東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Unknown-Unknowns in Human-Centric AI...

Maity, Aranyak,

Linked to FindBook

Google Book

Amazon

博客來

Unknown-Unknowns in Human-Centric AI Systems /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Unknown-Unknowns in Human-Centric AI Systems // Aranyak Maity.
Author:	Maity, Aranyak,
Description:	1 electronic resource (122 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-09, Section: A.
Contained By:	Dissertations Abstracts International86-09A.
Subject:	Automotive engineering. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31841882
ISBN:	9798308197287

Unknown-Unknowns in Human-Centric AI Systems /
Maity, Aranyak,

Unknown-Unknowns in Human-Centric AI Systems /Aranyak Maity. - 1 electronic resource (122 pages)

Source: Dissertations Abstracts International, Volume: 86-09, Section: A.

Artificial intelligence (AI) systems are increasingly being deployed in safety-critical real-world environments involving human participants, which may pose risks to human safety. The unpredictable nature of real-world conditions and the inherent variability of human behavior often lead to situations that were not anticipated during the systems design or verification phases. Moreover, the inclusion of AI components like large language models (LLM) often regarded as "black boxes", adds complexity to these systems, heightening the likelihood of encountering unforeseen challenging scenarios or "unknown-unknowns".Unknown-unknowns present a significant challenge because their causes and impacts on the system are often not identified or are not known to the human-in-the-loop at the time of the error. These errors often precipitate a chain of events over time, starting with errors, leading to faults, which may escalate into hazards, and ultimately lead to accidents or safety violations, adversely affecting the human participants. To address these challenges, this thesis considers a conformal inference-based detection framework for identifying unknown-unknowns. This framework relearns operational models using physics guided surrogate models. The incorporation of physical into the framework ensures that it preemptively detects unknown-unknowns before causing any harm or safety violation. Unlike traditional rare class detection and anomaly detection methods, this approach does not rely on predefined error traces or definitions since for unknown-unknowns these are completely new scenarios not present during training or validation.Lastly, to distinguish unknown-unknowns from traditional anomalies or rare events, this thesis proposes categorizing them into two main subclasses: those stemming from predictive model errors and those arising from other physical dynamics and human interactions. Additionally, this thesis also investigates the effects of LLM-based agents in real world scenarios and their role in introducing more unknown-unknowns into the overall system.This research aims to make the interactions between AI enabled assistive devices and humans safer in the real world which is essential for the widespread deployment of such systems. By addressing the problem of unknown-unknowns associated with these safety-critical systems, this research contributes to increased trust and acceptance in diverse sectors such as healthcare, daily planning, transportation, and industrial automation.

English

ISBN: 9798308197287Subjects--Topical Terms:

2181195
Automotive engineering.
Subjects--Index Terms:

Large language models

Unknown-Unknowns in Human-Centric AI Systems /
LDR:03927nmm a22004213i 4500 001 2432283
005 20250707081335.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798308197287
035 $a (MiAaPQD)AAI31841882
035 $a AAI31841882
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Maity, Aranyak, $e author. $3 3821443
245 1 0 $a Unknown-Unknowns in Human-Centric AI Systems / $c Aranyak Maity.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (122 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-09, Section: A.
500 $a Advisors: Gupta, Sandeep K. S. Committee members: Banerjee, Ayan; Lee, Kookjin; Gupta, Vivek; Lamrani, Imane.
502 $b Ph.D. $c Arizona State University $d 2025.
520 $a Artificial intelligence (AI) systems are increasingly being deployed in safety-critical real-world environments involving human participants, which may pose risks to human safety. The unpredictable nature of real-world conditions and the inherent variability of human behavior often lead to situations that were not anticipated during the systems design or verification phases. Moreover, the inclusion of AI components like large language models (LLM) often regarded as "black boxes", adds complexity to these systems, heightening the likelihood of encountering unforeseen challenging scenarios or "unknown-unknowns".Unknown-unknowns present a significant challenge because their causes and impacts on the system are often not identified or are not known to the human-in-the-loop at the time of the error. These errors often precipitate a chain of events over time, starting with errors, leading to faults, which may escalate into hazards, and ultimately lead to accidents or safety violations, adversely affecting the human participants. To address these challenges, this thesis considers a conformal inference-based detection framework for identifying unknown-unknowns. This framework relearns operational models using physics guided surrogate models. The incorporation of physical into the framework ensures that it preemptively detects unknown-unknowns before causing any harm or safety violation. Unlike traditional rare class detection and anomaly detection methods, this approach does not rely on predefined error traces or definitions since for unknown-unknowns these are completely new scenarios not present during training or validation.Lastly, to distinguish unknown-unknowns from traditional anomalies or rare events, this thesis proposes categorizing them into two main subclasses: those stemming from predictive model errors and those arising from other physical dynamics and human interactions. Additionally, this thesis also investigates the effects of LLM-based agents in real world scenarios and their role in introducing more unknown-unknowns into the overall system.This research aims to make the interactions between AI enabled assistive devices and humans safer in the real world which is essential for the widespread deployment of such systems. By addressing the problem of unknown-unknowns associated with these safety-critical systems, this research contributes to increased trust and acceptance in diverse sectors such as healthcare, daily planning, transportation, and industrial automation.
546 $a English
590 $a School code: 0010
650 4 $a Automotive engineering. $3 2181195
650 4 $a Transportation. $3 555912
653 $a Large language models
653 $a Human behavior
653 $a Industrial automation
653 $a Safety violation
690 $a 0800
690 $a 0709
690 $a 0540
710 2 $a Arizona State University. $b Computer Science. $e degree granting institution. $3 3815405
720 1 $a Gupta, Sandeep K. S. $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-09A.
790 $a 0010
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31841882