Salvato in:
Dettagli Bibliografici
Autori principali: Murzaku, John, Rambow, Owen
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2502.08777
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916611873570816
author Murzaku, John
Rambow, Owen
author_facet Murzaku, John
Rambow, Owen
contents We present two LLM-based approaches to zero-shot source-and-target belief prediction on FactBank: a unified system that identifies events, sources, and belief labels in a single pass, and a hybrid approach that uses a fine-tuned DeBERTa tagger for event detection. We show that multiple open-sourced, closed-source, and reasoning-based LLMs struggle with the task. Using the hybrid approach, we achieve new state-of-the-art results on FactBank and offer a detailed error analysis. Our approach is then tested on the Italian belief corpus ModaFact.
format Preprint
id arxiv_https___arxiv_org_abs_2502_08777
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Zero-Shot Belief: A Hard Problem for LLMs
Murzaku, John
Rambow, Owen
Computation and Language
We present two LLM-based approaches to zero-shot source-and-target belief prediction on FactBank: a unified system that identifies events, sources, and belief labels in a single pass, and a hybrid approach that uses a fine-tuned DeBERTa tagger for event detection. We show that multiple open-sourced, closed-source, and reasoning-based LLMs struggle with the task. Using the hybrid approach, we achieve new state-of-the-art results on FactBank and offer a detailed error analysis. Our approach is then tested on the Italian belief corpus ModaFact.
title Zero-Shot Belief: A Hard Problem for LLMs
topic Computation and Language
url https://arxiv.org/abs/2502.08777