Aligning Large Language Models with Human: A Survey

By Yufei Wang, Wanjun Zhong, Liangyou Li, Fei Mi, Xingshan Zeng, Wenyong Huang, Lifeng Shang, Xin Jiang, Qun Liu. arXiv.org, 2023

495 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Materials Chemistry

View Paper: https://www.semanticscholar.org/paper/ac771182d1780c863954243809d1e144433919f9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Fan Yang
2. Deyi Xiong
3. Hai Zhao
4. Mengzhou Xia
5. Yangsibo Huang
6. Wei Cheng
7. Zhang Tao
8. Xinwei Wu

In Materials Chemistry

1. Zhang Tao

Citations in the corpus

• Large Language Model Alignment: A Survey (2023, background): “In response to the ever-growing interest in this area, a few articles have recently reviewed (or incidentally discussed) alignment methods for LLMs (Pan et al., 2023; Zhao et al., 2023b; Fernandes et al., 2023; Liu et al., 2023d; Wang et al., 2023d).”
• A Comprehensive Overview of Large Language Models (2023, unknown): “1: The trends in the number of LLM models introduced over the years.”
• Making Large Language Models Better Reasoners with Alignment (2023, unknown): “Preference alignment research focuses on directing AI systems toward human-intended preferences Wang et al. (2023e).”
• A survey on large language model based autonomous agents (2023, unknown): “For example, in [20], the authors employ many an-notators, and ask them to provide feedback on five key questions that directly associated with the agent capability.”
• A Survey on the Memory Mechanism of Large Language Model-based Agents (2024, unknown): “In addition, cognitive psychology has been studied for a long time, so many effective human memory theories and architectures have been accumulated, which can support more advanced capabilities of the agents [147].”
• A Survey on Large Language Models for Code Generation (2024, unknown): “While significant efforts have been dedicated to the performance evaluation of LLMs, most of these research questions remain unanswered, such as: “Are the evaluations and comparisons fair and are the differences significant?” or “Do findings from performance evaluation truly reflect the usability…”
• Baichuan 2: Open Large-scale Language Models (2023, background): “Most of them fine-tune the foundation models to align with human (OpenAI, 2022; Wang et al., 2023).”
• Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation (2023, methodology): “While there are a variety of different techniques suggested for improving alignment in LLMs (Ouyang et al., 2022; Bai et al., 2022a; Glaese et al., 2022; Korbak et al., 2023; Zhou et al., 2023; Wang et al., 2023), the most popular models follow the same overall strategy.”