Natural Language Processing Techniques

Últimos artículos

• Nonparametric LLM Evaluation from Preference Data

  Dennis Frauen, Athiya Deviyani, Mihaela van der Schaar, Stefan Feuerriegel · 30 de enero de 2026

  Evaluating the performance of large language models (LLMs) from human preference data is crucial for obtaining LLM leaderboards. However, many existing approaches either rely on restrictive parametric assumptions or lack valid uncertainty quantification when flexible machine learning methods are use…

• DASH: Deterministic Attention Scheduling for High-throughput Reproducible LLM Training

  Xinwei Qiang, Hongmin Chen, Shixuan Sun, Jingwen Leng, Xin Liu, Minyi Guo · 30 de enero de 2026

  Determinism is indispensable for reproducibility in large language model (LLM) training, yet it often exacts a steep performance cost. In widely used attention implementations such as FlashAttention-3, the deterministic backward pass can incur up to a 37.9% throughput reduction relative to its non-d…

• Task-Awareness Improves LLM Generations and Uncertainty

  Tim Tomov, Dominik Fuchsgruber, Stephan G\"unnemann · 30 de enero de 2026

  In many applications of LLMs, natural language responses often have an underlying structure such as representing discrete labels, numerical values, or graphs. Yet, existing decoding and uncertainty estimation methods operate only in language space and largely disregard structural information. We add…

• GenOM: Ontology Matching with Description Generation and Large Language Model

  Yiping Song, Jiaoyan Chen, Renate A. Schmidt · 30 de enero de 2026

  Ontology matching (OM) plays an essential role in enabling semantic interoperability and integration across heterogeneous knowledge sources, particularly in the biomedical domain which contains numerous complex concepts related to diseases and pharmaceuticals. This paper introduces GenOM, a large la…

• Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models

  Rui Cai, Bangzheng Li, Xiaofei Wen, Muhao Chen, Zhe Zhao · 30 de enero de 2026

  Multimodal Large Language Models demonstrate strong performance on multimodal benchmarks, yet often exhibit poor robustness when exposed to spurious modality interference, such as irrelevant text in vision understanding, or irrelevant visual content in question answering. At its core, modality inter…

• Procedural Pretraining: Warming Up Language Models with Abstract Data

  Liangze Jiang, Zachary Shinnick, Anton van den Hengel, Hemanth Saratchandran, Damien Teney · 30 de enero de 2026

  Pretraining directly on web-scale corpora is the de facto paradigm for building language models. We study an alternative setting where the model is initially exposed to abstract structured data, as a means to ease the subsequent acquisition of rich semantic knowledge, much like humans learn simple l…

• TBDFiltering: Sample-Efficient Tree-Based Data Filtering

  Robert Istvan Busa-Fekete, Julian Zimmert, Anne Xiangyi Zheng, Claudio Gentile, Andras Gyorgy · 30 de enero de 2026

  The quality of machine learning models depends heavily on their training data. Selecting high-quality, diverse training sets for large language models (LLMs) is a difficult task, due to the lack of cheap and reliable quality metrics. While querying existing LLMs for document quality is common, this …

• Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening

  Xiaotong Ji, Rasul Tutunov, Matthieu Zimmer, Haitham Bou Ammar · 30 de enero de 2026

  Reinforcement learning (RL) post-training is a dominant approach for improving the reasoning performance of large language models (LLMs), yet growing evidence suggests that its gains arise primarily from distribution sharpening rather than the acquisition of new capabilities. Recent work has shown t…

• When "Better" Prompts Hurt: Evaluation-Driven Iteration for LLM Applications

  Daniel Commey · 30 de enero de 2026

  Evaluating Large Language Model (LLM) applications differs from traditional software testing because outputs are stochastic, high-dimensional, and sensitive to prompt and model changes. We present an evaluation-driven workflow - Define, Test, Diagnose, Fix - that turns these challenges into a repeat…

