Investigating the Impact of Model Instability on Explanations and Uncertainty (2024.findings-acl)
Copied to clipboard
| Challenge: | Explainable AI methods are typically evaluated holistically, but small perturbations to inputs can vastly distort explanations. |
| Approach: | They artificially simulate epistemic uncertainty in text input by introducing noise at inference time and measure the effect on the output of pre-trained language models. |
| Outcome: | The proposed model can detect salient tokens when uncertain, but it is not reliable when small perturbations are exposed during training. |
Similar Papers
Interpreting the Robustness of Neural NLP Models to Textual Perturbations (2022.findings-acl)
Copied to clipboard
| Challenge: | Modern Natural Language Processing models are sensitive to input perturbations and their performance can decrease when applied to noisy data. |
| Approach: | They propose to explain the extent to which a model is affected by an unseen textual perturbation by the learnability of the perturbation. |
| Outcome: | The proposed model is better at identifying a perturbation (higher learnability) but worse at ignoring it (lower robustness). |
Quantifying Uncertainty in Natural Language Explanations of Large Language Models for Question Answering (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown strong capabilities, enabling concise, context-aware answers in question answering tasks. |
| Approach: | They propose a framework that provides valid uncertainty guarantees for LLMs . they also propose 'model-agnostic' uncertainty estimation method that maintains valid guarantees even under noise. |
| Outcome: | The proposed method provides valid uncertainty guarantees even under noise. |
Calibration Meets Explanation: A Simple and Effective Approach for Model Confidence Estimates (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to improve confidence calibration of pre-trained language models are still a mystery. |
| Approach: | They propose a method that leverages model explanations to make models less confident with non-inductive attributions. |
| Outcome: | The proposed method improves confidence calibration in all settings and reduces calibration errors when combined with temperature scaling. |
“Are Your Explanations Reliable?” Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack (2023.emnlp-main)
Copied to clipboard
| Challenge: | Extensive experiments on text datasets demonstrate that XAIFooler significantly outperforms all baselines by large margins in its ability to manipulate LIME’s explanations with high semantic preservability. |
| Approach: | They propose to use LIME to establish a baseline and then propose an algorithm to perturb text inputs and manipulate explanations. |
| Outcome: | The proposed algorithm outperforms baselines on text datasets and achieves high semantic preservability. |
The Illusion of Competence: Evaluating the Effect of Explanations on Users’ Mental Models of Visual Question Answering Systems (2024.emnlp-main)
Copied to clipboard
Judith Sieker, Simeon Junker, Ronja Utescher, Nazia Attari, Heiko Wersing, Hendrik Buschmeier, Sina Zarrieß
| Challenge: | Using visual inputs, we hypothesize that explanations will make limited AI capabilities more transparent to users, but our results show that explanation increases users’ perceptions of the system’s competence regardless of its actual performance. |
| Approach: | They employ a visual question answer and explanation task where participants control the AI system’s limitations by manipulating visual inputs. |
| Outcome: | The proposed explanations do not increase users’ perceptions of the system’s competence regardless of its actual performance. |
Evaluating the Robustness of Neural Language Models to Input Perturbations (2021.emnlp-main)
Copied to clipboard
| Challenge: | High-performance neural language models have achieved state-of-the-art results on a wide range of NLP tasks, but results for common benchmark datasets often do not reflect model reliability and robustness when applied to noisy, real-world data. |
| Approach: | They propose to implement character-level and word-level perturbation methods to simulate scenarios in which input texts may be slightly noisy or different from the data distribution on which NLP systems were trained. |
| Outcome: | The proposed methods simulate scenarios in which input texts may be slightly noisy or different from the data distribution on which NLP systems were trained. |
On the Interaction of Belief Bias and Explanations (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to evaluate explainability fail to account for belief biases affecting human performance . previous studies have shown that neural models can make confident predictions relying on artifacts . |
| Approach: | They propose to account for belief bias in explainability by using models of varying quality and adversarial examples. |
| Outcome: | The proposed methods show that results change when using models of varying quality and adversarial examples. |
Diagnosing Hidden Instabilities in Model Editing via Uncertainty Quantification (2026.acl-long)
Copied to clipboard
Zihan Gu, TianYi Zhang, Xinyan Zhang, Zhiyuan Wang, Han Zhang, Yuhao Wei, Jiacheng Lu, Tianyi Ma, Xingsheng Zhang, Hua Zhang, Yue Hu
| Challenge: | Existing methods to update large language models (LLMs) without expensive retraining are fragile under single-edit evaluation protocols. |
| Approach: | They propose a framework that characterizes activation-based editing as a constrained intervention on intermediate representations. |
| Outcome: | The proposed method reveals local knowledge conflicts invisible to existing benchmarks. |
SHAP-Based Explanation Methods: A Review for NLP Interpretability (2022.coling-1)
Copied to clipboard
| Challenge: | Existing models with opacity problems have been proposed to address this problem. |
| Approach: | They propose a unified local-interpretability framework with a rigorous theoretical foundation on the game-theoretic concept of Shapley values. |
| Outcome: | The proposed framework is based on the Shapley-value-based model explanations. |
Robustness Testing of Language Understanding in Task-Oriented Dialog (2021.acl-long)
Copied to clipboard
Jiexi Liu, Ryuichi Takanobu, Jiaxin Wen, Dazhen Wan, Hongguang Li, Weiran Nie, Cheng Li, Wei Peng, Minlie Huang
| Challenge: | a lack of systematic studies on the robustness of language understanding models in task-oriented dialog systems is limiting . authors propose a model-agnostic toolkit LAUG to approximate natural language perturbations . |
| Approach: | They propose a model-agnostic toolkit LAUG to approximate natural language perturbations for testing the robustness of language understanding models in task-oriented dialog systems. |
| Outcome: | The proposed toolkit reveals critical robustness issues in state-of-the-art models. |