Latest NLP Research Papers
The newest NLP papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks NLP so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.
Get the latest NLP papers in your inbox — free →Recent papers
- Towards a transformative and territorial leadership: The case of organic farming development in OccitaniePierre Triboulet, Charlène Arnaud, Liz Carey-Libbrecht · Cairn.info · Jan 1, 2050
The aim of this article is to characterize the modalities of transformative leadership in support of local public action. It posits that this transformation is based on both the democratic and the distributed dimensions of leadership, and t…
- Des villes en pixels aux cités réelles : influence des jeux vidéo sur l’architecture urbaine contemporaineAntoine Chollet · Cairn.info · Jan 1, 2028
This research explores how video games, as an immersive, interactive, and fictional medium, influencing representations, imaginations, and conceptions of contemporary cities. Based on a review of literature combining urban planning, archite…
- L’apport de l’informalité de l’économie sociale et solidaire à la mise en œuvre de l’économie circulairePhilippe Duez · Cairn.info · Jan 1, 2028
We can make informality a strong concept that allows us to discuss the problems of regulating the dominant economy in its search for more sustainable development. The informality of the circular economy intersects the economy and the enviro…
- L’innovation locale et sa contribution au développement durable : pour une taxonomie du système local de transitionChristian Brodhag · Cairn.info · Jan 1, 2028
L’article examine l’innovation locale en l’opposant au modèle schumpétérien, centré sur le marché, qui aborde les territoires uniquement dans le cadre de la compétition mondiale. Envisager l’innovation au service du développement durable du…
- L’enchantement de la planification territoriale par le design fiction : les cas de Grand Paris et Grand LondresThomas Michaud · Cairn.info · Jan 1, 2028
This article draws on Raphaële Bidault-Waddington’s design fiction work on the future of Greater Paris, as well as other speculative works, to explore the growing influence of fictional speculation in territorial planning and innovation. Th…
- Vers un Leadership Transformatif Territorial : le cas du développement de l’agriculture biologique en OccitaniePierre Triboulet, Charlène Arnaud · Cairn.info · Jan 1, 2027
Cet article a pour objectif de caractériser les modalités d’un leadership transformatif au service d’une action publique locale. Il fait la double hypothèse que cette transformation s’appuie sur les dimensions démocratiques et distribuées d…
- Exposure with response prevention in virtual reality for obsessive-compulsive disorder: A randomized controlled trialL. Rolvien, L. Jelinek, L. Lohse, S. Moritz et al. · MPG.PuRe (Max Planck Society) · Dec 31, 2026
- HCl-based halide vapor phase epitaxy and selective-area HCl gas etching of (−112) β-Ga <sub>2</sub> O <sub>3</sub>Takayoshi Oshima, Yuichi Oshima · Institutional Repositories ... · Dec 31, 2026
We propose (−112) and crystallographically equivalent (1−1−2), (−1−12), and (11−2) planes as fundamental crystal orientations for β-Ga2O3 studies. In homoepitaxy, the epilayer exhibited single crystallinity with tilt and twist dispersions c…
- Therapeutic efficacy of naloxone hydrochloride combined with hemoperfusion in toxic acute renal failure via the oxidative stress/Nrf2 pathway.Yin Zhu, Huichun Sun, Qiuyang Wang, Yong Sheng et al. · PubMed · Dec 1, 2026
BACKGROUND: Toxic acute renal failure (ARF) involves severe oxidative stress. The Nrf2 pathway is a key antioxidant defense mechanism. OBJECTIVES: To investigate whether naloxone combined with hemoperfusion alleviates oxidative injury via N…
- PGR expression as a pharmacogenomic companion biomarker to GENE70-derived genomic risk in ER-positive/HER2-negative breast cancer.Orcun Can · PubMed · Dec 1, 2026
BACKGROUND: The biology of the estrogen receptor-positive (ER+) and human epidermal growth factor receptor 2-negative (HER2-) breast cancers is heterogeneous even when they are categorized by their risk via genomics. Transcriptomic PGR expr…
- La autoevaluación y el entrenamiento de estrategias de aprendizaje personalizadas mediante una aplicación para teléfonos móviles en educación superior: el desarrollo y análisis psicométrico de la Escala de Autorregulación del AprendizajeAgustín Freiberg Hoffmann, Agustín Romero Medina, Carlos Vigh, Fabiana Edith Uriel et al. · CONICET Digital (CONICET) · Dec 1, 2026
The study aims to develop a scale to measure self-regulated learning and estimate its psychometric indices. It is framed on a wider development of a smartphone app containing tools for college undergraduates to self-assess and train their s…
- Prognostic impact of age and MDS-associated mutations in NPM1-mutated AML.Vivian M. Liu, Megan Othus, Jasmine Naru, Rhonda E Ries et al. · PubMed · Nov 1, 2026
AML is not independently associated with adverse risk after adjusting for age, and highlight the need for age-adjusted AML risk models....
