mlsanityData to 14 Oct 2026

Zero-Shot Belief: A Hard Problem for LLMs

arXiv 2502.08777 ↗First posted 12 Feb 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 30 references that are in the map. First posted on arXiv 12 Feb 2025.

Builds on

8 of 30 references.

References · 8

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  2. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,818
  3. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,254
  4. 2018Neural models of factualitycited by 20
  5. 2018Lexicosyntactic Inference in Neural Modelscited by 14
  6. 2021He Thinks He Knows Better than the Doctors: BERT for Event Factuality Fails on Pragmaticscited by 12
  7. 2019Graph based Neural Networks for Event Factuality Prediction using Syntactic and Semantic Structurescited by 9
  8. 2024MAVEN-Fact: A Large-scale Event Factuality Detection Datasetcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning
  2. 2023LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond
  3. 2024Are LLMs Good Zero-Shot Fallacy Classifiers?
  4. 2023Prompt to be Consistent is Better than Self-Consistent? Few-Shot and Zero-Shot Fact Verification with Pre-trained Language Models
  5. 2025Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers
  6. 2022Large Language Models are Zero-Shot Reasoners
  7. 2025Training-free LLM Verification via Recycling Few-shot Examples
  8. 2025Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning