Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.03939 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914140215312384 |
|---|---|
| author | Sharma, Raghav Mehta, Manan Raina, Sai Tiger |
| author_facet | Sharma, Raghav Mehta, Manan Raina, Sai Tiger |
| contents | Reinforcement Learning from Human Feedback (RLHF) is the standard for aligning Large Language Models (LLMs), yet recent progress has moved beyond canonical text-based methods. This survey synthesizes the new frontier of alignment research by addressing critical gaps in multi-modal alignment, cultural fairness, and low-latency optimization. To systematically explore these domains, we first review foundational algo- rithms, including PPO, DPO, and GRPO, before presenting a detailed analysis of the latest innovations. By providing a comparative synthesis of these techniques and outlining open challenges, this work serves as an essential roadmap for researchers building more robust, efficient, and equitable AI systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_03939 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RLHF: A comprehensive Survey for Cultural, Multimodal and Low Latency Alignment Methods Sharma, Raghav Mehta, Manan Raina, Sai Tiger Machine Learning Artificial Intelligence Computation and Language Reinforcement Learning from Human Feedback (RLHF) is the standard for aligning Large Language Models (LLMs), yet recent progress has moved beyond canonical text-based methods. This survey synthesizes the new frontier of alignment research by addressing critical gaps in multi-modal alignment, cultural fairness, and low-latency optimization. To systematically explore these domains, we first review foundational algo- rithms, including PPO, DPO, and GRPO, before presenting a detailed analysis of the latest innovations. By providing a comparative synthesis of these techniques and outlining open challenges, this work serves as an essential roadmap for researchers building more robust, efficient, and equitable AI systems. |
| title | RLHF: A comprehensive Survey for Cultural, Multimodal and Low Latency Alignment Methods |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2511.03939 |