Prompt Robustness

Ask about this topic

Momentum

0 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 12

All topics
CardsList

  1. Prompt-Robust Language Models: Which Training Strategies Work?

    Sep 1, 2026Frederic Sadrieh, Michal ŠtefánikPrompt SensitivityLLM Fine-Tuning

    Center for Information and Language Processing, LMU Munich · R&D Centre for Large Language Models, National Institute of Informatics, Japan

  2. Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety

    Aug 13, 2026Ping Wu, Haibo Tong, Feifei Zhao +7LLM Safety AlignmentLLM Refusal Behavior

    BrainCog Lab, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · Beijing Key Laboratory of Safe AI and Superalignment +2

  3. Improving Generalization Robustness of Multimodal RLVR

    Aug 9, 2026Pengfei Zhou, Zhiwei Tang, Xiaopeng Peng +11Multimodal RobustnessMultimodal Large Language Models

    1National University of Singapore, HPC-AI Lab · 2DAMO Academy, Alibaba Group · 3Hupan Lab +7

  4. BASIS: Breach-Aware Selective Prompt Injection Shielding with Prefill Attention Probes

    Aug 8, 2026Laiqiao Qin, Tianqing Zhu, Longxiang Gao +1Prompt Injection DefensePrompt Injection Attacks on LLMs

    City University of Macau, Macau · Qilu University of Technology

  5. Prompt Robustness Is Task-Dependent: Comparing Objective and Belief-Style Questions in LLM Evaluation

    Jul 6, 2026Sadia Kamal, Arefa Patwary, Anthony Marchiafava +2LLM EvaluationLanguage Model Generation Evaluation

    Oklahoma State University · University of North Texas

  6. MPSelectTune: Prompt-type Selection for Fine-tuning improves Concept Unlearning in LLMs

    Jul 4, 2026Shubhadip Nag, Srinjoy Das, Agniva Saha +5LLM Fine-TuningMachine Unlearning

    *IIT Kharagpur · †MPI-SWS · ‡HPE Labs

  7. Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming

    Jun 3, 2026Nicholas SabanComputer-Use AgentsAI Agent Safety

    Patronus AI · University of California, Berkeley

  8. Harnessing non-adversarial robustness in large language models

    May 28, 2026Qinghua Zhou, Ellina Aleshina, Andrey Lovyagin +6LLM Fine-TuningNeural Network Robustness

    International Joint Laboratory of AI for Industry, QUST, Qingdao, China · King’s College London, London, UK · Applied AI Institute, Moscow, Russia +2

  9. One prompt is not enough: Instruction Sensitivity Undermines Embedding Model Evaluation

    May 21, 2026Yevhen Kostiuk, Kenneth EnevoldsenPrompt SensitivityText Embedding Evaluation

    Aarhus University

  10. What Single-Prompt Accuracy Misses: A Multi-Variant Reliability Audit of Language Models

    May 3, 2026Ranit Karmakar, Jayita ChatterjeeLLM EvaluationLanguage Model Calibration

    Harvard University, Boston, MA 02115 · Boston, MA 02134

  11. Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models

    May 2, 2026Zhuoyun Li, Boxuan Wang, Jinwei Hu +6Neural Network RobustnessNoise Robustness

    School of Computer Science and Informatics, University of Liverpool, UK

  12. Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMs

    Oct 16, 2025Parsa Hejabi, Elnaz Rahmati, Alireza S. Ziabari +1Unsupervised LearningLanguage Model Robustness

    University of Southern California