Natural Language Processing Techniques

Últimos artículos

• MineDraft: A Framework for Batch Parallel Speculative Decoding

  Zhenwei Tang, Arun Verma, Zijian Zhou, Zhaoxuan Wu, Alok Prakash, Daniela Rus, Bryan Kian Hsiang Low · 20 de marzo de 2026

  Speculative decoding (SD) accelerates large language model inference by using a smaller draft model to propose draft tokens that are subsequently verified by a larger target model. However, the performance of standard SD is often limited by the strictly sequential execution of these drafting and ver…

• Adapting Methods for Domain-Specific Japanese Small LMs: Scale, Architecture, and Quantization

  Takato Yasuno · 20 de marzo de 2026

  This paper presents a systematic methodology for building domain-specific Japanese small language models using QLoRA fine-tuning. We address three core questions: optimal training scale, base-model selection, and architecture-aware quantization. Stage 1 (Training scale): Scale-learning experiments (…

• Mi:dm K 2.5 Pro

  KT Tech innovation Group · 20 de marzo de 2026

  The evolving LLM landscape requires capabilities beyond simple text generation, prioritizing multi-step reasoning, long-context understanding, and agentic workflows. This shift challenges existing models in enterprise environments, especially in Korean-language and domain-specific scenarios where sc…

• From Binary to Bilingual: How the National Weather Service is Using Artificial Intelligence to Develop a Comprehensive Translation Program

  Joseph E. Trujillo-Falcon, Monica L. Bozeman, Liam E. Llewellyn, Samuel T. Halvorson, Meryl Mizell, Stuti Deshpande, Bob Manning, Chris Rohrbach, Ian Blaylock, Angel Montanez, Todd Fagin · 20 de marzo de 2026

  To advance a Weather-Ready Nation, the National Weather Service (NWS) is developing a systematic translation program to better serve the 68.8 million people in the U.S. who do not speak English at home. This article outlines the foundation of an automated translation tool for NWS products, powered b…

• NANOZK: Layerwise Zero-Knowledge Proofs for Verifiable Large Language Model Inference

  Zhaohui Geoffrey Wang · 20 de marzo de 2026

  When users query proprietary LLM APIs, they receive outputs with no cryptographic assurance that the claimed model was actually used. Service providers could substitute cheaper models, apply aggressive quantization, or return cached responses - all undetectable by users paying premium prices for fro…

• SVGBuilder: Component-Based Colored SVG Generation with Text-Guided Autoregressive Transformers

  Zehao Chen, Rong Pan · 20 de marzo de 2026

  Scalable Vector Graphics (SVG) are essential XML-based formats for versatile graphics, offering resolution independence and scalability. Unlike raster images, SVGs use geometric shapes and support interactivity, animation, and manipulation via CSS and JavaScript. Current SVG generation methods face …

• Analysis Of Linguistic Stereotypes in Single and Multi-Agent Generative AI Architectures

  Martina Ullasci, Marco Rondina, Riccardo Coppola, Flavio Giobergia, Riccardo Bellanca, Gabriele Mancari Pasi, Luca Prato, Federico Spinoso, Silvia Tagliente · 20 de marzo de 2026

  Many works in the literature show that LLM outputs exhibit discriminatory behaviour, triggering stereotype-based inferences based on the dialect in which the inputs are written. This bias has been shown to be particularly pronounced when the same inputs are provided to LLMs in Standard American Engl…

• VEPO: Variable Entropy Policy Optimization for Low-Resource Language Foundation Models

  Chonghan Liu, Yimin Du, Qi An, Xin He, Cunqi Zhai, Fei Tan, Weijia Lin, Xiaochun Gong, Yongchao Deng, Shousheng Jia, Xiangzheng Zhang · 20 de marzo de 2026

  Large language models frequently exhibit suboptimal performance on low resource languages, primarily due to inefficient subword segmentation and systemic training data imbalances. In this paper, we propose Variable Entropy Policy Optimization (VEPO), which leverages Reinforcement Learning with Verif…

• Continually self-improving AI

  Zitong Yang · 20 de marzo de 2026

  Modern language model-based AI systems are remarkably powerful, yet their capabilities remain fundamentally capped by their human creators in three key ways. First, although a model's weights can be updated via fine-tuning, acquiring new knowledge from small, specialized corpora after pretraining re…

• ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression

  Ruibo Fan, Xiangrui Yu, Xinglin Pan, Zeyu Li, Weile Luo, Qiang Wang, Wei Wang, Xiaowen Chu · 19 de marzo de 2026

