This page is still being polished. If you have thoughts, please share them via the feedback form.
Data on this page is preliminary and may change. Please do not share or cite these figures publicly.
Training methods that shape model behavior through objectives, feedback, and optimization targets.
Also in Model
Toxicity filtering during the pre-training stage requires training LLMs from scratch, which is impractical for many applications. Therefore, detoxification during the fine-tuning stage offers a more flexible way to deal with toxicity in LLMs.
Gehman et al. (2020) employ the DAPT framework (Gururangan et al., 2020) to further train GPT-2 on a non-toxic subset of the OpenWebTextCorpus (OWTC).6 Similarly, Solaiman & Dennison (2021) fine-tune LLMs by constructing small, high-quality datasets that reflect specific social values, aligning the behaviors of the fine-tuned LLMs with those values. They use toxicity assessments and human evaluations to guide the generation of additional training samples, progressively improving the LLMs. In addition to human-curated and web-extracted data, fine-tuning on model-generated data has also proven effective. Wang et al. (2022) identify the least toxic documents from text randomly generated by LLMs, segmenting them into prompts and continuations to create low-toxicity prompts for fine-tuning. The study also explores parameter-efficient fine-tuning techniques, such as adapters (Houlsby et al., 2019) and prefix-tuning (Li & Liang, 2021), as alternatives to full parameter fine-tuning. Results indicate that, compared to full fine-tuning, adapters effectively reduce toxicity while controlling model perplexity.
Reasoning
Supervised fine-tuning shapes model behavior through training objectives targeting toxicity reduction.
Value Misalignment
99.9 OtherValue Misalignment > Mitigating social bias
1 AI SystemValue Misalignment > Privacy protection
1 AI SystemValue Misalignment > Methods for mitigating toxicity
1 AI SystemValue Misalignment > Methods for mitigating LLM amorality
1 AI SystemRobustness to attack
1 AI SystemLarge Language Model Safety: A Holistic Survey
Shi, Dan; Shen, Tianhao; Huang, Yufei; Li, Zhigen; Leng, Yongqi; Jin, Renren; Liu, Chuang; Wu, Xinwei; Guo, Zishan; Yu, Linhao; Shi, Ling; Jiang, Bojian; Xiong, Deyi (2024)
The rapid development and deployment of large language models (LLMs) have introduced a new frontier in artificial intelligence, marked by unprecedented capabilities in natural language understanding and generation. However, the increasing integration of these models into critical applications raises substantial safety concerns, necessitating a thorough examination of their potential risks and associated mitigation strategies. This survey provides a comprehensive overview of the current landscape of LLM safety, covering four major categories: value misalignment, robustness to adversarial attacks, misuse, and autonomous AI risks. In addition to the comprehensive review of the mitigation methodologies and evaluation resources on these four aspects, we further explore four topics related to LLM safety: the safety implications of LLM agents, the role of interpretability in enhancing LLM safety, the technology roadmaps proposed and abided by a list of AI companies and institutes for LLM safety, and AI governance aimed at LLM safety with discussions on international cooperation, policy proposals, and prospective regulatory directions. Our findings underscore the necessity for a proactive, multifaceted approach to LLM safety, emphasizing the integration of technical solutions, ethical considerations, and robust governance frameworks. This survey is intended to serve as a foundational resource for academy researchers, industry practitioners, and policymakers, offering insights into the challenges and opportunities associated with the safe integration of LLMs into society. Ultimately, it seeks to contribute to the safe and beneficial development of LLMs, aligning with the overarching goal of harnessing AI for societal advancement and well-being. A curated list of related papers has been publicly available at https://github.com/tjunlp-lab/Awesome-LLM-Safety-Papers.
Build and Use Model
Training, fine-tuning, and integrating the AI model
Developer
Entity that creates, trains, or modifies the AI system
Manage
Prioritising, responding to, and mitigating AI risks
