Skip to main content

Advanced Search

Projected result for your current search: 0

Search Operators:

You can use operators in your search query to narrow down your results even more. Click on the search operator to see an explanation of how it works.
Finds documents with exactly this word group, in exactly this word order and spelling (e.g. "employer branding").
Finds documents with both search terms (e.g. sales AND bonus).
Finds documents with one or the other search term (e.g. porsche OR volkswagen).
Finds documents with all search terms. Blank space is understood as AND (e.g. man robot production).
Finds documents with no appearance of the word behind NOT (e.g. ford NOT "harrison ford").
Finds documents where the search term is mentioned at least "n" times."n" may be any number (e.g. COUNT(gear)>8).
Finds documents with both search terms in any word order, permitting "n" words as a maximum distance between them. Best choose between 15 and 30 (e.g. NEAR(recruit, professionals, 20)).
Finds documents with the search term in word versions or composites. The asterisk * marks whether you wish them BEFORE, BEHIND, or BEFORE and BEHIND the search term (e.g. lightweight*, *lightweight, *lightweight*).
Finds documents with the search term in different spellings. "?" allows only one character (e.g. organi?ation).
Special characters are understood as AND (e.g. Miller Bros. & Sons).

Semantic Search

powered by (Link opens in a new window)
loading …
Log in
Top

Evaluating the Reliability of Self-explanations in Large Language Models

  • 2025
  • OriginalPaper
  • Chapter
Published in:
Authors
Korbinian Randl
John Pavlopoulos
Aron Henriksson
Tony Lindgren
Published in
Discovery Science
Publisher
Springer Nature Switzerland

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

The chapter delves into the reliability of self-explanations generated by large language models (LLMs) for their own outputs. It evaluates extractive and counterfactual self-explanations on two classification tasks, showing that while extractive explanations often correlate well with human judgment, counterfactual explanations can be highly faithful and informative. The study also compares these self-explanations with attention- and gradient-based explainability methods, highlighting the complexities and nuances in understanding the internal reasoning of LLMs. The findings shed light on the potential of LLMs to provide explanations that are both human-like and faithful, making the chapter a valuable resource for researchers and practitioners in the field of AI explainability.
AI Generated

This summary of the content was generated with the help of AI.

Already a customer? Then log in here to gain access.

Customer login

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Business + Economics & Engineering + Technology"

Online-Abonnement

Springer Professional "Business + Economics & Engineering + Technology" gives you access to:

  • more than 130.000 books
  • more than 540 journals

from the following subject areas:

  • Automotive
  • Construction + Real Estate
  • Business IT + Informatics
  • Electrical Engineering + Electronics
  • Energy + Sustainability
  • Finance + Banking
  • Management + Leadership
  • Marketing + Sales
  • Mechanical Engineering + Materials
  • Surfaces + Materials Technology
  • Insurance + Risk


Secure your knowledge advantage now!

inform now

Springer Professional "Engineering + Technology"

Online-Abonnement

Springer Professional "Engineering + Technology" gives you access to:

  • more than 75.000 books
  • more than 390 journals

from the following specialised fileds:

  • Automotive
  • Business IT + Informatics
  • Construction + Real Estate
  • Electrical Engineering + Electronics
  • Energy + Sustainability
  • Mechanical Engineering + Materials
  • Surfaces + Materials Technology





 

Secure your knowledge advantage now!

inform now

Springer Professional "Business + Economics"

Online-Abonnement

Springer Professional "Business + Economics" gives you access to:

  • more than 100.000 books
  • more than 340 journals

from the following specialised fileds:

  • Construction + Real Estate
  • Business IT + Informatics
  • Finance + Banking
  • Management + Leadership
  • Marketing + Sales
  • Insurance + Risk



Secure your knowledge advantage now!

inform now

For explorers: Get to know our platforms better with a free registration.

Register for free
previous chapter Large Language Models-Based Local Explanations of Text Classifiers
next chapter Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitation
Title
Evaluating the Reliability of Self-explanations in Large Language Models
Authors
Korbinian Randl
John Pavlopoulos
Aron Henriksson
Tony Lindgren
Copyright Year
2025
Book
Discovery Science

Print ISBN: 978-3-031-78976-2

Electronic ISBN: 978-3-031-78977-9

Copyright Year: 2025

DOI
https://doi.org/10.1007/978-3-031-78977-9_3
This content is only visible if you are logged in and have the appropriate permissions.
This content is only visible if you are logged in and have the appropriate permissions.

Premium Partner

    Image Credits
    Neuer Inhalt/© ITandMEDIA, Nagarro GmbH/© Nagarro GmbH, AvePoint Deutschland GmbH/© AvePoint Deutschland GmbH, AFB Gemeinnützige GmbH/© AFB Gemeinnützige GmbH, USU GmbH/© USU GmbH, Ferrari electronic AG/© Ferrari electronic AG