paper-with-me

Papers

Nothing Else Matters: Model-Agnostic Explanations By Identifying Prediction Invariance

2016-11-17 · Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin

At the core of interpretable machine learning is the question of whether humans are able to make accurate predictions about a model's behavior. Assumed in this question are three properties of the interpretable output: coverage, precision, and effort. Coverage refers to how often humans think they can predict the model's behavior, precision to how accurate humans are in those predictions, and effort is either the up-front effort required in interpreting the model, or the effort required to make predictions about a model's behavior. In this work, we propose anchor-LIME (aLIME), a model-agnostic technique that produces high-precision rule-based explanations for which the coverage boundaries are very clear. We compare aLIME to linear LIME with simulated experiments, and demonstrate the flexibility of aLIME with qualitative examples from a variety of domains and tasks.

📄 PDF Abstract BibTeX arXiv:1611.05817

Code (0)

등록된 구현이 없습니다.

Tasks

Interpretable Machine Learning

Methods 이 논문이 사용한 방법론

LIME LIME, or Local Interpretable Model-Agnostic Explanations, is an algorithm that can explain the predictions of any classifier or regressor in a faithful way, by…

Similar Papers 제목 키워드 기반

A Study on Bootstrapping Bilingual Vector Spaces from Non-Parallel Data (and Nothing Else)

2013-10-01 · EMNLP 2013 10 · Ivan Vuli{\'c}, Marie-Francine Moens
Information RetrievalMachine TranslationSemantic Role LabelingTransfer Learning+1

Global Aggregations of Local Explanations for Black Box models

2019-07-05 · Ilse van der Linden, Hinda Haned, Evangelos Kanoulas

The decision-making process of many state-of-the-art machine learning models is inherently inscrutable to the extent that it is impossible for a human to interpret the model directly: they are black box models. This has …

Decision MakingOpen-Ended Question Answering

Explanations for Monotonic Classifiers

2021-06-01 · Joao Marques-Silva, Thomas Gerspacher, Martin Cooper, Alexey Ignatiev 외

In many classification tasks there is a requirement of monotonicity. Concretely, if all else remains constant, increasing (resp. decreasing) the value of one or more features must not decrease (resp. increase) the value …

Graphing else matters: exploiting aspect opinions and ratings in explainable graph-based recommendations

2021-07-07 · Iván Cantador, Andrés Carvallo, Fernando Diez, Denis Parra

The success of neural network embeddings has entailed a renewed interest in using knowledge graphs for a wide variety of machine learning and information retrieval tasks. In particular, current recommendation methods bas…

Graph EmbeddingInformation RetrievalKnowledge GraphsRetrieval

Does Verbose Chain-of-Thought Really Help? In-Distribution Evidence that Content, Not Length, Matters

2026-06-29 · Wenlong Wang, Fergal Reid arxiv

Chain-of-thought (CoT) prompting improves LLM reasoning, but the source is contested: do the intermediate steps help because they carry useful semantic content, or because conditioning on more tokens buys extra computati…