Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mishra, Aditi, Rahman, Sajjadur, Kim, Hannah, Mitra, Kushan, Hruschka, Estevam
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2311.05085
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913218274787328
author Mishra, Aditi
Rahman, Sajjadur
Kim, Hannah
Mitra, Kushan
Hruschka, Estevam
author_facet Mishra, Aditi
Rahman, Sajjadur
Kim, Hannah
Mitra, Kushan
Hruschka, Estevam
contents Large language models (LLMs) are proficient at generating fluent text with minimal task-specific supervision. Yet, their ability to provide well-grounded rationalizations for knowledge-intensive tasks remains under-explored. Such tasks, like commonsense multiple-choice questions, require rationales based on world knowledge to support predictions and refute alternate options. We consider the task of generating knowledge-guided rationalization in natural language by using expert-written examples in a few-shot manner. Surprisingly, crowd-workers preferred knowledge-grounded rationales over crowdsourced rationalizations, citing their factuality, sufficiency, and comprehensive refutations. Although LLMs-generated rationales were preferable, further improvements in conciseness and novelty are required. In another study, we show how rationalization of incorrect model predictions erodes humans' trust in LLM-generated rationales. Motivated by these observations, we create a two-stage pipeline to review task predictions and eliminate potential incorrect decisions before rationalization, enabling trustworthy rationale generation.
format Preprint
id arxiv_https___arxiv_org_abs_2311_05085
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Characterizing Large Language Models as Rationalizers of Knowledge-intensive Tasks
Mishra, Aditi
Rahman, Sajjadur
Kim, Hannah
Mitra, Kushan
Hruschka, Estevam
Computation and Language
Artificial Intelligence
Large language models (LLMs) are proficient at generating fluent text with minimal task-specific supervision. Yet, their ability to provide well-grounded rationalizations for knowledge-intensive tasks remains under-explored. Such tasks, like commonsense multiple-choice questions, require rationales based on world knowledge to support predictions and refute alternate options. We consider the task of generating knowledge-guided rationalization in natural language by using expert-written examples in a few-shot manner. Surprisingly, crowd-workers preferred knowledge-grounded rationales over crowdsourced rationalizations, citing their factuality, sufficiency, and comprehensive refutations. Although LLMs-generated rationales were preferable, further improvements in conciseness and novelty are required. In another study, we show how rationalization of incorrect model predictions erodes humans' trust in LLM-generated rationales. Motivated by these observations, we create a two-stage pipeline to review task predictions and eliminate potential incorrect decisions before rationalization, enabling trustworthy rationale generation.
title Characterizing Large Language Models as Rationalizers of Knowledge-intensive Tasks
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2311.05085