• Toward Robust Multilingual Adaptation of LLMs for Low-Resource Languages

  Haolin Li, Haipeng Zhang, Mang Li, Yaohua Wang, Lijie Wen, Yu Zhang, Biqing Huang · 30 de enero de 2026

  Large language models (LLMs) continue to struggle with low-resource languages, primarily due to limited training data, translation noise, and unstable cross-lingual alignment. To address these challenges, we propose LiRA (Linguistic Robust Anchoring for LLMs)-a plug-and-play framework that requires …

• TIDE: Tuning-Integrated Dynamic Evolution for LLM-Based Automated Heuristic Design

  Chentong Chen, Mengyuan Zhong, Ye Fan, Jialong Shi, Jianyong Sun · 30 de enero de 2026

  Although Large Language Models have advanced Automated Heuristic Design, treating algorithm evolution as a monolithic text generation task overlooks the coupling between discrete algorithmic structures and continuous numerical parameters. Consequently, existing methods often discard promising algori…

• MURAD: A Large-Scale Multi-Domain Unified Reverse Arabic Dictionary Dataset

  Serry Sibaee, Yasser Alhabashi, Nadia Sibai, Yara Farouk, Adel Ammar, Sawsan AlHalawani, Wadii Boulila · 30 de enero de 2026

  Arabic is a linguistically and culturally rich language with a vast vocabulary that spans scientific, religious, and literary domains. Yet, large-scale lexical datasets linking Arabic words to precise definitions remain limited. We present MURAD (Multi-domain Unified Reverse Arabic Dictionary), an o…

• SDSC:A Structure-Aware Metric for Semantic Signal Representation Learning

  Jeyoung Lee, Hochul Kang · 30 de enero de 2026

  We propose the Signal Dice Similarity Coefficient (SDSC), a structure-aware metric function for time series self-supervised representation learning. Most Self-Supervised Learning (SSL) methods for signals commonly adopt distance-based objectives such as mean squared error (MSE), which are sensitive …

• Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures

  Shuangshuang Ying, Yunwen Li, Xingwei Qu, Xin Li, Sheng Jin, Minghao Liu, Zhoufutu Wen, Xeron Du, Tianyu Zheng, Yichi Zhang, Letian Ni, Yuyang Cheng, Zhenzhu Yang, Qiguang Chen, Jingzhe Ding, Shengda Long, Wangchunshu Zhou, Jiazhan Feng, Wanjun Zhong, Libo Qin, Ge Zhang, Wenhao Huang, Wanxiang Che, Chenghua Lin · 29 de enero de 2026

  Current preference learning methods achieve high accuracy on standard benchmarks but exhibit significant performance degradation when objective quality signals are removed. We introduce WritingPreferenceBench, a dataset of 1,800 human-annotated preference pairs (1,200 English, 600 Chinese) across 8 …

• Beyond Syntax: Action Semantics Learning for App Agents

  Bohan Tang, Dezhao Luo, Jianheng Liu, Jingxuan Chen, Shaogang Gong, Jianye Hao, Jun Wang, Kun Shao · 29 de enero de 2026

  The recent development of Large Language Models (LLMs) enables the rise of App agents that interpret user intent and operate smartphone Apps through actions such as clicking and scrolling. While prompt-based solutions with proprietary LLM APIs show promising ability, they incur heavy compute costs a…

• mR3: Multilingual Rubric-Agnostic Reward Reasoning Models

  David Anugraha, Shou-Yi Hung, Zilu Tang, Annie En-Shiun Lee, Derry Tanti Wijaya, Genta Indra Winata · 29 de enero de 2026

  Evaluation using Large Language Model (LLM) judges has been widely adopted in English and shown to be effective for automatic evaluation. However, their performance does not generalize well to non-English settings, and it remains unclear what constitutes effective multilingual training for such judg…

• LinguaMap: Which Layers of LLMs Speak Your Language and How to Tune Them?

