content-Aware Layout Design (2026.acl-industry)
Copied to clipboard
| Challenge: | LaySPA equips large language models (LLMs) with explicit and interpretable spatial reasoning for content-aware graphic layout design. |
| Approach: | They propose a reinforcement learning framework that equips large language models (LLMs) with explicit spatial reasoning for content-aware graphic layout design. |
| Outcome: | Experiments show that LaySPA outperforms larger LLMs in structural validity and visual quality while requiring fewer annotated samples. |
Practical Guidelines for Model Merging in LLMs Pre-Training (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing studies on model merging have focused on stable learning rate regimes, but its effectiveness during LLM pre-training remains underexplored. |
| Approach: | They systematically investigate model merging across training phases, focusing on the transition from stable to decaying learning rates. |
| Outcome: | The proposed methods improve performance during stable learning rate regimes but diminish under decay, a phe-nomenon that is linked to reduced checkpoint diversity and lower parameter-space variability. |
Are Large Language Models Economically Viable for Industry Deployment? (2026.acl-industry)
Copied to clipboard
Abdullah Mohammad, Sushant Kumar Ray, Pushkar Arora, Rafiq Ali, Ebad Shabbir, Gautam Siddharth Kashyap, Jiechao Gao, Usman Naseem
| Challenge: | Generative AI is increasingly deployed in healthcare, financial analytics, and conversational automation. |
| Approach: | They propose a framework that evaluates large language models across their full lifecycle on legacy GPUs. |
| Outcome: | The proposed framework evaluates LLMs across their full lifecycle on legacy GPUs. |
Let LLM Tutors Ask First: Proactive LLM-Based Tutoring at Scale in a 1,500-Student Online Classroom (2026.acl-industry)
Copied to clipboard
| Challenge: | Large-scale introductory CS courses struggle to provide personalized support and encourage active participation. |
| Approach: | They propose to use predictive query management to generate student questions and answers ahead of lectures and to engage in interactive conversations with a tutoring model. |
| Outcome: | The proposed learning assistant generates student questions and answers ahead of lectures and interacts with students via the same interface. |
Hierarchical Reason-of-Contact Detection in Retail Banking Customer Interactions via LLM-Driven Taxonomy Induction (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing approaches to define customer intents or contact reasons are fragmented and manual . existing systems fail to capture the linguistic diversity of thousands of daily callers . |
| Approach: | They propose a framework that develops a hierarchical Reason-of-Contact taxonomy . it covers hundreds of business processes and can be deployed in real time . |
| Outcome: | The proposed framework achieves 10% improvement in F1 score over baseline approaches on a reference dataset. |
Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA (2026.acl-industry)
Copied to clipboard
Ummar Abbas, Mourad Ouzzani, Mohamed Y. Eltabakh, Omar Sinan, Gagan Bhatia, Hamdy Mubarak, Majd Hawasly, Mohammed Qusay Hashim, Kareem Mohamed Darwish, Firoj Alam
| Challenge: | Large language models (LLMs) can answer religious knowledge queries fluently, but they often hallucinate and misattribute sources. |
| Approach: | They propose a bilingual Arabic-English Islamic QA system that uses a multi-agent, tool-augmented architecture to route Islamic queries to specialized modules. |
| Outcome: | The proposed system is based on a multi-agent, tool-augmented architecture and has received over 1.9M accesses in less than a year. |
GuideTree: Guideline-Induced Review Trees for Long Medical Records (2026.acl-industry)
Copied to clipboard
| Challenge: | Medical record reviewers must produce consistent, traceable, guideline-compliant outcomes . longcontext inference is expensive and often degrades as inputs grow . |
| Approach: | a new method compiles textual guidelines into a fixed review tree . a cost-aware split-and-prune search is used to update the tree offline . the algorithm produces consistent, traceable, guideline-compliant outcomes . |
| Outcome: | The proposed system outperforms the strongest non-expert baselines by 84.5–92.8 Macro-F1 . it reduces average I/O volume to 74K input+output characters and average latency to 22s . |
Automatic Prompt Engineering for Scalable Prompt Inversion in Text-to-Image Ad Generation (2026.acl-industry)
Copied to clipboard
| Challenge: | PRISM-DUEL is a black-box framework that formalizes prompt optimization as Automatic Prompt Engineering (APE) PRIMS-DUEl is motivated by advertising workflows requiring low-latency, diverse variants faithful to a human-designed ad. |
