BELLS: A Framework Towards Future Proof Benchmarks for the Evaluation of LLM Safeguards

• URL: http://arxiv.org/abs/2406.01364v1
• Date: Mon, 3 Jun 2024 14:32:30 GMT
• Title: BELLS: A Framework Towards Future Proof Benchmarks for the Evaluation of LLM Safeguards
• Authors: Diego Dorn, Alexandre Variengien, Charbel-Raphaël Segerie, Vincent Corruble,
• Abstract summary: We introduce the Benchmarks for the Evaluation of LLM Safeguards (BELLS) BELLS is a structured collection of tests, organized into three categories: established failure tests, emerging failure tests and next-gen architecture tests. We implement and share the first next-gen architecture test, using the MACHIAVELLI environment, along with an interactive visualization of the dataset.
• Score: 43.86118338226387
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Input-output safeguards are used to detect anomalies in the traces produced by Large Language Models (LLMs) systems. These detectors are at the core of diverse safety-critical applications such as real-time monitoring, offline evaluation of traces, and content moderation. However, there is no widely recognized methodology to evaluate them. To fill this gap, we introduce the Benchmarks for the Evaluation of LLM Safeguards (BELLS), a structured collection of tests, organized into three categories: (1) established failure tests, based on already-existing benchmarks for well-defined failure modes, aiming to compare the performance of current input-output safeguards; (2) emerging failure tests, to measure generalization to never-seen-before failure modes and encourage the development of more general safeguards; (3) next-gen architecture tests, for more complex scaffolding (such as LLM-agents and multi-agent systems), aiming to foster the development of safeguards that could adapt to future applications for which no safeguard currently exists. Furthermore, we implement and share the first next-gen architecture test, using the MACHIAVELLI environment, along with an interactive visualization of the dataset.

Related papers

• PaCoST: Paired Confidence Significance Testing for Benchmark Contamination Detection in Large Language Models [41.772263447213234]
  Large language models (LLMs) are known to be trained on vast amounts of data, which may unintentionally or intentionally include data from commonly used benchmarks. This inclusion can lead to cheatingly high scores on model leaderboards, yet result in disappointing performance in real-world applications. We introduce PaCoST, a Paired Confidence Significance Testing to effectively detect benchmark contamination in LLMs.
  arXiv  Detail & Related papers  (2024-06-26T13:12:40Z)
• Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph [85.51252685938564]
  Uncertainty quantification (UQ) is becoming increasingly recognized as a critical component of applications that rely on machine learning (ML) As with other ML models, large language models (LLMs) are prone to make incorrect predictions, hallucinate'' by fabricating claims, or simply generate low-quality output for a given input. We introduce a novel benchmark that implements a collection of state-of-the-art UQ baselines, and provides an environment for controllable and consistent evaluation of novel techniques.
  arXiv  Detail & Related papers  (2024-06-21T20:06:31Z)
• Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations [76.19419888353586]
  Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations. We present our efforts to create and deploy a library of detectors: compact and easy-to-build classification models that provide labels for various harms.
  arXiv  Detail & Related papers  (2024-03-09T21:07:16Z)
• TRUCE: Private Benchmarking to Prevent Contamination and Improve Comparative Evaluation of LLMs [12.839640915518443]
  Benchmarking is the de-facto standard for evaluating LLMs, due to its speed, replicability and low cost. Recent work has pointed out that the majority of the open source benchmarks available today have been contaminated or leaked into LLMs. We propose Private Benchmarking, a solution where test datasets are kept private and models are evaluated without revealing the test data to the model.
  arXiv  Detail & Related papers  (2024-03-01T09:28:38Z)
• Self-Evaluation Improves Selective Generation in Large Language Models [54.003992911447696]
  We reformulate open-ended generation tasks into token-level prediction tasks. We instruct an LLM to self-evaluate its answers. We benchmark a range of scoring methods based on self-evaluation.
  arXiv  Detail & Related papers  (2023-12-14T19:09:22Z)
• Towards Reliable AI: Adequacy Metrics for Ensuring the Quality of System-level Testing of Autonomous Vehicles [5.634825161148484]
  We introduce a set of black-box test adequacy metrics called "Test suite Instance Space Adequacy" (TISA) metrics. The TISA metrics offer a way to assess both the diversity and coverage of the test suite and the range of bugs detected during testing. We evaluate the efficacy of the TISA metrics by examining their correlation with the number of bugs detected in system-level simulation testing of AVs.
  arXiv  Detail & Related papers  (2023-11-14T10:16:05Z)
• Don't Make Your LLM an Evaluation Benchmark Cheater [142.24553056600627]
  Large language models(LLMs) have greatly advanced the frontiers of artificial intelligence, attaining remarkable improvement in model capacity. To assess the model performance, a typical approach is to construct evaluation benchmarks for measuring the ability level of LLMs. We discuss the potential risk and impact of inappropriately using evaluation benchmarks and misleadingly interpreting the evaluation results.
  arXiv  Detail & Related papers  (2023-11-03T14:59:54Z)
• DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection [55.70982767084996]
  A critical yet frequently overlooked challenge in the field of deepfake detection is the lack of a standardized, unified, comprehensive benchmark. We present the first comprehensive benchmark for deepfake detection, called DeepfakeBench, which offers three key contributions. DeepfakeBench contains 15 state-of-the-art detection methods, 9CL datasets, a series of deepfake detection evaluation protocols and analysis tools, as well as comprehensive evaluations.
  arXiv  Detail & Related papers  (2023-07-04T01:34:41Z)
• Unifying Evaluation of Machine Learning Safety Monitors [0.0]
  runtime monitors have been developed to detect prediction errors and keep the system in a safe state during operations. This paper introduces three unified safety-oriented metrics, representing the safety benefits of the monitor (Safety Gain) and the remaining safety gaps after using it (Residual Hazard) Three use-cases (classification, drone landing, and autonomous driving) are used to demonstrate how metrics from the literature can be expressed in terms of the proposed metrics.
  arXiv  Detail & Related papers  (2022-08-31T07:17:42Z)
• Benchmarking Safety Monitors for Image Classifiers with Machine Learning [0.0]
  High-accurate machine learning (ML) image classifiers cannot guarantee that they will not fail at operation. The use of fault tolerance mechanisms such as safety monitors is a promising direction to keep the system in a safe state. This paper aims at establishing a baseline framework for benchmarking monitors for ML image classifiers.
  arXiv  Detail & Related papers  (2021-10-04T07:52:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.