  J. Ben Tamo, Daniel Carlander-Reuterfelt, Jonathan Rubin, Dezhi Hong, Mingxian Wang, Oleg Poliannikov · 29 de enero de 2026

  Despite multilingual pretraining, large language models often struggle with non-English tasks, particularly in language control, the ability to respond in the intended language. We identify and characterize two key failure modes: the multilingual transfer bottleneck (correct language, incorrect task…

• Summaries as Centroids for Interpretable and Scalable Text Clustering

  Jairo Diaz-Rodriguez · 29 de enero de 2026

  We introduce k-NLPmeans and k-LLMmeans, text-clustering variants of k-means that periodically replace numeric centroids with textual summaries. The key idea, summary-as-centroid, retains k-means assignments in embedding space while producing human-readable, auditable cluster prototypes. The method i…

• An Actionable Framework for Assessing Bias and Fairness in Large Language Model Use Cases

  Dylan Bouchard · 29 de enero de 2026

  Bias and fairness risks in Large Language Models (LLMs) vary substantially across deployment contexts, yet existing approaches lack systematic guidance for selecting appropriate evaluation metrics. We present a decision framework that maps LLM use cases, characterized by a model and population of pr…

• LogogramNLP: Comparing Visual and Textual Representations of Ancient Logographic Writing Systems for NLP

  Danlu Chen, Freda Shi, Aditi Agarwal, Jacobo Myerston, Taylor Berg-Kirkpatrick · 29 de enero de 2026

  Standard natural language processing (NLP) pipelines operate on symbolic representations of language, which typically consist of sequences of discrete tokens. However, creating an analogous representation for ancient logographic writing systems is an extremely labor intensive process that requires e…

• Beyond Random Sampling: Efficient Language Model Pretraining via Curriculum Learning

  Yang Zhang, Amr Mohamed, Hadi Abdine, Guokan Shang, Michalis Vazirgiannis · 29 de enero de 2026

  Curriculum learning-organizing training data from easy to hard-has improved efficiency across machine learning domains, yet remains underexplored for language model pretraining. We present the first systematic investigation of curriculum learning in LLM pretraining, with over 200 models trained on u…

• RPO:Reinforcement Fine-Tuning with Partial Reasoning Optimization

  Hongzhu Yi, Xinming Wang, Zhenghao zhang, Tianyu Zong, Yuanxiang Wang, Jun Xie, Tao Yu, Haopeng Jin, Zhepeng Wang, Kaixin Xu, Feng Chen, Jiahuan Chen, Yujia Yang, Zhenyu Guan, Bingkang Shi, Jungang Xu · 28 de enero de 2026

  Within the domain of large language models, reinforcement fine-tuning algorithms necessitate the generation of a complete reasoning trajectory beginning from the input query, which incurs significant computational overhead during the rollout phase of training. To address this issue, we analyze the i…

• Representational Homomorphism Predicts and Improves Compositional Generalization In Transformer Language Model

  Zhiyu An, Wan Du · 28 de enero de 2026

  Compositional generalization-the ability to interpret novel combinations of familiar components-remains a persistent challenge for neural networks. Behavioral evaluations reveal when models fail but offer limited insight into why failures arise at the representational level. We introduce Homomorphis…

• AECBench: A Hierarchical Benchmark for Knowledge Evaluation of Large Language Models in the AEC Field

  Chen Liang, Zhaoqi Huang, Haofen Wang, Fu Chai, Chunying Yu, Huanhuan Wei, Zhengjie Liu, Yanpeng Li, Hongjun Wang, Ruifeng Luo, Xianzhong Zhao · 28 de enero de 2026

  Large language models (LLMs), as a novel information technology, are seeing increasing adoption in the Architecture, Engineering, and Construction (AEC) field. They have shown their potential to streamline processes throughout the building lifecycle. However, the robustness and reliability of LLMs i…

• Confidence intervals for forced alignment boundaries using model ensembles

  Matthew C. Kelley · 28 de enero de 2026

  Forced alignment is a common tool to align audio with orthographic and phonetic transcriptions. Most forced alignment tools provide only a single estimate of a boundary. The present project introduces a method of deriving confidence intervals for these boundaries using a neural network ensemble tech…