_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: gemma
Bibliography items where occurs: 19
- Unlocking the Potential of ChatGPT: A Comprehensive Exploration of its Applications, Advantages, Limitations, and Future Directions in Natural Language Processing / 2304.02017 / ISBN:https://doi.org/10.48550/arXiv.2304.02017 / Published by ArXiv / on (web) Publishing site
- 3 Transformers and pre-trained language models
- The Future of Child Development in the AI Era. Cross-Disciplinary Perspectives Between AI and Child Development Experts / 2405.19275 / ISBN:https://doi.org/10.48550/arXiv.2405.19275 / Published by ArXiv / on (web) Publishing site
- 1. Introduction
- How Ethical Should AI Be? How AI Alignment Shapes the Risk Preferences of LLMs / 2406.01168 / ISBN:https://doi.org/10.48550/arXiv.2406.01168 / Published by ArXiv / on (web) Publishing site
- II. Risk Characteristics of LLMs
- MoralBench: Moral Evaluation of LLMs / 2406.04428 / Published by ArXiv / on (web) Publishing site
- 4 Experiments
- The Ethics of Interaction: Mitigating Security Threats in LLMs / 2401.12273 / ISBN:https://doi.org/10.48550/arXiv.2401.12273 / Published by ArXiv / on (web) Publishing site
- 1 Introduction
- Open Artificial Knowledge / 2407.14371 / ISBN:https://doi.org/10.48550/arXiv.2407.14371 / Published by ArXiv / on (web) Publishing site
- Abstract
3. OAK Dataset
6. Conclusion and Future Work
Appendices - VersusDebias: Universal Zero-Shot Debiasing for Text-to-Image Models via SLM-Based Prompt Engineering and Generative Adversary / 2407.19524 / ISBN:https://doi.org/10.48550/arXiv.2407.19524 / Published by ArXiv / on (web) Publishing site
- 4 Experiment
- ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs / 2409.09586 / ISBN:https://doi.org/10.48550/arXiv.2409.09586 / Published by ArXiv / on (web) Publishing site
- 3 ValueCompass Framework
4 Experimental Settings
5 Results - Learning Human-like Representations to Enable Learning Human Values / 2312.14106 / ISBN:https://doi.org/10.48550/arXiv.2312.14106 / Published by ArXiv / on (web) Publishing site
- A. Appendix
- Improving governance outcomes through AI documentation: Bridging theory and practice / 2409.08960 / ISBN:https://doi.org/10.48550/arXiv.2409.08960 / Published by ArXiv / on (web) Publishing site
- The doctor will polygraph you now: ethical concerns with AI for fact-checking patients / 2408.07896 / ISBN:https://doi.org/10.48550/arXiv.2408.07896 / Published by ArXiv / on (web) Publishing site
- 4. Results
- Large-scale moral machine experiment on large language models / 2411.06790 / ISBN:https://doi.org/10.48550/arXiv.2411.06790 / Published by ArXiv / on (web) Publishing site
- Abstract
Introduction
Materials and methods
Results
Discussion - Safety at Scale: A Comprehensive Survey of Large Model Safety / 2502.05206 / ISBN:https://doi.org/10.48550/arXiv.2502.05206 / Published by ArXiv / on (web) Publishing site
- 3 Large Language Model Safety
- 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 / on (web) Publishing site
- 1 Introduction
2 Background
4 Designing TrustGen, a Dynamic Benchmark Platform for Evaluating the Trustworthiness of GenFMs
6 Benchmarking Large Language Models - Comprehensive Analysis of Transparency and Accessibility of ChatGPT, DeepSeek, And other SoTA Large Language Models / 2502.18505 / ISBN:https://doi.org/10.48550/arXiv.2502.18505 / Published by ArXiv / on (web) Publishing site
- 3. Results
- MinorBench: A hand-built benchmark for content-based risks for children / 2503.10242 / ISBN:https://doi.org/10.48550/arXiv.2503.10242 / Published by ArXiv / on (web) Publishing site
- 2 Literature Review
- ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs / 2409.09586 / ISBN:https://doi.org/10.48550/arXiv.2409.09586 / Published by ArXiv / on (web) Publishing site
- Appendices
- Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs / 2505.02009 / ISBN:https://doi.org/10.48550/arXiv.2505.02009 / Published by ArXiv / on (web) Publishing site
- 4 Topical and Toxic Prompt (TTP)
6 Results - Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data / 2505.09974 / ISBN:https://doi.org/10.48550/arXiv.2505.09974 / Published by ArXiv / on (web) Publishing site
- Abstract
2 Related Work
3 Methodology
4 Results - Are Language Models Consequentialist or Deontological Moral Reasoners? / 2505.21479 / ISBN:https://doi.org/10.48550/arXiv.2505.21479 / Published by ArXiv / on (web) Publishing site
- 4 Methodology
5 Experimental Findings
Appendix