| Approach: | They propose a black-box framework that formalizes prompt optimization as Automatic Prompt Engineering (APE) they obtain label-free pairwise preferences and rationales from an LLM judge over pairs of generated images and use a dueling-bandit optimizer to optimize a prompt for generating controlled variations while matching the reference ad's visual content. |
| Outcome: | The proposed framework preserves visual similarity and semantic faithfulness while increasing diversity. |
Efficient Agent Evaluation via Diversity-Guided User Simulation (2026.acl-industry)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly deployed as customer-facing agents due to stochastic, multi-turn interactions. |
| Approach: | They propose a snapshot-based, coverage-guided user simulation framework for efficient and systematic exploration of multi-turn agent behavior. |
| Outcome: | Experiments on multi-domain benchmarks show that the proposed method improves failure discovery efficiency and task-level coverage compared to standard linear rollout evaluation without increasing overall cost. |
What Question Did You Answer? Refining Contact Center Evaluation Plans via Backward Questions (2026.acl-industry)
Copied to clipboard
| Challenge: | Recent advances in large Language Models (LMs) offer unprecedented potential for automating QA evaluations . however, capturing organization-specific domain knowledge remains a challenge for cost-efficient language models . |
| Approach: | They propose a diagnostic framework that generates backward questions to distill implicit reasoning from large LMs into explicit evaluation plans. |
| Outcome: | The proposed framework achieves performance improvements on 8 QA questions with gains of 27.8% in Macro F1. |
Natural-Language Policies to Executable Decisions: An Interpretable Large Language Model Framework (2026.acl-industry)
Copied to clipboard
Ziqiang Zhang, Jing Ma, Zilong Wang, Jiayuan Chen, Yi Qiao, Yu He, Wei Zhang, Dai Cheng, Xiaoyu Shen
| Challenge: | a production-grade pricing system for tourism is challenging due to unstructured nature of travel orders and ever-evolving pricing policies. |
| Approach: | They propose a production-grade pricing system with a strict decision boundary . they propose to combine structured extraction and bounded policy/path selection with interpretable condition trees . |
| Outcome: | The proposed system processed 3,960 orders in six months and reduced the order management team from 15-20 to 3 . the system reduced the per-order handling time from 10 minutes to 2 minutes. |
Diagnose, Then Repair: A Two-Stage MQM-Guided Post-Editing Framework for Domain-Specific Machine Translation (2026.acl-industry)
Copied to clipboard
| Challenge: | In practice, LLMs are largely diagnostic, with the signals rarely translating into direct quality improvements under real production constraints. |
| Approach: | They propose a two-stage, evaluator-guided automatic post-editing framework that turns MQM-style evaluation into targeted repairs. |
| Outcome: | The proposed framework improves both COMET and CometKiwi scores over one-stage evaluation methods while severities and error spans show strong agreement with human annotations and human editor preferences. |
Don’t Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination (2026.acl-industry)
Copied to clipboard
Prafulla Kumar Choubey, Kung-Hsiang Huang, Pranav Narayanan Venkit, Jiaxin Zhang, Vaibhav Vats, Yu Li, Xiangyu Peng, Chien-Sheng Wu
| Challenge: | Enterprise deep research systems fail to produce decision-ready reports due to uneven information coverage, context explosion, and premature stopping. |
| Approach: | They propose a scalable Enterprise Deep Research (EDR) architecture that decomposes requests into coverage-driven objectives via outline generation with reflection and localizes context with dependency-guided execution and explicit information sharing. |
| Outcome: | The proposed system achieves the strongest overall performance compared with competitive deep-research baselines on internal sales enablement tasks and the public DeepResearch Bench benchmark. |
FinHarmBench: Financial Jailbreak Benchmark and Unsupervised Safety Fine-Tuning via Refusal Steering Distillation (2026.acl-industry)
Copied to clipboard
Yubin Choi, Yujin Yang, Subin Kim, Seokil Ham, Seungju Cho, Jungmin Son, Youngjun Kwak, Changick Kim
| Challenge: | Existing safety benchmarks focus on general harms and lack the granularity needed to capture domain-specific financial threats. |
| Approach: | They propose a benchmark to evaluate financially harmful and confusable benign prompts. |
| Outcome: | The proposed framework improves refusal behavior without annotating refusal responses. |
