paper-with-me

Papers

Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining

2021-10-15 · Andreas Madsen, Nicholas Meade, Vaibhav Adlakha, Siva Reddy

To explain NLP models a popular approach is to use importance measures, such as attention, which inform input tokens are important for making a prediction. However, an open question is how well these explanations accurately reflect a model's logic, a property called faithfulness. To answer this question, we propose Recursive ROAR, a new faithfulness metric. This works by recursively masking allegedly important tokens and then retraining the model. The principle is that this should result in worse model performance compared to masking random tokens. The result is a performance curve given a masking-ratio. Furthermore, we propose a summarizing metric using relative area-between-curves (RACU), which allows for easy comparison across papers, models, and tasks. We evaluate 4 different importance measures on 8 different datasets, using both LSTM-attention models and RoBERTa models. We find that the faithfulness of importance measures is both model-dependent and task-dependent. This conclusion contradicts previous evaluations in both computer vision and faithfulness of attention literature.

📄 PDF Abstract BibTeX arXiv:2110.08412

Code (1)

AndreasMadsen/nlp-roar-interpretability 공식 구현 pytorch

Tasks

Open-Ended Question Answering

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
WordPiece 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Faithfulness Measurable Masked Language Models

2023-10-11 · Andreas Madsen, Siva Reddy, Sarath Chandar

A common approach to explaining NLP models is to use importance measures that express which tokens are important for a prediction. Unfortunately, such explanations are often wrong despite being persuasive. Therefore, it …

AIM: Adversarial Information Masking for Faithfulness Evaluation of Saliency Maps

2026-05-16 · Chia-Ying Hsieh, Hsin-Yuan Fang, Chun-Shu Wei arxiv

Post-hoc saliency methods are widely used to interpret deep neural networks, but their faithfulness is difficult to evaluate reliably. Existing evaluations mask features according to saliency-induced feature ordering and…

Robust Infidelity: When Faithfulness Measures on Masked Language Models Are Misleading

2023-08-13 · Evan Crothers, Herna Viktor, Nathalie Japkowicz

A common approach to quantifying neural text classifier interpretability is to calculate faithfulness metrics based on iteratively masking salient input tokens and measuring changes in the model prediction. We propose th…

Sensitivity

Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning

2026-05-22 · Jinghan Jia, Joe Benton, Eric Easley arxiv

Chain-of-thought (CoT) reasoning is useful for monitoring language models only when the reasoning trace faithfully reflects the computation that produces the final answer. However, models can rely on prompt-to-answer sho…

Code Repair

Framework for Evaluating Faithfulness of Local Explanations

2022-02-01 · Sanjoy Dasgupta, Nave Frost, Michal Moshkovitz

We study the faithfulness of an explanation system to the underlying prediction model. We show that this can be captured by two properties, consistency and sufficiency, and introduce quantitative measures of the extent t…