- Quasi-Constitutionality and Indigenous-State Treaties in AustraliaHobbs, Harry ; https://orcid.org/0000-0001-9903-6908, Taylor, Alice · UNSWorks (University of New... · Oct 1, 2026
The Statewide Treaty negotiated between the First Peoples Assembly of Victoria and the Victorian government is momentous. However, the Statewide Treaty Bill 2025 (Vic), which implements the agreement, is an ordinary piece of legislation sub…
- Euthanasia and abandonment: Non-ideal theory, opportunity costs and financial incentivesLuis Cordeiro-Rodrigues, Demin Duan · Scientific Electronic Libra... · Oct 1, 2026
Abstract: Recently, in Portugal, there have been several attempts by the parliament to pass a law that decriminalises euthanasia, and only the last one has passed. One of the arguments that have been raised against euthanasia, in the Portug…
- Efficient sampling of liver tissue for histological analysis of rodent MASLD/MASH models.Jenny Norlin, Sara Toftegaard Hjuler, Kasper Almholt, Rikke Kaae Kirk et al. · PubMed · Oct 1, 2026
Mouse and rat models of MASLD/MASH can provide valuable information about the effects of potential new treatments on liver histopathology. Liver samples for histology must therefore be representative of the entire organ, but it is also impo…
- The human adenosine A2A receptor co-isolates with anionic phospholipids in SMALPs from Pichia pastoris membranesIdoia Company-Marín, Andrew R. Pitt, Corinne M. Spickett · Aston Publications Explorer... · Oct 1, 2026
The adenosine A2A receptor (A2AR) is a GPCR that binds adenosine, leading to modulation of inflammation, platelet aggregation and vasodilation of coronary arteries. It is known that phospholipids surrounding GPCRs affect their activity but …
- Associations between BMI trajectories and young adult bone: a 10-yr follow-up from the Norwegian Fit Futures cohort.Marianne Lund, Anja Davis Norbye, Anne-Sofie Furberg, Jonas Johansson et al. · PubMed · Oct 1, 2026
< .001). Despite continued increases in BMI, the moderate-increasing trajectory was not associated with proportionally greater skeletal accrual than the high-stable trajectory, and statistically significant trajectory-by-time interactions w…
- Efficiency vs. safety in AI-enabled medical education: an ethical analysis of AI as a bridge or a wedgeLiu Yanling, Liu Huanhuan, Gao Jie · Scientific Electronic Libra... · Oct 1, 2026
Abstract: Artificial intelligence is rapidly changing medical education, promising faster workflows and richer learning resources while quietly reshaping how future clinicians think and act. This paper examines the central tension between e…
- Size-age structure of Artemia parthenogenetica and A. tibetiana (Crustacea: Anostraca) populations in hypersaline lakes of southern Western Siberia, 2025Lyubov V. Vesnina, Dmitry M. Bezmaternykh, Mikhail V. Lassyi, Yuri A. Vesnin · Acta Biologica Sibirica (Al... · Sep 19, 2026
Endorheic hypersaline lakes of diverse hydrochemical types in southern Western Siberia, with zooplankton communities dominated by the genus Artemia Leach, 1819, are reliable indicators of water availability and are sensitive to climate–driv…
- Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated DataAtindra Jha, Margaret Li, Jure Leskovec, Percy Liang et al. · arXiv · Sep 10, 2026
As the supply of human-written text is exhausted, it has become standard practice to repeat language model training data. Prior work has studied data repetition for densely activated Transformers, but the effects of data repetition remains …
- Distance generalization in transformers: why bother with positional encoding?Daniel Henrik Nevermann, Claudius Gros · arXiv · Sep 10, 2026
