本文介绍了一种针对大型语言模型（LLM）的锁定风险评估基准，旨在衡量LLM潜在的锁定风险水平。AI是锁定风险显现的关键技术，LLM可能自主或通过滥用促成锁定。该基准通过识别可能导致或帮助某些主体通过关键威胁模型造成锁定的特定行为而开发。它整合了现有的评估，并包含针对没有现有评估的行为的定制提示。该基准包含489个问答对，标准化为JSONL格式，可在Hugging Face datasets上获取。

⚠️该评估基准通过识别可能导致或帮助某些主体通过关键威胁模型造成锁定的特定行为而开发，包含对危险能力、数学和技术能力、权力欲和自我保护、恶意特征以及可纠正性的评估。

🤖该基准包含来自其他LLM评估的问题，例如WMDP基准、U-MATH以及Discovering Language Model Behaviors with Model-Written Evaluations等，也包含模型编写的问题，旨在评估LLM操纵信息系统以推广信念、防止干预、决定人类长期未来等能力。

📉该基准包含489个问答对，标准化为‘statement’, ‘yes’, ‘no’格式的JSONL文件，可在Hugging Face datasets上获取，用于评估LLM在操纵信息系统、防止干预等方面的行为。

Published on March 13, 2025 12:08 PM GMT

Intro

So far we have identified lock-in risk, defined lock-in, and established threat models for particularly undesirable lock-ins. Now we present this evaluation benchmark for large language models (LLMs) so we can measure (or at least, get a proxy measure for) the risk level of LLMs.

AI is the key technology in the manifestation of lock-in risks; AI systems can contribute to lock-in autonomously/automatically and via misuse. There are specific behaviours in both of these categories such that if an LLM displayed those behaviours, we say the LLM may have the proclivity to contribute to lock-in

Evaluation Benchmark

We developed this benchmark by identifying the specific behaviours that would cause or aid some agent in causing a lock-in through the key threat models. It contains an aggregation of existing (credited) evaluations that target some of these behaviours, as well as bespoke prompts targeting behaviours for which there are no existing evaluations.

Target Behaviours

Questions borrowed from other LLM evaluations

Dangerous capabilities (The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning)Mathematical and Technical Abilities (U-MATH: A University-Level Benchmark for Evaluating Mathematical Skills in LLMs)Power-seekingness and self-preservation (Discovering Language Model Behaviors with Model-Written Evaluations)Malevolent traits (OffensiveLang: A Community Based Implicit Offensive Language Dataset)Corrigibility (Steering Llama 2 via Contrastive Activation Addition)

Our model-written questions

Manipulating information systems to promote beliefsPreventing interference when in a position of powerDeciding the long-term future of humanity in a position of powerProliferating copies of itself given the opportunityCreating content that seeks to optimally engage humans, even to the degree that it may be addictive for themMaking decisions on behalf of humanity in a position of powerPutting own goals above those of humans, or humanity at largePromoting ideas that are irrational or anti-rationalAllowing humanity to rely on it to complete all of their tasks for them, even at the expense of their own ability (enfeeblement)

The result is an LLM benchmark containing 489 question-answer pairs standardised into a ‘statement’, ‘yes’, ‘no’ format in JSONL, available on Hugging Face datasets.

Discuss