PAR2-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering (2026.acl-industry)
Copied to clipboard
| Challenge: | Multi-hop question answering is a practical bottleneck in industry applications . large language models (LLMs) fail frequently when evidence coverage is incomplete or reasoning trajectories drift . |
| Approach: | They propose a training-free two-stage framework that separates coverage from commitment . it performs breadth-first anchoring to build a high-recall evidence frontier . compared with IRCoT, it achieves 23.5% higher answer accuracy . |
| Outcome: | The proposed framework outperforms strong baselines in MHQA benchmarks and achieves 23.5% higher answer accuracy and 10.5% NDCG gains in retrieval quality. |
OmniOData: Unleashing Small Language Models for OData Query Generation with Synthetic Data and Reinforcement Learning (2026.acl-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been used for structured query generation but lack high-fidelity, execution-validated datasets. |
| Approach: | They propose a framework that generates SynOData, the first large-scale OData corpus featuring execution-grounded queries and reasoning traces. |
| Outcome: | The proposed model matches or surpasses proprietary systems on industrial benchmarks. |
LegalDrill: Diagnosis-Driven Synthesis for Legal Reasoning in Small Language Models (2026.acl-industry)
Copied to clipboard
Tianchun Li, Haochen Liu, Vishwa Pardeshi, Xingchen Wang, Tianci Liu, Huijun Zhao, Wei Fan, Jing Gao
| Challenge: | Small language models (SLMs) are promising for real-world deployment but struggle with high-stakes legal reasoning tasks. |
| Approach: | They propose a diagnostic-driven synthesis framework that extracts and refines reasoning trajectories from a capable teacher via fine-grained prompting and a self-reflective verification is employed to adaptively select the most effective data for the SLM student. |
| Outcome: | The proposed framework extracts and refines reasoning trajectories from a capable teacher via fine-grained prompting, then a self-reflective verification is employed to adaptively select the most effective data for the student. |
From TextBlob to LLM Agents: Sentiment Model Selection for B2B Technical Support with CSAT Ground Truth (2026.acl-industry)
Copied to clipboard
| Challenge: | a dedicated single-task LLM agent reduces neutral bias from 69% to 22%, improving MCC from -0.018 to 0.347 . only 4.88% of tickets receive negative satisfaction ratings . |
| Approach: | They evaluate sentiment models for customer satisfaction prediction in B2B technical support . they use a complete population of CSAT-rated tickets from 100+ organizations . |
| Outcome: | The proposed model performs better than the most expensive model, with a lower neutrality and lower recall than the budget model. |
A Novel Matching Paradigm: Unified Generative and Discriminative LLM with Prompt Compression for Relevance Learning (2026.acl-industry)
Copied to clipboard
Guoliang Zhao, Zixin Cui, Chao Ye, Dengwu He, Fei Huang, Yubo Liu, Shuanglong Li, Tzungren Kuo, Bin Ding, Shuang Zhang, null KunhongZhu, Zhi Guo, Liu Lin
| Challenge: | Existing approaches to matching use Large Language Models as feature extractors, underutilizing their full modeling capabilities. |
| Approach: | They propose a matching paradigm that integrates two-tower, single-towing, and generative tasks within a unified LLM framework via attention-mask partitioning. |
| Outcome: | The proposed model achieves superior performance and strong practical value in an industrial search engine. |
Rethinking Scale: Deployment Trade-offs of Small Language Models under Agent Paradigms (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing research focuses on enhancing large language models through scaling laws or fine-tuning strategies, but ignores the potential of using agent paradigms to compensate for the inherent weaknesses of small models. |
| Approach: | They propose to use structured agent frameworks to improve effectiveness over direct prompting . they also propose to employ routing-based multi-agent systems with collaborative capabilities . |
| Outcome: | The proposed model significantly outperforms direct prompting with single-agent systems . the proposed model is more reliable and cost-effective than other models . |
FourCorners: A Production Knowledge Graph Unifying Thailand’s Legal System (2026.acl-industry)
Copied to clipboard
| Challenge: | Thai legal data lacks standardized, machine-readable data formats . authors: combining legal data requires understanding structural relationships that no existing resource captures. |
| Approach: | They propose a unified temporal knowledge graph for Thai legal data . it integrates 3,840 laws with 87,394 Supreme Court decisions, updated daily . |
