2 Reads
·
30 Citations
This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.
... Faithfulness. In interpretability, faithfulness (also called fidelity or reliability) means that an explanation should "accurately represent the reasoning process behind the model's prediction", which is a fundamental requirement of an explanation (Harrington et al., 1985;Ribeiro et al., 2016;Gilpin et al., 2018;Jacovi & Goldberg, 2020). 2 It should be contrasted with plausibility (a.k.a. persuasiveness or understandability), which refers to "how convincing an explanation is to humans" (Herman, 2019;Jacovi & Goldberg, 2020). ...
Reference:
Faithful Chain-of-Thought Reasoning