When in Doubt, Cascade: Towards Building Efficient and Capable Guardrails

• URL: http://arxiv.org/abs/2407.06323v1
• Date: Mon, 8 Jul 2024 18:39:06 GMT
• Title: When in Doubt, Cascade: Towards Building Efficient and Capable Guardrails
• Authors: Manish Nagireddy, Inkit Padhi, Soumya Ghosh, Prasanna Sattigeri,
• Abstract summary: We develop a synthetic pipeline to generate targeted and labeled data. We show that our method achieves competitive performance with a fraction of the cost in compute.
• Score: 19.80434777786657
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have convincing performance in a variety of downstream tasks. However, these systems are prone to generating undesirable outputs such as harmful and biased text. In order to remedy such generations, the development of guardrail (or detector) models has gained traction. Motivated by findings from developing a detector for social bias, we adopt the notion of a use-mention distinction - which we identified as the primary source of under-performance in the preliminary versions of our social bias detector. Armed with this information, we describe a fully extensible and reproducible synthetic data generation pipeline which leverages taxonomy-driven instructions to create targeted and labeled data. Using this pipeline, we generate over 300K unique contrastive samples and provide extensive experiments to systematically evaluate performance on a suite of open source datasets. We show that our method achieves competitive performance with a fraction of the cost in compute and offers insight into iteratively developing efficient and capable guardrail models. Warning: This paper contains examples of text which are toxic, biased, and potentially harmful.

Related papers

• Sub-graph Based Diffusion Model for Link Prediction [43.15741675617231]
  Denoising Diffusion Probabilistic Models (DDPMs) represent a contemporary class of generative models with exceptional qualities. We build a novel generative model for link prediction using a dedicated design to decompose the likelihood estimation process via the Bayesian formula. Our proposed method presents numerous advantages: (1) transferability across datasets without retraining, (2) promising generalization on limited training data, and (3) robustness against graph adversarial attacks.
  arXiv  Detail & Related papers  (2024-09-13T02:23:55Z)
• DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception [78.26734070960886]
  Current perceptive models heavily depend on resource-intensive datasets. We introduce perception-aware loss (P.A. loss) through segmentation, improving both quality and controllability. Our method customizes data augmentation by extracting and utilizing perception-aware attribute (P.A. Attr) during generation.
  arXiv  Detail & Related papers  (2024-03-20T04:58:03Z)
• Root Causing Prediction Anomalies Using Explainable AI [3.970146574042422]
  We present a novel application of explainable AI (XAI) for root-causing performance degradation in machine learning models. A single feature corruption can cause cascading feature, label and concept drifts. We have successfully applied this technique to improve the reliability of models used in personalized advertising.
  arXiv  Detail & Related papers  (2024-03-04T19:38:50Z)
• Improving the Robustness of Summarization Systems with Dual Augmentation [68.53139002203118]
  A robust summarization system should be able to capture the gist of the document, regardless of the specific word choices or noise in the input. We first explore the summarization models' robustness against perturbations including word-level synonym substitution and noise. We propose a SummAttacker, which is an efficient approach to generating adversarial samples based on language models.
  arXiv  Detail & Related papers  (2023-06-01T19:04:17Z)
• Provable Robustness for Streaming Models with a Sliding Window [51.85182389861261]
  In deep learning applications such as online content recommendation and stock market analysis, models use historical data to make predictions. We derive robustness certificates for models that use a fixed-size sliding window over the input stream. Our guarantees hold for the average model performance across the entire stream and are independent of stream size, making them suitable for large data streams.
  arXiv  Detail & Related papers  (2023-03-28T21:02:35Z)
• Interpretable Data-Based Explanations for Fairness Debugging [7.266116143672294]
  Gopher is a system that produces compact, interpretable, and causal explanations for bias or unexpected model behavior. We introduce the concept of causal responsibility that quantifies the extent to which intervening on training data by removing or updating subsets of it can resolve the bias. Building on this concept, we develop an efficient approach for generating the top-k patterns that explain model bias.
  arXiv  Detail & Related papers  (2021-12-17T20:10:00Z)
• Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models [0.06372261626436676]
  Out-of-distribution (OOD) detection is an important task in machine learning systems. Deep probabilistic generative models facilitate OOD detection by estimating the likelihood of a data sample. We propose a new detection metric that operates without outlier exposure.
  arXiv  Detail & Related papers  (2021-06-15T06:36:10Z)
• Hidden Biases in Unreliable News Detection Datasets [60.71991809782698]
  We show that selection bias during data collection leads to undesired artifacts in the datasets. We observed a significant drop (>10%) in accuracy for all models tested in a clean split with no train/test source overlap. We suggest future dataset creation include a simple model as a difficulty/bias probe and future model development use a clean non-overlapping site and date split.
  arXiv  Detail & Related papers  (2021-04-20T17:16:41Z)
• Negative Data Augmentation [127.28042046152954]
  We show that negative data augmentation samples provide information on the support of the data distribution. We introduce a new GAN training objective where we use NDA as an additional source of synthetic data for the discriminator. Empirically, models trained with our method achieve improved conditional/unconditional image generation along with improved anomaly detection capabilities.
  arXiv  Detail & Related papers  (2021-02-09T20:28:35Z)
• Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation [51.29486247405601]
  We design a framework to generate counterfactuals for raw data instances with the proposed Attribute-Informed Perturbation (AIP) By utilizing generative models conditioned with different attributes, counterfactuals with desired labels can be obtained effectively and efficiently. Experimental results on real-world texts and images demonstrate the effectiveness, sample quality as well as efficiency of our designed framework.
  arXiv  Detail & Related papers  (2021-01-18T08:37:13Z)

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.