Open-Weight Language Models

Ask about this topic

Overview

Open-weight language models make trained model weights available so people can run them locally, adapt them to new tasks or languages, and examine how they behave. Researchers build them with dense or mixture-of-experts architectures, then improve them through instruction tuning, preference training, retrieval, and quantization for efficient deployment. Evaluations cover reasoning, coding, multilingual and domain tasks, as well as bias, safety, reliability, and energy use; capable open models can compete with proprietary systems in some settings, but performance varies across languages, tasks, and hardware. Wider access supports local control and reproducibility, while also making misuse easier and leaving open how to provide robust safeguards, trustworthy evaluations, and model-lineage accountability.

Latest papers

CardsList

54 papers6 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

  1. Padding to k: A Minimum Count in the Schema Makes Open-Weight Models Pad Their Extraction Lists

    Oct 22, 2026Abhishek Barali, Aayush PaudelLLM Information ExtractionText Generation

    St. Xavier’s College Maitighar, Kathmandu Tribhuvan University, Nepal

  2. Wolof-Adapted Industry-Ready Open-Weight Language Models

    Oct 14, 2026Gwénolé Lecorvé, Delphine Charlet, Pierre Adam +15Language ModelingOpen-Weight Language Models

    Orange Research, France

  3. Measuring the Inference Energy Efficiency of Open-Weight LLMs across Benchmarks, Reasoning Modes, and Hardware

    Oct 9, 2026Zeyu Yang, Wes ArmourEnergy-Aware LLM InferenceLLM Inference Efficiency

    Department of Engineering Science, University of Oxford

  4. Unconstrained CTI-REALM with Open-Weights

    Oct 9, 2026Sahil Garg, Ruhi Gottumukkala, Vishal Agarwal +1AI Agent EvaluationAI Agent Security Benchmarks

    Averlon, Redmond, WA

  5. Autonomous Structuring of Radiology Reports Across Modalities at Archive Scale Using an Open-Weight Large Language Model

    Oct 3, 2026Friedrich Puttkammer, Fabian Drexel, Marlene Fritzsche +19Medical Report GenerationRadiology Report Generation

    Department of Radiology, Charité – Berlin University of Medicine, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, Germany · Department of Diagnostic and Interventional Radiology, School of Medicine and Health, TUM Klinikum Rechts der Isar, Technical University of Munich, Munich, Germany · Chair for AI in Healthcare and Medicine, Technical University of Munich (TUM) and TUM University Hospital, Munich, Germany +9

  6. The Fragility of Trigger-Tag Mechanisms for Misuse Detection in Open-Weight LLMs

    Oct 2, 2026Toluwani Aremu, Manit Baser, Mohan Gurusamy +2Adversarial Attacks on LLMsOpen-Weight Language Models

    MBZUAI, UAE · National University of Singapore · A*STAR Institute of Advanced Intelligence and Computing

  7. Cheap, open agents make LLM pollution harder to mitigate

    Sep 25, 2026Raluca Rilla, Anne-Marie Nussberger, Rui Mata +1AI-Generated Text DetectionLLM Agent Evaluation

    Center for Humans and Machines, Max Planck Institute for Human Development, Berlin, Germany · International Max Planck Research School on Learning, Institutions, and Future Evolution (LIFE), Berlin, Germany · University of Basel, Basel, Switzerland +2

  8. Witness Overlap: Directional Provenance Inside Open-Weight Model Families

    Sep 24, 2026Siyuan Li, Haoxuan Zeng, Xin Luo +6LLM AuditingOpen-Weight Language Models

    ModelOS · University of Michigan · Carnegie Mellon University

  9. Evaluating Open-Weight LLMs for Turkish Domain Documents Under Retrieval and Hardware Constraints

    Sep 23, 2026Imtiaz Ul Hassan, Öykü Akbulut, Onur Kaya +4Multilingual Language Model EvaluationLLM Evaluation

    Edge Hill University, United Kingdom · Ermetal Otomotiv ve E¸sya San. Tic. A.¸S., Türkiye

  10. Misaligned Clinical Risk Classification and Cost Asymmetry in Open-Weight Large Language Models

    Sep 21, 2026Star S. D. Liu, Xiyu Ding, Robert B. Barrett +3Cost-Sensitive LearningLLM Interpretability

    Biomedical Informatics and Data Science, Johns Hopkins University School of Medicine, Baltimore, MD, USA · Microsoft, Redmond, WA, USA · National Institutes of Health, Bethesda, MD, USA

  11. WiC is Not WSD: A Study on LLMs and Lexical Ambiguity Resolution

    Sep 17, 2026Yi Zhou, Kiamehr Rezaee, Danushka Bollegala +2Open-Weight Language ModelsWord Sense Disambiguation

    Cardiff University · University of Liverpool · Amazon

  12. Linguistic Triggers of Gender and Racial Bias in Open-Weight LLMs Applied to Recruitment

    Sep 16, 2026Kosuke Kitahara, Nobuhiro YamaguchiGender Bias in Language ModelsAI-Assisted Decision Making