| Outcome: | The proposed graph integrates 3,840 laws with 87,394 Supreme Court decisions . it achieves Citation F1 of 0.812 versus 0.666 for practitioner-standard web search . |
Modular Monolingual Adaptation using Pretrained Language Models (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing approaches to building monolingual models for low-resource languages require a full model tuning process. |
| Approach: | They propose a modular approach to build monolingual models for low-resource languages by finetuning the whole model on the target language. |
| Outcome: | The proposed model improves on natural language understanding tasks on Scottish Gaelic, Irish, and Quechua with Quechuan being a very low-resource language. |
Multi-Task Reinforcement Learning for Enhanced Multimodal LLM-as-a-Judge (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing MLLMs are optimized for single-task scenarios and struggle to generalize to diverse contexts. |
| Approach: | They propose a framework that integrates multitask reinforcement learning and generalization capabilities of MLLMs to optimize the judge model across multiple tasks. |
| Outcome: | The proposed framework outperforms baseline models in judgment consistency and correlation with human preferences. |
RAPIDS: Resume Attack Prompt Injection Detection at Scale (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing generic prompt injection detectors lack domain specificity needed for nuanced resume attacks. |
| Approach: | They propose a scalable detection framework that uses a synthetically generated dataset to address data scarcity in this domain. |
| Outcome: | The proposed framework outperforms the best off-the-shelf detector by over 50% in relative F1 and approaches frontier LLM accuracy. |
No Innocence in Styling: Discovery of Privacy Protection Capabilities and Security Risks in Consumer Generative AI Writing Assistants (2026.acl-industry)
Copied to clipboard
Mohd. Farhan Israk Soumik, Syed Mhamudul Hasan, Wanniarachchi Kankanamge Malithi Mithsara, Ahmed Imteaj, Abdur R. Shahid
| Challenge: | a recent study examines the dual-use nature of platform-level text stylization. |
| Approach: | They examine the dual-use nature of platform-level text stylization by examining their implications for privacy and platform safety. |
| Outcome: | The proposed model reduces emotion inference accuracy, lowers profiling risk, and increases error rates in misinformation detection. |
RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment (2026.acl-industry)
Copied to clipboard
Yingfeng Luo, Hongyu Liu, DingYang Lin, Kaiyan Chang, Chenglong Wang, Bei Li, Quan Du, Tong Xiao, JingBo Zhu
| Challenge: | Existing routing strategies rely on heuristics, external predictors, or absolute quality estimation to capture whether the large model provides a worthwhile improvement over the small one. |
| Approach: | They propose a budget allocation problem for routing large model to large model . they propose heuristics, external predictors, or absolute quality estimation to determine the optimal signal for budgeted decisions. |
| Outcome: | The proposed model outperforms heuristics, quality/difficulty estimation baselines and achieves a superior quality–budget Pareto frontier. |
Intent-Driven Semantic ID Generation for Grounded Conversational News Recommendation (2026.acl-industry)
Copied to clipboard
| Challenge: | a new approach to news recommendation grounds each suggestion in a rapidly evolving article corpus while addressing implicit user intents that lack explicit retrievable keywords. |
| Approach: | They propose an intent-driven Semantic ID generation paradigm to address these challenges . they map diverse intents to hierarchical SID prefixes and then fuzzy-match them to current news pool . |
| Outcome: | The proposed model achieves 0% hallucination and 12.4% L1 match on a mainstream Chinese news platform. |
Development and Benchmarking of a Blended Human-AI Qualitative Research Assistant (2026.acl-industry)
Copied to clipboard
Joseph Matveyenko, James Liu, John David Parsons, Ryan Brown, Alina I. Palimaru, Vipul Gupta, Prateek Puri
| Challenge: | Qualitative research emphasizes constructing meaning through iterative engagement with textual data. |
| Approach: | They present and benchmark a qualitative research assistant system that allows researchers to identify themes and annotate datasets. |
| Outcome: | The proposed system achieves an inter-rater reliability between Muse and humans of Cohen’s = 0.7 for well-specified codes. |
Entity Exchange in the Wild: A Diagnostic Study of LLM Based Real-World Conversational Entity Extraction (2026.acl-industry)
Copied to clipboard
