Beyond Accuracy: An Explainability-Driven Analysis of Harmful Content Detection

• URL: http://arxiv.org/abs/2603.18015v1
• Date: Tue, 24 Feb 2026 16:27:06 GMT
• Title: Beyond Accuracy: An Explainability-Driven Analysis of Harmful Content Detection
• Abstract summary: A neural harmful content detection model trained on the Civil Comments dataset is analyzed explainability-drivenly.<n>Two popular post-hoc explanation methods, Shapley Additive Explanations and Integrated Gradients, are used.<n>Despite strong overall performance, with an area under the curve of 0.93 and an accuracy of 0.94, the analysis reveals limitations that are not observable from aggregate evaluation metrics alone.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although automated harmful content detection systems are frequently used to monitor online platforms, moderators and end users frequently cannot understand the logic underlying their predictions. While recent studies have focused on increasing classification accuracy, little focus has been placed on comprehending why neural models identify content as harmful, especially when it comes to borderline, contextual, and politically sensitive situations. In this work, a neural harmful content detection model trained on the Civil Comments dataset is analyzed explainability-drivenly. Two popular post-hoc explanation methods, Shapley Additive Explanations and Integrated Gradients, are used to analyze the behavior of a RoBERTa-based classifier in both correct predictions and systematic failure cases. Despite strong overall performance, with an area under the curve of 0.93 and an accuracy of 0.94, the analysis reveals limitations that are not observable from aggregate evaluation metrics alone. Integrated Gradients appear to extract more diffuse contextual attributions while Shapley Additive Explanations extract more focused attributions on explicit lexical cues. The consequent divergence in their outputs manifests in both false negatives and false positives. Qualitative case studies reveal recurring failure modes such as indirect toxicity, lexical over-attribution, or political discourse. The results suggest that explainable AI can foster human-in-the-loop moderation by exposing model uncertainty and increasing the interpretable rationale behind automated decisions. Most importantly, this work highlights the role of explainability as a transparency and diagnostic resource for online harmful content detection systems rather than as a performance-enhancing lever.

Related papers

• A Multi-Dimensional Evaluation of Explainability in Media Bias Detection [10.798797986346914]
  We present a multi-dimensional evaluation of explainability in encoder-based media bias detection using the Bias s By Experts dataset.<n>We study BERT and RoBERTa as classifiers along three complementary axes: predictive performance, explanation plausibility, and mechanistic faithfulness.<n>Our findings suggest that predictive performance, attribution plausibility, and mechanistic faithfulness characterize different aspects of model behavior.
  arXiv  Detail & Related papers  (2026-07-22T09:29:49Z)
• Explanation-Aware Learning for Enhanced Interpretability in Biomedical Imaging [0.0]
  Post-hoc explanation methods are widely used to visualize model decisions in the form of saliency maps.<n>This paper analyzes how different explanation loss designs and supervision strengths influence both predictive performance and spatial faithfulness of explanations.
  arXiv  Detail & Related papers  (2026-05-11T06:27:55Z)
• Reason-IAD: Knowledge-Guided Dynamic Latent Reasoning for Explainable Industrial Anomaly Detection [85.29900916231655]
  Reason-IAD is a knowledge-guided dynamic latent reasoning framework for explainable industrial anomaly detection.<n>Experiments demonstrate that Reason-IAD consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-02-10T14:54:17Z)
• Empirical Analysis of Adversarial Robustness and Explainability Drift in Cybersecurity Classifiers [0.0]
  This paper presents an empirical study of adversarial robustness and explainability drift across two cybersecurity domains.<n>We introduce a quantitative metric, the Robustness Index (RI), defined as the area under the accuracy perturbation curve.<n>Experiments on the Phishing Websites and NB15 datasets show consistent robustness trends, with adversarial training improving RI by up to 9 percent while maintaining clean-data accuracy.
  arXiv  Detail & Related papers  (2026-02-06T05:30:37Z)
• The Dead Salmons of AI Interpretability [9.722180905657268]
  In AI interpretability, reports of similar ''dead salmon'' artifacts abound.<n>We argue for a pragmatic statistical-causal reframing.
  arXiv  Detail & Related papers  (2025-12-21T16:07:44Z)
• DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models [55.30555646945055]
  Text-to-Image (T2I) models are vulnerable to semantic leakage.<n>We introduce DeLeaker, a lightweight approach that mitigates leakage by directly intervening on the model's attention maps.<n>SLIM is the first dataset dedicated to semantic leakage.
  arXiv  Detail & Related papers  (2025-10-16T17:39:21Z)
• Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing [12.835224376066769]
  Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their deployment is frequently undermined by undesirable behaviors.<n>We introduce a novel and efficient framework that diagnoses a range of undesirable LLM behaviors by analyzing representation and its gradients.<n>We systematically evaluate our method for tasks that include tracking harmful content, detecting backdoor poisoning, and identifying knowledge contamination.
  arXiv  Detail & Related papers  (2025-09-26T12:07:47Z)
• Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection [49.26064449816502]
  We propose a Gradient-based Influence-Aware Constrained Decoding (GACD) method to address text-visual bias and co-occurrence bias.<n>GACD effectively reduces hallucinations and improves the visual grounding of MLLM outputs.
  arXiv  Detail & Related papers  (2025-09-03T08:13:52Z)
• Aligned Probing: Relating Toxic Behavior and Model Internals [78.20380492883022]
  We introduce aligned probing, a novel interpretability framework that aligns the behavior of language models (LMs)<n>Using this framework, we examine over 20 OLMo, Llama, and Mistral models, bridging behavioral and internal perspectives for toxicity for the first time.<n>Our results show that LMs strongly encode information about the toxicity level of inputs and subsequent outputs, particularly in lower layers.
  arXiv  Detail & Related papers  (2025-03-17T17:23:50Z)
• Interpretable Imitation Learning with Dynamic Causal Relations [65.18456572421702]
  We propose to expose captured knowledge in the form of a directed acyclic causal graph. We also design this causal discovery process to be state-dependent, enabling it to model the dynamics in latent causal graphs. The proposed framework is composed of three parts: a dynamic causal discovery module, a causality encoding module, and a prediction module, and is trained in an end-to-end manner.
  arXiv  Detail & Related papers  (2023-09-30T20:59:42Z)
• Topological Interpretability for Deep-Learning [0.30806551485143496]
  Deep learning (DL) models cannot quantify the certainty of their predictions. This work presents a method to infer prominent features in two DL classification models trained on clinical and non-clinical text.
  arXiv  Detail & Related papers  (2023-05-15T13:38:13Z)
• NeuroExplainer: Fine-Grained Attention Decoding to Uncover Cortical Development Patterns of Preterm Infants [73.85768093666582]
  We propose an explainable geometric deep network dubbed NeuroExplainer. NeuroExplainer is used to uncover altered infant cortical development patterns associated with preterm birth.
  arXiv  Detail & Related papers  (2023-01-01T12:48:12Z)
• Toxicity Detection with Generative Prompt-based Inference [3.9741109244650823]
  It is a long-known risk that language models (LMs), once trained on corpus containing undesirable content, have the power to manifest biases and toxicity. In this work, we explore the generative variant of zero-shot prompt-based toxicity detection with comprehensive trials on prompt engineering.
  arXiv  Detail & Related papers  (2022-05-24T22:44:43Z)
• The Hidden Uncertainty in a Neural Networks Activations [105.4223982696279]
  The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data. This work investigates whether this distribution correlates with a model's epistemic uncertainty, thus indicating its ability to generalise to novel inputs.
  arXiv  Detail & Related papers  (2020-12-05T17:30:35Z)

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.