Responsibility & Safety
As part of our Responsible release approach, we followed a three-pronged strategy to managing trust & safety risks:
- Enable developers to deploy helpful, safe, and flexible experiences for their target audience and for the use cases supported by Llama.
- Protect developers against adversarial users aiming to exploit Llama capabilities to potentially cause harm.
- Provide protections for the community to help prevent the misuse of our models.
Responsible Deployment
Llama is a foundational technology designed to be used in a variety of use cases. Examples of how Meta’s Llama models have been responsibly deployed can be found in our Community Stories webpage. Our approach is to build the most helpful models enabling the world to benefit from the technology's power by aligning our model safety for the generic use cases addressing a standard set of harms. Developers are then in the driver's seat to tailor safety for their use case, defining their own policy and deploying the models with the necessary safeguards in their Llama systems. Llama 3.1 was developed following the best practices outlined in our Responsible Use Guide. You can refer to the Responsible Use Guide to learn more.
Llama 3.1 Instruct
Our main objectives for conducting safety fine-tuning are to provide the research community with a valuable resource for studying the robustness of safety fine-tuning, as well as to offer developers a readily available, safe, and powerful model for various applications to reduce the developer workload to deploy safe AI systems. For more details on the safety mitigations implemented, please read the Llama 3 paper.
Fine-Tuning Data
We employ a multi-faceted approach to data collection, combining human-generated data from our vendors with synthetic data to mitigate potential safety risks. Weʼve developed many large language model (LLM)-based classifiers that enable us to thoughtfully select high-quality prompts and responses, enhancing data quality control.
Refusals and Tone
Building on the work we started with Llama 3, we put a great emphasis on model refusals to benign prompts as well as refusal tone. We included both borderline and adversarial prompts in our safety data strategy and modified our safety data responses to follow tone guidelines.
Llama 3.1 Systems
Large language models, including Llama 3.1, are not designed to be deployed in isolation but instead should be deployed as part of an overall AI system with additional safety guardrails as required. Developers are expected to deploy system safeguards when building agentic systems. Safeguards are key to achieving the right helpfulness-safety alignment as well as mitigating safety and security risks inherent to the system and any integration of the model or system with external tools.
As part of our responsible release approach, we provide the community with safeguards that developers should deploy with Llama models or other LLMs, including Llama Guard 3, Prompt Guard, and Code Shield. All our reference implementation demos contain these safeguards by default, so developers can benefit from system-level safety out-of-the-box.
New Capabilities
Note that this release introduces new capabilities, including a longer context window, multilingual inputs and outputs, and possible integrations by developers with third-party tools. Building with these new capabilities requires specific considerations in addition to the best practices that generally apply across all Generative AI use cases.
-
Tool-use: Just like in standard software development, developers are responsible for the integration of the LLM with the tools and services of their choice. They should define a clear policy for their use case and assess the integrity of the third-party services they use to be aware of the safety and security limitations when using this capability. Refer to the Responsible Use Guide for best practices on the safe deployment of third-party safeguards.
-
Multilinguality: Llama 3.1 supports 7 languages in addition to English: French, German, Hindi, Italian, Portuguese, Spanish, and Thai. Llama may be able to output text in other languages beyond those that meet performance thresholds for safety and helpfulness. We strongly discourage developers from using this model to converse in non-supported languages without implementing fine-tuning and system controls in alignment with their policies and the best practices shared in the Responsible Use Guide.
Evaluations
We evaluated Llama models for common use cases as well as specific capabilities. Common use case evaluations measure safety risks of systems for most commonly built applications including chatbots, coding assistants, and tool calls. We built dedicated, adversarial evaluation datasets and evaluated systems composed of Llama models and Llama Guard 3 to filter input prompts and output responses. It is important to evaluate applications in context, and we recommend building a dedicated evaluation dataset for your use case. Prompt Guard and Code Shield are also available if relevant to the application.
Capability evaluations measure vulnerabilities of Llama models inherent to specific capabilities, for which we crafted dedicated benchmarks, including long context, multilingual, tool calls, coding, or memorization.
Red Teaming
For both scenarios, we conducted recurring red teaming exercises with the goal of discovering risks via adversarial prompting, and we used the learnings to improve our benchmarks and safety tuning datasets.
We partnered early with subject-matter experts in critical risk areas to understand the nature of these real-world harms and how such models may lead to unintended harm for society. Based on these conversations, we derived a set of adversarial goals for the red team to attempt to achieve, such as extracting harmful information or reprogramming the model to act in a potentially harmful capacity. The red team consisted of experts in cybersecurity, adversarial machine learning, responsible AI, and integrity in addition to multilingual content specialists with backgrounds in integrity issues in specific geographic markets.
Critical and Other Risks
We specifically focused our efforts on mitigating the following critical risk areas:
-
CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive materials) Helpfulness
To assess risks related to the proliferation of chemical and biological weapons, we performed uplift testing designed to assess whether the use of Llama 3.1 models could meaningfully increase the capabilities of malicious actors to plan or carry out attacks using these types of weapons.
-
Child Safety
Child Safety risk assessments were conducted using a team of experts to assess the modelʼs capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine-tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective-based methodologies to assess the model risks along multiple attack vectors, including the additional languages Llama 3 is trained on. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking into account market-specific nuances or experiences.
-
Cyber Attack Enablement
Our cyber attack uplift study investigated whether LLMs can enhance human capabilities in hacking tasks, both in terms of skill level and speed.
Our attack automation study focused on evaluating the capabilities of LLMs when used as autonomous agents in cyber offensive operations, specifically in the context of ransomware attacks. This evaluation was distinct from previous studies that considered LLMs as interactive assistants. The primary objective was to assess whether these models could effectively function as independent agents in executing complex cyber-attacks without human intervention.
Our study of Llama-3.1-405Bʼs social engineering uplift for cyber attackers was conducted to assess the effectiveness of AI models in aiding cyber threat actors in spear phishing campaigns. Please read our Llama 3.1 Cybersecurity whitepaper to learn more.
Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership on AI, and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open-sourced for the community to use and widely distributed across ecosystem partners, including cloud service providers. We encourage community contributions to our GitHub repository.
We also set up the Llama Impact Grants program to identify and support the most compelling applications of Metaʼs Llama model for societal benefit across three categories: education, climate, and open innovation.
Finally, we put in place a set of resources, including an output reporting mechanism and bug bounty program, to continuously improve the Llama technology with the help of the community.
Ethical Considerations and Limitations
The core values of Llama 3.1 are openness, inclusivity, and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences, and perspectives. Llama 3.1 addresses users and their needs as they are, without unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3.1 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3.1ʼs potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased, or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3.1 models, developers should perform safety testing and tuning tailored to their specific applications of the model. Please refer to available resources including our Responsible Use Guide, Trust and Safety solutions, and other resources to learn more about responsible development.