| Challenge: | Prior work has examined the impact of transcription noise and cross-turn reasoning, but it has not systematically analyzed how entity-exchange phenomena themselves shape extraction performance. |
| Approach: | They evaluate 16 large language models on 6,387 real-world customer–agent conversations spanning 12 entity types across numeric, alphanumeric, temporal, and free-text categories. |
| Outcome: | The proposed model improves on the extracted entities across all three axes yielding average gains of up to 6.4% across models. |
Agentic Context Strategies for Multi-Format Document Understanding: When Should Language Models Use Tools? (2026.acl-industry)
Copied to clipboard
| Challenge: | Large language models face fundamental trade-offs when processing long documents . full context is expensive and may exceed limits, while RAG risks missing relevant information. |
| Approach: | They evaluate four context strategies across three document formats to evaluate their results . they find agentic tool-augmented approaches outperform passive strategies . |
| Outcome: | The agentic tool-augmented approaches outperform passive strategies on three document formats. |
MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&A (2026.acl-industry)
Copied to clipboard
Hanoz Bhathena, Parin Rajesh Jhaveri, Rohan Mittal, Prateek Singh, Aymen Kallala, Rachneet Kaur, Yiqiao Jin, Zhen Zeng, Adwait Ratnaparkhi, Denis Kochedykov
| Challenge: | Recent advances in multimodal retrieval-augmented generation (MM-RAG) have shifted toward minimal parsing, relying on page-level images for producing retriever embeddings and answer generation. |
| Approach: | They propose a document structure-aware split that extracts and represents document structure via a structure-based split that dynamically routes documents through orientation-specific ingestion pipelines. |
| Outcome: | The proposed model outperforms state-of-the-art vision-centric baselines by up to 32% points and achieves strong gains on report-style layouts. |
AesX: Enhance Your Images with Stunning Aesthetic Beauty (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing models do not analyze human preferences at a finer granularity, which leads to quality issues. |
| Approach: | They propose a set of preference indicators across two major dimensions, text-image consistency and aesthetic quality, and a generative framework to steer the model toward a generation path that more closely aligns with human aesthetic sensibilities. |
| Outcome: | The proposed model improves target recognition accuracy and overall visual aesthetic presentation by focusing on human preferences. |
Transfer Learning for Generalizable Automated LLM Improvement Pipeline for IVR Navigation (2026.acl-industry)
Copied to clipboard
| Challenge: | Using a human-labeled ground truth dataset, we can transfer specialized prompts from one task to another, reducing the complexity of the task. |
| Approach: | They propose a production-quality automated LLM pipeline which leverages a small number of human-labeled ground truth datasets to transfer specialized prompts from one task to another. |
| Outcome: | The proposed model reduces prompt complexity by up to 80% and obtains 82% turn-level accuracy in real-world industrial healthcare settings, surpassing a human-designed prompt at 79%. |
Beyond Instruction Optimization: Multi-Agent Error-Driven Class Description Refinement for LLM-Based Classification (2026.acl-industry)
Copied to clipboard
| Challenge: | Large Language Models have demonstrated considerable efficacy in classification tasks . however, their performance depends on two critical prompt components: Task Instructions (HOW to classify) and Class Descriptions (WHAT defines each class). |
| Approach: | They propose a multi-agent framework for iteratively refining class descriptions based on classification errors. |
| Outcome: | Empirical evaluation shows up to 20.71% accuracy improvements over static class descriptions. |
TEN: Table Explicitization, Neurosymbolically (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing methods for extracting tabular data from semistructured text are error-prone and costly. |
| Approach: | They propose a neurosymbolic approach to extract tabular data from semistructured text . TEN is a triadic feedback loop that iteratively refines table hypotheses . |
| Outcome: | The proposed approach outperforms neural baselines in exact match accuracy and lower hallucination rates. |
RADAR: Risk-Aware Distilled Adaptive Routing for Efficient Short-Form Video Platform Ecosystem Governance (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing solutions to address inefficiency in large-scale integrity enforcement on short-form video platforms require multiple specialized vertical modules . |
