Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Ley, Dan"'
Data Attribution (DA) methods quantify the influence of individual training data points on model outputs and have broad applications such as explainability, data selection, and noisy label identification. However, existing DA methods are often comput
Externí odkaz:
http://arxiv.org/abs/2410.09940
As Large Language Models (LLMs) are increasingly being employed in real-world applications in critical domains such as healthcare, it is important to ensure that the Chain-of-Thought (CoT) reasoning generated by these models faithfully captures their
Externí odkaz:
http://arxiv.org/abs/2406.10625
Recent advancements in Large Language Models (LLMs) have demonstrated exceptional capabilities in complex tasks like machine translation, commonsense reasoning, and language understanding. One of the primary reasons for the adaptability of LLMs in su
Externí odkaz:
http://arxiv.org/abs/2310.05797
The Right to Explanation is an important regulatory principle that allows individuals to request actionable explanations for algorithmic decisions. However, several technical challenges arise when providing such actionable explanations in practice. F
Externí odkaz:
http://arxiv.org/abs/2306.06716
Autor:
Ley, Dan, Tang, Leonard, Nazari, Matthew, Lin, Hongjin, Srinivas, Suraj, Lakkaraju, Himabindu
This work addresses the challenge of providing consistent explanations for predictive models in the presence of model indeterminacy, which arises due to the existence of multiple (nearly) equally well-performing models for a given dataset and task. D
Externí odkaz:
http://arxiv.org/abs/2306.06193
Autor:
Tang, Leonard, Ley, Dan
It is well-known that modern computer vision systems often exhibit behaviors misaligned with those of humans: from adversarial attacks to image corruptions, deep learning vision models suffer in a variety of settings that humans capably handle. In li
Externí odkaz:
http://arxiv.org/abs/2306.04955
Counterfactual explanations have been widely studied in explainability, with a range of application dependent methods prominent in fairness, recourse and model understanding. The major shortcoming associated with these methods, however, is their inab
Externí odkaz:
http://arxiv.org/abs/2305.17021
Autor:
Agarwal, Chirag, Ley, Dan, Krishna, Satyapriya, Saxena, Eshika, Pawelczyk, Martin, Johnson, Nari, Puri, Isha, Zitnik, Marinka, Lakkaraju, Himabindu
While several types of post hoc explanation methods have been proposed in recent literature, there is very little work on systematically benchmarking these methods. Here, we introduce OpenXAI, a comprehensive and extensible open-source framework for
Externí odkaz:
http://arxiv.org/abs/2206.11104
Counterfactual explanations have been widely studied in explainability, with a range of application dependent methods emerging in fairness, recourse and model understanding. However, the major shortcoming associated with these methods is their inabil
Externí odkaz:
http://arxiv.org/abs/2204.06917
To interpret uncertainty estimates from differentiable probabilistic models, recent work has proposed generating a single Counterfactual Latent Uncertainty Explanation (CLUE) for a given data point where the model is uncertain, identifying a single,
Externí odkaz:
http://arxiv.org/abs/2112.02646