Out-of-distribution length generalization, namely to extrapolate a task from short to longer context, has been studied intensively for transformers. Here we focus on distance generalization, which probes performance when inter-token distanc…
- MindTopo: Can Foundation Models Reason in Topological Space?Yunfei Ge, Anbang Liu, Qineng Wang, Johnalbert Garnica et al. · arXiv · Sep 10, 2026
Spatial reasoning depends not only on metric properties such as distance, angle, and shape, but also on topological relations that remain invariant under continuous deformation. Cognitive science identifies these relations as foundational t…
- Nuha-Speech: Building General-Purpose Arabic Speech-LLMsYingzhi Wang, Reem Alhazzani, Muhammad Alqurishi · arXiv · Sep 10, 2026
As Speech Large Language Models (speech-LLMs) become increasingly multilingual, Arabic remains significantly underrepresented, highlighting the need for dedicated infrastructure to train and evaluate Arabic speech-LLMs. To address this gap,…
- Domain-Specific Hallucination Detection in Large Language ModelsVarun Teja Chundru, Debasmita Biswas · arXiv · Sep 10, 2026
Large language models generate fluent text that can contain unfaithful claims -- a phenomenon known as hallucination. We present a multi-signal detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo (MC) Dropout unce…
- Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR ScreensCarl Edwards, Edward De Brouwer, Xiner Li, Namkyeong Lee et al. · arXiv · Sep 10, 2026
Many biological discovery problems require experiments to be selected sequentially under constrained budgets. CRISPR screening is a prominent example, as exhaustive perturbation testing is often infeasible and candidate perturbations must i…
- The Last AI Built by Humans: Toward Genuine Recursive Self-ImprovementYi Duan, Ying Liu, Zirui Tang, Haodong Chen et al. · arXiv · Sep 10, 2026
Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improvement. We first use the Headroom-Closed Index (HCI) to reveal t…
- Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language ModelLisa Bylinina · arXiv · Sep 10, 2026
A language model normally begins training with random word embeddings: whatever 'banana' means must be learned from training corpora. I implement St. Augustine's picture of word learning, meaning by ostension, for a small masked language mo…
- Epistemic orientation predicts legislative effectiveness among members of the US CongressSegun Aroyehun, Stephan Lewandowsky, David Garcia · arXiv · Sep 10, 2026
Truth and evidence-based communication provide important foundations for democratic governance, accountability, and collective decision-making. Prior work shows that evidence-oriented language in US congressional floor speeches has declined…
- RetroThinker: Enabling Retrospective Thinking in Speech LLMsYi-Jen Shih, Puyuan Peng, Abdelrahman Mohamed, David Harwath · arXiv · Sep 10, 2026
Speech large language models (SpeechLLMs) offer reduced latency and retain paralinguistic nuances that are typically lost in cascaded automatic speech recognition (ASR) and text-based LM architectures. However, they continue to lag behind t…
- IndicTriMix: Developing Language Identification Datasets and Models for Tri-Language Code-MixingPruthwik Mishra, Rudra Trivedi, Avi Patel, Ashok Urlana et al. · arXiv · Sep 10, 2026
Language identification in code-mixed text, largely observed in social media, is highly essential when users frequently switch between multiple languages within a single utterance. Accurately identifying the languages of code-mixed tokens b…