  Lossless model compression holds tremendous promise for alleviating the memory and bandwidth bottlenecks in bit-exact Large Language Model (LLM) serving. However, existing approaches often result in substantial inference slowdowns due to fundamental design mismatches with GPU architectures: at the k…

• Ensemble Self-Training for Unsupervised Machine Translation

  Ido Aharon, Jonathan Shaki, Sarit Kraus · 19 de marzo de 2026

  We present an ensemble-driven self-training framework for unsupervised neural machine translation (UNMT). Starting from a primary language pair, we train multiple UNMT models that share the same translation task but differ in an auxiliary language, inducing structured diversity across models. We the…

• From Language to Action in Arabic: Reliable Structured Tool Calling via Data-Centric Fine-Tuning

  Omer Nacar, Deema Alquffari, Saleh Alsharideh, Adeem AlOtaibi, Abdulaziz Alabdulkarim, Leen Alhazmi, Nada Alomar, Wareef Alzubaidi, Nada Alsultan, Ahmed Alrabghi, Demah Alhoshan, Rana Alsayyari, Hamed Alruwaili, Albaraa Jaafar, Khaled Alusmani, Abdulaziz Alsohimy, Munirah Alsubaie, Shahd Aldukhayil, Arwa Alali, Yazeed BinShihah, Razan Alsulaymi, Nourah Alhumaid, Razan Abdulsalam, Reem Alamoudi, Mohammed Alkhalifa · 19 de marzo de 2026

  Function-calling language models are essential for agentic AI systems that translate natural language into executable structured actions, yet existing models exhibit severe structural instability when applied to Arabic. We present AISA-AR-FunctionCall, a production-oriented Arabic function-calling f…

• TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas

  Ai Jian, Xiaoyun Zhang, Wanrou Du, Jingqing Ruan, Jiangbo Pei, Weipeng Zhang, Ke Zeng, Xunliang Cai · 18 de marzo de 2026

  Text-to-SQL parsing has achieved remarkable progress under the Full Schema Assumption. However, this premise fails in real-world enterprise environments where databases contain hundreds of tables with massive noisy metadata. Rather than injecting the full schema upfront, an agent must actively ident…

• Morphemes Without Borders: Evaluating Root-Pattern Morphology in Arabic Tokenizers and LLMs

  Yara Alakeel, Chatrine Qwaider, Hanan Aldarmaki, Sawsan Alqahtani · 18 de marzo de 2026

  This work investigates how effectively large language models (LLMs) and their tokenization schemes represent and generate Arabic root-pattern morphology, probing whether they capture genuine morphological structure or rely on surface memorization. Arabic morphological system provides a rich testbed …

• Transformer-Encoder Trees for Efficient Multilingual Machine Translation and Speech Translation

  Yiwen Guan, Jacob Whitehill · 18 de marzo de 2026

  Multilingual translation suffers from computational redundancy, especially when translating into multiple languages simultaneously. In addition, translation quality can suffer for low-resource languages. To address this, we introduce Transformer Encoder Tree (TET), a hierarchical, non-autoregressive…

• Are LLMs Good Text Diacritizers? An Arabic and Yoruba Case Study

  Hawau Olamide Toyin, Samar Mohamed Magdy, Hanan Aldarmaki · 18 de marzo de 2026

  We investigate the effectiveness of large language models (LLMs) for text diacritization in two typologically distinct languages: Arabic and Yoruba. To enable a rigorous evaluation, we introduce a novel multilingual dataset MultiDiac, with diverse samples that capture a range of diacritic ambiguitie…

• QV May Be Enough: Toward the Essence of Attention in LLMs

  Zhang Edward · 18 de marzo de 2026

  Starting from first principles and a linguistic perspective centered on part-of-speech (POS) and syntactic analysis, this paper explores and derives the underlying essence of the Query-Key-Value (QKV) mechanism within the Transformer architecture. Based on this theoretical foundation, we provide a u…

• POaaS: Minimal-Edit Prompt Optimization as a Service to Lift Accuracy and Cut Hallucinations on On-Device sLLMs

  Jungwoo Shim, Dae Won Kim, Sun Wook Kim, Soo Young Kim, Myungcheol Lee, Jae-geun Cha, Hyunhwa Choi · 18 de marzo de 2026

  Small language models (sLLMs) are increasingly deployed on-device, where imperfect user prompts--typos, unclear intent, or missing context--can trigger factual errors and hallucinations. Existing automatic prompt optimization (APO) methods were designed for large cloud LLMs and rely on search that o…