    Recruit Co., Ltd. 1-9-2 Marunouchi Chiyoda-ku, Tokyo 100-6640 Japan

  13. AquiLLM: Evaluating Faithfulness in Open-Weight RAG-LLM Systems for Scientific Research

    Sep 15, 2026Bernie Boscoe, Srinath Saikrishnan, Vikram Seenivasan +6AI-Assisted Scientific ResearchOpen-Weight Language Models

    Dept. of Computer Science, Southern Oregon University, USA · Dept. of Computer Science, University of California, Los Angeles, USA · Dept. of Physics & Astronomy, University of California, Los Angeles, USA +1

  14. List Counting Failures Are Not One Phenomenon

    Sep 3, 2026Iyad Ait Hou, Saad Mankarious, Aya Zirikly +1Numerical Reasoning in Language ModelsOpen-Weight Language Models

    Department of Computer Science The George Washington University Washington, D.C., USA

  15. Manacá-1B: An Open, Reproducible Brazilian-Portuguese Language Model and a Tokenizer-Aware, Paired Evaluation

    Aug 31, 2026Bruno Leonardo Santos Menezes, Carlos Leonardo Souza Cardoso, Fabio Andre Machado PortoLanguage Model PretrainingPortuguese Language Models

    Laboratório Nacional de Computação Científica (LNCC), Petrópolis, Brazil

  16. LLMs as Acquisition Policies for Finite-Pool Materials Optimization: A Controlled Study

    Aug 20, 2026Dino-Rober Demir, Florian Le Bronnec, Rio YokotaLarge Language Model-Guided OptimizationActive Learning

    RIKEN Center for Computational Science, Tokyo, Japan

  17. Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification

    Aug 14, 2026Aman Singh Thakur, Rayan KhouryLanguage Model FingerprintingOpen-Weight Language Models

    Massachusetts Institute of Technology, USA

  18. Behavioral Reprogramming of Open-Weights Models: Cognitive Plasticity and Alignment Bounds

    Aug 13, 2026Lucia MalíčkováLLM AlignmentLanguage Model Steering

    National Supercomputing Centre, Slovakia.

  19. Can Open-Weight Models Compete on Financial Text Comprehension?

    Aug 9, 2026Jan SpörerLLM EvaluationFinancial QA

    University of St. Gallen, Switzerland

  20. Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space

    Aug 7, 2026Yiwei Chen, Bingqi Shang, Sijia LiuLanguage Model FingerprintingOpen-Weight Language Models

    Michigan State University

  21. K-EXAONE 2.0 Technical Report

    Aug 5, 2026Eunbi Choi, Kibong Choi, Sehyun Chun +74Multilingual Language ModelsMixture-of-Experts Language Models

  22. Language Equality has a Price: A Systematic Investigation of Multi-turn LLM Performance for EU-24+

    Aug 2, 2026Sherzod Hakimov, Karl Osswald, Jelle Psurek +3Multilingual Language Model EvaluationLLM Evaluation

    Computational Linguistics, Department of Linguistics University of Potsdam, Germany · 1German Research Center for Artificial Intelligence (DFKI), Berlin, Germany

  23. Selecting Open-Weight Language Models for Zero-Shot Intent Classification: A Systematic Evaluation of 41 Models

    Jul 29, 2026Parishruthi Ganesh, Gerry Dozier, Cheryl SealsLLM EvaluationZero-Shot Text Classification

    Department of Computer Science and Software Engineering Auburn University Auburn, Alabama, USA

  24. Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks

    Jul 23, 2026Mack Nixon, Liam Wright, Yevgeniya Kovalchuk +4AI Agent BenchmarksOpen-Weight Language Models

    Centre for Advanced Research Computing, University College London, London, UK · Centre for Longitudinal Studies, University College London, London, UK · UK Longitudinal Linkage Collaboration, University of Bristol, Bristol, UK

  25. Graph Feedback Controls Consensus and Clique Formation in Open-Weight Language-Model Populations

    Jul 13, 2026Samer Saab, Chaouki AbdallahOpen-Weight Language ModelsMulti-Agent Systems

    Lebanese American University Byblos, Lebanon · Electrical and Computer Engineering Department Lebanese American University Byblos, Lebanon

  26. modelDNA: Calibrated Lineage Verification and Merge Decomposition from Sampled Weight Fingerprints

    Jul 12, 2026Muhammad Awais Bin Adil, Saad AamirLanguage Model FingerprintingOpen-Weight Language Models

    Independent

  27. Gemma 4 Technical Report

    Jul 2, 2026Gemma Team, Sherif El Abd, Vaibhav Aggarwal +298Efficient Multimodal InferenceUnified Multimodal Models

  28. Large Databases Need Small, Open-Weight Language Models

    Jun 30, 2026Parker Glenn, Alfy SamuelSmall Language ModelsOpen-Weight Language Models

    Capital One

  29. Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs

    Jun 19, 2026Charbel El Feghali, Arkil Patel, Nicholas Meade +3Open-Weight Language ModelsLLM Security

    McGill-NLP/tiered-language-models

  30. An Empirical Study of OpenPangu Quantization on Ascend NPUs

    Jun 19, 2026Tong Shi, Jiacheng Wang, Hui Xie +4LLM QuantizationAI Accelerator Inference

    State Key Laboratory of Complex & Critical Software Environment, Beihang University · School of Artificial Intelligence, Beihang University · School of Computer Science and Engineering, Beihang University