Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kambhamettu, Hita, Hwang, Alyssa, Laban, Philippe, Head, Andrew
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910098495897600
author Kambhamettu, Hita
Hwang, Alyssa
Laban, Philippe
Head, Andrew
author_facet Kambhamettu, Hita
Hwang, Alyssa
Laban, Philippe
Head, Andrew
contents AI answer engines are a relatively new kind of information search tool: rather than returning a ranked list of documents, they generate an answer to a search question with inline citations to sources. But reading the cited sources is costly, and citation links themselves offer little guidance about what evidence they contain. We present attribution gradients, a technique to boost the informativeness of citations by consolidating scent and information prey in place. Its first feature is bringing evidence amounts, supporting/contradictory excerpts, links to source, contextual explanation into one place. Its second feature is the ability to unravel second-degree citations in place. In a lab study we demonstrate usage of the full gradient in a critical reading task and its support for deep engagement that increased the depth of what readers took away from the sources versus a standard citation and document QA design.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00361
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers
Kambhamettu, Hita
Hwang, Alyssa
Laban, Philippe
Head, Andrew
Human-Computer Interaction
Artificial Intelligence
AI answer engines are a relatively new kind of information search tool: rather than returning a ranked list of documents, they generate an answer to a search question with inline citations to sources. But reading the cited sources is costly, and citation links themselves offer little guidance about what evidence they contain. We present attribution gradients, a technique to boost the informativeness of citations by consolidating scent and information prey in place. Its first feature is bringing evidence amounts, supporting/contradictory excerpts, links to source, contextual explanation into one place. Its second feature is the ability to unravel second-degree citations in place. In a lab study we demonstrate usage of the full gradient in a critical reading task and its support for deep engagement that increased the depth of what readers took away from the sources versus a standard citation and document QA design.
title Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2510.00361