• Fanar 2.0: Arabic Generative AI Stack

  FANAR TEAM, Ummar Abbas, Mohammad Shahmeer Ahmad, Minhaj Ahmad, Abdulaziz Al-Homaid, Anas Al-Nuaimi, Enes Altinisik, Ehsaneddin Asgari, Sanjay Chawla, Shammur Chowdhury, Fahim Dalvi, Kareem Darwish, Nadir Durrani, Mohamed Elfeky, Ahmed Elmagarmid, Mohamed Eltabakh, Asim Ersoy, Masoomali Fatehkia, Mohammed Qusay Hashim, Majd Hawasly, Mohamed Hefeeda, Mus'ab Husaini, Keivin Isufaj, Soon-Gyo Jung, Houssam Lachemat, Ji Kim Lucas, Abubakr Mohamed, Tasnim Mohiuddin, Basel Mousi, Hamdy Mubarak, Ahmad Musleh, Mourad Ouzzani, Amin Sadeghi, Husrev Taha Sencar, Mohammed Shinoy, Omar Sinan, Yifan Zhang · 18 de marzo de 2026

  We present Fanar 2.0, the second generation of Qatar's Arabic-centric Generative AI platform. Sovereignty is a first-class design principle: every component, from data pipelines to deployment infrastructure, was designed and operated entirely at QCRI, Hamad Bin Khalifa University. Fanar 2.0 is a sto…

• Prose2Policy (P2P): A Practical LLM Pipeline for Translating Natural-Language Access Policies into Executable Rego

  Vatsal Gupta, Darshan Sreenivasamurthy · 18 de marzo de 2026

  Prose2Policy (P2P) is a LLM-based practical tool that translates natural-language access control policies (NLACPs) into executable Rego code (the policy language of Open Policy Agent, OPA). It provides a modular, end-to-end pipeline that performs policy detection, component extraction, schema valida…

• LLAMAFUZZ: Large Language Model Enhanced Greybox Fuzzing

  Hongxiang Zhang, Yuyang Rong, Yifeng He, Hao Chen · 18 de marzo de 2026

  Greybox fuzzing has achieved success in revealing bugs and vulnerabilities in programs. However, randomized mutation strategies have limited the fuzzer's performance on structured data. Specialized fuzzers can handle complex structured data, but require additional efforts in grammar and suffer from …

• Who Benchmarks the Benchmarks? A Case Study of LLM Evaluation in Icelandic

  Finnur \'Ag\'ust Ingimundarson, Steinunn Rut Fri{\dh}riksd\'ottir, Bjarki \'Armannsson, Iris Edda Nowenstein, Stein{\th}\'or Steingr\'imsson · 18 de marzo de 2026

  This paper evaluates current Large Language Model (LLM) benchmarking for Icelandic, identifies problems, and calls for improved evaluation methods in low/medium-resource languages in particular. We show that benchmarks that include synthetic or machine-translated data that have not been verified in …

• Can Linguistically Related Languages Guide LLM Translation in Low-Resource Settings?

  Aishwarya Ramasethu, Niyathi Allu, Rohin Garg, Harshwardhan Fartale, Dun Li Chan · 18 de marzo de 2026

  Large Language Models (LLMs) have achieved strong performance across many downstream tasks, yet their effectiveness in extremely low-resource machine translation remains limited. Standard adaptation techniques typically rely on large-scale parallel data or extensive fine-tuning, which are infeasible…

• Boosting Text-to-Chart Retrieval through Training with Synthesized Semantic Insights

  Yifan Wu, Lutao Yan, Yizhang Zhu, Yenchi Tseng, Yinan Mei, Yong Wang, Jiannan Wang, Nan Tang, Yuyu Luo · 18 de marzo de 2026

  Text-to-chart retrieval, enabling users to find relevant charts via natural language queries, has gained significant attention. However, evaluating models in real-world business intelligence (BI) scenarios is challenging, as current benchmarks fail to simulate realistic user queries or test for deep…

• CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language

  Junhang Cheng, Fang Liu, Jia Li, Chengru Wu, Nanxiang Jiang, Li Zhang · 17 de marzo de 2026

  Large Language Models excel in high-resource programming languages but struggle with low-resource ones. Existing research related to low-resource programming languages primarily focuses on Domain-Specific Languages (DSLs), leaving general-purpose languages that suffer from data scarcity underexplore…