AttaQ
Progress Over Time
Interactive timeline showing model performance evolution on AttaQ
AttaQ Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | 8B | — | — | |||
| 1 | 8B | — | — | |||
| 3 | 7B | — | — |
What is AttaQ?
AttaQ is a unique dataset containing adversarial examples in the form of questions designed to provoke harmful or inappropriate responses from large language models. The benchmark evaluates safety vulnerabilities by using specialized clustering techniques that analyze both the semantic similarity of input attacks and the harmfulness of model responses, facilitating targeted improvements to model safety mechanisms.
AttaQ is a text benchmark evaluating models on safety tasks. LLM Stats tracks 3 models on this benchmark, scored on a 0–1 scale. The current average is 0.9, with the leader at 0.9.
Compare leaders on the best AI for safety leaderboards.
Current leaders
Granite 3.3 8B Base from IBM currently leads the AttaQ leaderboard with a score of 0.885 across 3 evaluated AI models.
Source paper
- Title
- Unveiling Safety Vulnerabilities of Large Language Models
- Authors
- George Kour, Marcel Zalmanovici, Naama Zwerdling, Esther Goldbraich, and 4 others
- Published
- arXiv
- 2311.04124
Abstract
As large language models become more prevalent, their possible harmful or inappropriate responses are a cause for concern. This paper introduces a unique dataset containing adversarial examples in the form of questions, which we call AttaQ, designed to provoke such harmful or inappropriate responses. We assess the efficacy of our dataset by analyzing the vulnerabilities of various models when subjected to it. Additionally, we introduce a novel automatic approach for identifying and naming vulnerable semantic regions - input semantic areas for which the model is likely to produce harmful outputs. This is achieved through the application of specialized clustering techniques that consider both the semantic similarity of the input attacks and the harmfulness of the model's responses. Automatically identifying vulnerable semantic regions enhances the evaluation of model weaknesses, facilitating targeted improvements to its safety mechanisms and overall reliability.
FAQ
Common questions about the AttaQ benchmark and leaderboard.