if you need more than one keyword, modify and separate by underscore _
the list of search keywords can be up to 50 characters long
if you modify the keywords, press enter within the field to confirm the new search key
Tag: sycophancy
Bibliography items where occurs: 17
- Specific versus General Principles for Constitutional AI / 2310.13798 / ISBN:https://doi.org/10.48550/arXiv.2310.13798 / Published by ArXiv / Version released on 2023-10-20 / on (web) Publishing site
- How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities / 2311.09447 / ISBN:https://doi.org/10.48550/arXiv.2311.09447 / Published by ArXiv / Version released on 2024-04-02 / on (web) Publishing site
- AI Alignment: A Comprehensive Survey / 2310.19852 / ISBN:https://doi.org/10.48550/arXiv.2310.19852 / Published by ArXiv / Version released on 2025-04-04 / on (web) Publishing site
- The AI Alignment Paradox / 2405.20806 / ISBN:https://doi.org/10.48550/arXiv.2405.20806 / Published by ArXiv / Version released on 2024-11-22 / on (web) Publishing site
- AI Alignment through Reinforcement Learning from Human Feedback? Contradictions and Limitations / 2406.18346 / ISBN:https://doi.org/10.48550/arXiv.2406.18346 / Published by ArXiv / Version released on 2024-06-26 / on (web) Publishing site
- Digital Homunculi: Reimagining Democracy Research with Generative Agents / 2409.00826 / ISBN:https://doi.org/10.48550/arXiv.2409.00826 / Published by ArXiv / Version released on 2024-09-01 / on (web) Publishing site
- TRIAGE: Ethical Benchmarking of AI Models Through Mass Casualty Simulations / 2410.18991 / ISBN:https://doi.org/10.48550/arXiv.2410.18991 / Published by ArXiv / Version released on 2024-11-04 / on (web) Publishing site
- Chat Bankman-Fried: an Exploration of LLM Alignment in Finance / 2411.11853 / ISBN:https://doi.org/10.48550/arXiv.2411.11853 / Published by ArXiv / Version released on 2024-11-21 / on (web) Publishing site
- Prioritization First, Principles Second: An Adaptive Interpretation of Helpful, Honest, and Harmless Principles / 2502.06059 / ISBN:https://doi.org/10.48550/arXiv.2502.06059 / Published by ArXiv / Version released on 2025-10-14 / on (web) Publishing site
- On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective / 2502.14296 / ISBN:https://doi.org/10.48550/arXiv.2502.14296 / Published by ArXiv / Version released on 2025-09-30 / on (web) Publishing site
- DarkBench: Benchmarking Dark Patterns in Large Language Models / 2503.10728 / ISBN:https://doi.org/10.48550/arXiv.2503.10728 / Published by ArXiv / Version released on 2025-03-13 / on (web) Publishing site
- Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions
/ 2504.15236 / ISBN:https://doi.org/10.48550/arXiv.2504.15236 / Published by ArXiv / Version released on 2025-04-21 / on (web) Publishing site
- The Silicon Reasonable Person: Can AI Predict How Ordinary People Judge Reasonableness? / 2508.02766 / ISBN:https://doi.org/10.48550/arXiv.2508.02766 / Published by ArXiv / Version released on 2025-08-04 / on (web) Publishing site
- Psychometric Personality Shaping Modulates Capabilities and Safety in Language Models / 2509.16332 / ISBN:https://doi.org/10.48550/arXiv.2509.16332 / Published by ArXiv / Version released on 2025-09-19 / on (web) Publishing site
- Diverse Human Value Alignment for Large Language Models via Ethical Reasoning / 2511.00379 / ISBN:https://doi.org/10.48550/arXiv.2511.00379 / Published by ArXiv / Version released on 2025-11-01 / on (web) Publishing site
- Systematizing LLM Persona Design: A Four-Quadrant Technical Taxonomy for AI Companion Applications
/ 2511.02979 / ISBN:https://doi.org/10.48550/arXiv.2511.02979 / Published by ArXiv / Version released on 2025-11-04 / on (web) Publishing site
- The Workflow as Medium: A Framework for Navigating Human-AI Co-Creation / 2511.18182 / ISBN:https://doi.org/10.48550/arXiv.2511.18182 / Version released on 2025-11-22 / on (web) Publishing site