paper-with-me

Papers

Automated Explanation Selection for Scientific Discovery

2024-07-24 · Markus Iser

Automated reasoning is a key technology in the young but rapidly growing field of Explainable Artificial Intelligence (XAI). Explanability helps build trust in artificial intelligence systems beyond their mere predictive accuracy and robustness. In this paper, we propose a cycle of scientific discovery that combines machine learning with automated reasoning for the generation and the selection of explanations. We present a taxonomy of explanation selection problems that draws on insights from sociology and cognitive science. These selection criteria subsume existing notions and extend them with new properties.

📄 PDF Abstract BibTeX arXiv:2407.17454

Code (0)

등록된 구현이 없습니다.

Tasks

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)scientific discoverySociology

Similar Papers 제목 키워드 기반

BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery

2025-01-02 · Kanishk Gandhi, Michael Y. Li, Lyle Goodyear, Louise Li 외

Understanding the world and explaining it with scientific theories is a central aspiration of artificial intelligence research. Proposing theories, designing experiments to test them, and then revising them based on data…

BenchmarkingExperimental DesignModel Discoveryscientific discovery

Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists

2026-07-13 · Chuhan Shi, Xiaoquan Ren, Sicheng Song, Haobo Li 외 hf

Existing benchmarks for scientific data analysis evaluate LLMs primarily on code execution or workflow completion, overlooking that scientific analysis serves to support distinct types of scientific claims: hypothesis ex…

CausalGame: Benchmarking Causal Thinking of LLM Agents in Games

2026-07-05 · Zhenhao Chen, Yongqiang Chen, Chenxi Liu, Junchi Yu 외 arxiv

Building AI Scientist agents with Large Language Models (LLMs) has recently attracted growing attention. Since scientific discovery fundamentally relies on uncovering causal relationships from observations, the capabilit…

Benchmarking the Discovery Engine

2025-07-01 · Jack Foxabbott, Arush Tagade, Andrew Cusick, Robbie McCorkell 외 arxiv

The Discovery Engine is a general purpose automated system for scientific discovery, which combines machine learning with state-of-the-art ML interpretability to enable rapid and robust scientific insight across diverse …

Scientific Discovery by Generating Counterfactuals using Image Translation

2020-07-10 · Arunachalam Narayanaswamy, Subhashini Venugopalan, Dale R. Webster, Lily Peng 외

Model explanation techniques play a critical role in understanding the source of a model's performance and making its decisions transparent. Here we investigate if explanation techniques can also be used as a mechanism f…

scientific discoveryTranslation