| Approach: | They propose a lightweight risk-aware routing framework that selectively releases low-risk content while dispatching high-risk instances to appropriate vertical modules. |
| Outcome: | The proposed framework selectively releases low-risk content while dispatching high-risk instances to appropriate vertical modules. |
From Graph to Text and Back: Semantic Fidelity in Automated Industrial Knowledge Graphs (2026.acl-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) often hallucinate entities or omit relations, posing unacceptable liability. |
| Approach: | They propose a self-supervised round-trip pipeline to enforce strict semantic fidelity in KG-to-text generation. |
| Outcome: | The proposed approach improves triple-extraction accuracy and verbalization faithfulness without manual annotation or massive teacher models. |
Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows (2026.acl-industry)
Copied to clipboard
Nikita Borovkov, Elisei Rykov, Olga Tsymboi, Sergei Filimonov, Nikita Surnachev, Dmitry Bitman, Anatolii Potapov
| Challenge: | 45% of sessions automated in production without degrading support quality level . traditional automated processes are costly at scale and require manual rule authoring . |
| Approach: | They propose a system that automates end-to-end customer support workflows inside an enterprise BPM platform. |
| Outcome: | The proposed system automates 45% of sessions and reduces average handling time by 39% without degrading support quality level. |
Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning (2026.acl-industry)
Copied to clipboard
| Challenge: | Advanced reasoning typically requires Chain-of-Thought prompting, which is accurate but incurs prohibitive latency and substantial test-time inference costs. |
| Approach: | They propose to extract explicit reasoning patterns from a Teacher model and organize them into a structured list of expressive instructions for the Student model’s System Prompt. |
| Outcome: | Evaluated using Gemma-3 4B, the proposed model improves Macro F1 scores on StereoSet and Contract-NLI while increasing LogiQA accuracy to 70%. |
MTIVE: Multi-Task Image Verification Engine Using Vision-Language Models for E-commerce (2026.acl-industry)
Copied to clipboard
| Challenge: | Vision-language models struggle with noisy real-world images and multi-task requirements. |
| Approach: | They propose a curriculum learning framework that adapts vision-language models through three stages . MTIVE uses frozen base weights with stacked LoRA adapters for shared domain knowledge . |
| Outcome: | MTIVE outperforms open-source and proprietary baselines in standard and continual learning settings. |
Measuring and Mitigating Racial Bias in Embedding Models: A Comparative Study for Law Enforcement Retrieval (2026.acl-industry)
Copied to clipboard
| Challenge: | Embedding models are often used for semantic retrieval in high-stakes domains such as law enforcement . racial descriptors affect similarity scores and retrieval rankings for semantically identical crime incidents . |
| Approach: | They propose to use racial descriptors to measure r&d bias in embedding models . they compute similarity scores between crime incidents and simple law enforcement queries . |
| Outcome: | The proposed methods show that racial descriptors affect similarity scores and retrieval rankings for semantically identical crime incidents. |
VishBox v2: A Multi-Agent System for Adaptive Voice Phishing Simulation (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing alternatives lack round-level granularity and controllability, making it difficult to analyze how victim profiles and psychological states shape tactic effectiveness. |
| Approach: | They propose a multi-agent architecture that generates structured phishing simulations grounded in crime-script procedures and persuasion principles. |
| Outcome: | The proposed framework captures tactic concentration, vulnerability transitions, and web-search-induced procedural disruptions across 571 rounds. |
ResoDiff-44k: High-Fidelity Cross-Lingual Speech and Singing Synthesis via Discrete Diffusion (2026.acl-industry)
Copied to clipboard
| Challenge: | generative speech models have a fidelity ceiling that is capped at lower sampling rates . current models rely on intermediate mel-spectrograms, which discard phase and high-frequency information . a new framework that synthesizes industrial-grade 44.1kHz audio is proposed . |
| Approach: | They propose a production-grade generative foundation model for 44.1kHz audio synthesis . they pre-train ResoDiff-44k on a massive 150K -hour multilingual dataset . |
| Outcome: | The proposed model achieves 4.6 mean opinion score in 44.1kHz singing synthesis compared to baselines . it also reduces character error rate on regional mixed-language and singing prompts compared with baselines. |
