paper-with-me

홈 › Papers

On the Evaluation Consistency of Attribution-based Explanations

2024-07-28 · Jiarui Duan, Haoling Li, Haofei Zhang, Hao Jiang, Mengqi Xue, Li Sun, Mingli Song, Jie Song

Attribution-based explanations are garnering increasing attention recently and have emerged as the predominant approach towards \textit{eXplanable Artificial Intelligence}~(XAI). However, the absence of consistent configurations and systematic investigations in prior literature impedes comprehensive evaluations of existing methodologies. In this work, we introduce {Meta-Rank}, an open platform for benchmarking attribution methods in the image domain. Presently, Meta-Rank assesses eight exemplary attribution methods using six renowned model architectures on four diverse datasets, employing both the \textit{Most Relevant First} (MoRF) and \textit{Least Relevant First} (LeRF) evaluation protocols. Through extensive experimentation, our benchmark reveals three insights in attribution evaluation endeavors: 1) evaluating attribution methods under disparate settings can yield divergent performance rankings; 2) although inconsistent across numerous cases, the performance rankings exhibit remarkable consistency across distinct checkpoints along the same training trajectory; 3) prior attempts at consistent evaluation fare no better than baselines when extended to more heterogeneous models and datasets. Our findings underscore the necessity for future research in this domain to conduct rigorous evaluations encompassing a broader range of models and datasets, and to reassess the assumptions underlying the empirical success of different attribution methods. Our code is publicly available at \url{https://github.com/TreeThree-R/Meta-Rank}.

📄 PDF Abstract BibTeX arXiv:2407.19471

Code (0)

등록된 구현이 없습니다.

Tasks

Benchmarking

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Harmonizing Feature Attributions Across Deep Learning Architectures: Enhancing Interpretability and Consistency

2023-07-05 · Md Abdul Kadir, Gowtham Krishna Addluri, Daniel Sonntag

Ensuring the trustworthiness and interpretability of machine learning models is critical to their deployment in real-world applications. Feature attribution methods have gained significant attention, which provide local …

Deep Learning

Evaluating Evidence Attribution in Generated Fact Checking Explanations

2024-06-18 · Rui Xing, Timothy Baldwin, Jey Han Lau

Automated fact-checking systems often struggle with trustworthiness, as their generated explanations can include hallucinations. In this work, we explore evidence attribution for fact-checking explanation generation. We …

Explanation GenerationFact Checking

RankingSHAP -- Listwise Feature Attribution Explanations for Ranking Models

2024-03-24 · Maria Heuss, Maarten de Rijke, Avishek Anand

While SHAP (SHapley Additive exPlanations) and other feature attribution methods are commonly employed to explain model predictions, their application within information retrieval (IR), particularly for complex outputs s…

Information RetrievalLearning-To-Rankvalid

RankSHAP: Shapley Value Based Feature Attributions for Learning to Rank

2024-05-03 · Tanya Chowdhury, Yair Zick, James Allan

Numerous works propose post-hoc, model-agnostic explanations for learning to rank, focusing on ordering entities by their relevance to a query through feature attribution methods. However, these attributions often weakly…

Computational EfficiencyLearning-To-Rank

Are self-explanations from Large Language Models faithful?

2024-01-15 · Andreas Madsen, Sarath Chandar, Siva Reddy

Instruction-tuned Large Language Models (LLMs) excel at many tasks and will even explain their reasoning, so-called self-explanations. However, convincing and wrong self-explanations can lead to unsupported confidence in…

counterfactualFaithfulness CriticNatural Language InferenceQuestion Answering+2