Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cohen, Roi, Biswas, Russa, de Melo, Gerard
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.20487
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908380610691072
author Cohen, Roi
Biswas, Russa
de Melo, Gerard
author_facet Cohen, Roi
Biswas, Russa
de Melo, Gerard
contents Factual completeness is a general term that captures how detailed and informative a factually correct text is. For instance, the factual sentence ``Barack Obama was born in the United States'' is factually correct, though less informative than the factual sentence ``Barack Obama was born in Honolulu, Hawaii, United States''. Despite the known fact that LLMs tend to hallucinate and generate factually incorrect text, they might also tend to choose to generate factual text that is indeed factually correct and yet less informative than other, more informative choices. In this work, we tackle this problem by proposing an informativeness alignment mechanism. This mechanism takes advantage of recent factual benchmarks to propose an informativeness alignment objective. This objective prioritizes answers that are both correct and informative. A key finding of our work is that when training a model to maximize this objective or optimize its preference, we can improve not just informativeness but also factuality.
format Preprint
id arxiv_https___arxiv_org_abs_2505_20487
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle InFact: Informativeness Alignment for Improved LLM Factuality
Cohen, Roi
Biswas, Russa
de Melo, Gerard
Computation and Language
Artificial Intelligence
Factual completeness is a general term that captures how detailed and informative a factually correct text is. For instance, the factual sentence ``Barack Obama was born in the United States'' is factually correct, though less informative than the factual sentence ``Barack Obama was born in Honolulu, Hawaii, United States''. Despite the known fact that LLMs tend to hallucinate and generate factually incorrect text, they might also tend to choose to generate factual text that is indeed factually correct and yet less informative than other, more informative choices. In this work, we tackle this problem by proposing an informativeness alignment mechanism. This mechanism takes advantage of recent factual benchmarks to propose an informativeness alignment objective. This objective prioritizes answers that are both correct and informative. A key finding of our work is that when training a model to maximize this objective or optimize its preference, we can improve not just informativeness but also factuality.
title InFact: Informativeness Alignment for Improved LLM Factuality
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2505.20487