NLP Verification: Towards a General Methodology for Certifying Robustness

• URL: http://arxiv.org/abs/2403.10144v2
• Date: Fri, 31 May 2024 13:11:15 GMT
• Title: NLP Verification: Towards a General Methodology for Certifying Robustness
• Authors: Marco Casadio, Tanvi Dinkar, Ekaterina Komendantskaya, Luca Arnaboldi, Matthew L. Daggitt, Omri Isac, Guy Katz, Verena Rieser, Oliver Lemon,
• Abstract summary: We discuss the technical challenge of semantic generalisability of verified subspaces. We propose a general methodology to analyse the effect of the embedding gap. We propose the metric of falsifiability of semantic subspaces as another fundamental metric to be reported as part of the NLP verification pipeline.
• Score: 9.897538432223714
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks have exhibited substantial success in the field of Natural Language Processing and ensuring their safety and reliability is crucial: there are safety critical contexts where such models must be robust to variability or attack, and give guarantees over their output. Unlike Computer Vision, NLP lacks a unified verification methodology and, despite recent advancements in literature, they are often light on the pragmatical issues of NLP verification. In this paper, we attempt to distil and evaluate general components of an NLP verification pipeline, that emerges from the progress in the field to date. Our contributions are two-fold. Firstly, we give a general (i.e. algorithm-independent) characterisation of verifiable subspaces that result from embedding sentences into continuous spaces. We identify, and give an effective method to deal with, the technical challenge of semantic generalisability of verified subspaces; and propose it as a standard metric in the NLP verification pipelines (alongside with the standard metrics of model accuracy and model verifiability). Secondly, we propose a general methodology to analyse the effect of the embedding gap -- a problem that refers to the discrepancy between verification of geometric subspaces, and the semantic meaning of sentences which the geometric subspaces are supposed to represent. In extreme cases, poor choices in embedding of sentences may invalidate verification results. We propose a number of practical NLP methods that can help to quantify the effects of the embedding gap; and in particular we propose the metric of falsifiability of semantic subspaces as another fundamental metric to be reported as part of the NLP verification pipeline. We believe that together these general principles pave the way towards a more consolidated and effective development of this new domain.

Related papers

• Revisiting Differential Verification: Equivalence Verification with Confidence [0.6562256987706128]
  When validated neural networks (NNs) are pruned (and retrained) before deployment, it is desirable to prove that the new NN behaves equivalently to the original NN. This paper revisits the idea of differential verification which performs reasoning on differences between NNs.
  arXiv  Detail & Related papers  (2024-10-26T15:53:25Z)
• Advancing Fairness in Natural Language Processing: From Traditional Methods to Explainability [0.9065034043031668]
  The thesis addresses the need for equity and transparency in NLP systems. It introduces an innovative algorithm to mitigate biases in high-risk NLP applications. It also presents a model-agnostic explainability method that identifies and ranks concepts in Transformer models.
  arXiv  Detail & Related papers  (2024-10-16T12:38:58Z)
• Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning [50.84938730450622]
  We propose a trajectory-based method TV score, which uses trajectory volatility for OOD detection in mathematical reasoning. Our method outperforms all traditional algorithms on GLMs under mathematical reasoning scenarios. Our method can be extended to more applications with high-density features in output spaces, such as multiple-choice questions.
  arXiv  Detail & Related papers  (2024-05-22T22:22:25Z)
• Goodhart's Law Applies to NLP's Explanation Benchmarks [57.26445915212884]
  We critically examine two sets of metrics: the ERASER metrics (comprehensiveness and sufficiency) and the EVAL-X metrics. We show that we can inflate a model's comprehensiveness and sufficiency scores dramatically without altering its predictions or explanations on in-distribution test inputs. Our results raise doubts about the ability of current metrics to guide explainability research, underscoring the need for a broader reassessment of what precisely these metrics are intended to capture.
  arXiv  Detail & Related papers  (2023-08-28T03:03:03Z)
• No Strong Feelings One Way or Another: Re-operationalizing Neutrality in Natural Language Inference [6.485890157501745]
  Natural Language Inference (NLI) has been a cornerstone task in evaluating language models' inferential reasoning capabilities. Standard three-way classification scheme used in NLI has well-known shortcomings in evaluating models' ability to capture the nuances of natural human reasoning. We argue that the operationalization of the neutral label in current NLI datasets has low validity, is interpreted inconsistently, and that at least one important sense of neutrality is often ignored.
  arXiv  Detail & Related papers  (2023-06-16T15:45:08Z)
• The #DNN-Verification Problem: Counting Unsafe Inputs for Deep Neural Networks [94.63547069706459]
  #DNN-Verification problem involves counting the number of input configurations of a DNN that result in a violation of a safety property. We propose a novel approach that returns the exact count of violations. We present experimental results on a set of safety-critical benchmarks.
  arXiv  Detail & Related papers  (2023-01-17T18:32:01Z)
• Validation Diagnostics for SBI algorithms based on Normalizing Flows [55.41644538483948]
  This work proposes easy to interpret validation diagnostics for multi-dimensional conditional (posterior) density estimators based on NF. It also offers theoretical guarantees based on results of local consistency. This work should help the design of better specified models or drive the development of novel SBI-algorithms.
  arXiv  Detail & Related papers  (2022-11-17T15:48:06Z)
• Evaluate Confidence Instead of Perplexity for Zero-shot Commonsense Reasoning [85.1541170468617]
  This paper reconsiders the nature of commonsense reasoning and proposes a novel commonsense reasoning metric, Non-Replacement Confidence (NRC) Our proposed novel method boosts zero-shot performance on two commonsense reasoning benchmark datasets and further seven commonsense question-answering datasets.
  arXiv  Detail & Related papers  (2022-08-23T14:42:14Z)
• Quantifying Robustness to Adversarial Word Substitutions [24.164523751390053]
  Deep-learning-based NLP models are found to be vulnerable to word substitution perturbations. We propose a formal framework to evaluate word-level robustness. metric helps us figure out why state-of-the-art models like BERT can be easily fooled by a few word substitutions.
  arXiv  Detail & Related papers  (2022-01-11T08:18:39Z)
• Incremental Verification of Fixed-Point Implementations of Neural Networks [0.19573380763700707]
  We develop and evaluate a novel symbolic verification framework using incremental bounded model checking (BMC), satisfiability modulo theories (SMT), and invariant inference. Our approach was able to verify and produce examples for 85.8% of 21 test cases considering different input images, and 100% of the properties related to covering methods.
  arXiv  Detail & Related papers  (2020-12-21T10:03:44Z)
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation [109.73983088432364]
  We propose the first method that aims to simultaneously learn invariant representations and risks under the setting of semi-supervised domain adaptation (Semi-DA) We introduce the LIRR algorithm for jointly textbfLearning textbfInvariant textbfRepresentations and textbfRisks.
  arXiv  Detail & Related papers  (2020-10-09T15:42:35Z)

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.