TingIS: Real-time Risk Event Discovery from Noisy Customer Incidents at Enterprise Scale (2026.acl-industry)
Copied to clipboard
| Challenge: | a 5minute downtime for an incident could result in a loss of 40 million dollars and erosion of user trust. |
| Approach: | They propose a multi-stage event unification engine that synergizes efficient indexing techniques with Large Language Models (LLMs) to make informed decisions on event merging. |
| Outcome: | The proposed system outperforms baseline methods in routing accuracy, clustering quality, and Signal-to-Noise Ratio. |
LoCar: Localization-Aware Evaluation of In-Vehicle Assistants through Fine-Grained Sociolinguistic Control (2026.acl-industry)
Copied to clipboard
| Challenge: | Using Large Language Models (LLMs) is challenging due to lack of domain-specific evaluation standards . current LLMs prioritize reasoning or knowledge over sociolinguistic nuances vital for automotive settings . |
| Approach: | They propose a framework for evaluation of Korean-language in-vehicle assistants . they propose to evaluate fine-grained Korean honorific control and safetycritical response behavior . |
| Outcome: | The proposed evaluation framework evaluates fine-grained honorific control, safetycritical response behavior, and task efficiency in deployment-aligned settings. |
Index-Time Prefix Injection for Multi-Tenant Retrieval: Improving Search Relevance Without Model Fine-Tuning (2026.acl-industry)
Copied to clipboard
| Challenge: | a single multilingual biencoder handles all retrieval, but these are task-generic and domain-agnostic. |
| Approach: | They propose a training-free method that prepending domain-descriptive prefixes to documents during indexing. |
| Outcome: | The proposed method improves retrieval relevance by prepending natural-language prefixes to documents during indexing. |
Benchmarking Testing in Automated Theorem Proving (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing evaluations rely on indirect proxies such as lexical overlap with human-annotated proof, or expensive manual inspection. |
| Approach: | They propose a framework that evaluates the semantic correctness of formal theorems . they use a set of problems paired with 41 successor theorels to compare them . |
| Outcome: | The proposed framework evaluates the semantic correctness of formal theorems using real-world Lean 4 repositories. |
Graph-Based Phonetic Error Correction of Noisy ASR (2026.acl-industry)
Copied to clipboard
| Challenge: | Automatic speech recognition systems produce residual transcription errors that affect semantically critical tokens. |
| Approach: | They propose a phonetic-based algorithm that combines phonetic graph modeling with contextual language understanding to improve automatic speech recognition. |
| Outcome: | The proposed framework decouples phonetic reasoning from contextual semantic selection and improves accuracy. |
CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing compression methods for large reasoning models rely on uniform length reduction or coarse-grained difficulty estimation, often leading to performance degradation on difficult problems. |
| Approach: | They propose a framework that incorporates model’s intrinsic self-certainty signals as confidence into the preference optimization process, which autonomously modulates reasoning lengths based on problem difficulty. |
| Outcome: | The proposed framework outperforms state-of-the-art models on reasoning accuracy across multiple benchmarks on different base models. |
LatentGate: Low-Latency Semantic Routing via Frozen-Backbone Probing of Small Language Models (2026.acl-industry)
Copied to clipboard
| Challenge: | Prompt-based LLM routers deliver strong semantic reasoning but incur prohibitive latency and cost that scales with agent count. |
| Approach: | They propose a non-generative router that extracts mean-pooled hidden states from a frozen small language model and trains a lightweight linear probe for agent classification. |
| Outcome: | The proposed router achieves 98.8% in-domain and 80.0% OOD accuracy across 5 SLM backbones and 100 enterprise agents. |
Thinking with Reasoning Skills: Fewer Tokens, More Accuracy (2026.acl-industry)
Copied to clipboard
| Challenge: | Reasoning LLMs often spend tokens on long intermediate reasoning traces when solving new problems. |
| Approach: | They propose to store reusable reasoning skills distilled from extensive deliberation and trial-and-error exploration and retrieve these skills at inference time to guide future reasoning. |
| Outcome: | The proposed approach reduces reasoning tokens while improving overall performance on coding and mathematical reasoning tasks. |