FineDialFact: A benchmark for Fine-grained Dialogue Fact Verification

TL;DR

FineDialFact introduces a new benchmark for fine-grained fact verification in dialogue responses, highlighting the challenges and potential of Chain-of-Thought reasoning methods in improving factual accuracy detection.

Contribution

The paper presents a novel benchmark and dataset for atomic fact verification in dialogue, emphasizing the need for fine-grained approaches beyond coarse factual labels.

Findings

Chain-of-Thought reasoning improves verification performance.

Best F1-score on HybriDialogue is 0.75, showing room for improvement.

Benchmark remains challenging for current methods.

Abstract

Large Language Models (LLMs) are known to produce hallucinations - factually incorrect or fabricated information - which poses significant challenges for many Natural Language Processing (NLP) applications, such as dialogue systems. As a result, detecting hallucinations has become a critical area of research. Current approaches to hallucination detection in dialogue systems primarily focus on verifying the factual consistency of generated responses. However, these responses often contain a mix of accurate, inaccurate or unverifiable facts, making one factual label overly simplistic and coarse-grained. In this paper, we introduce a benchmark, FineDialFact, for fine-grained dialogue fact verification, which involves verifying atomic facts extracted from dialogue responses. To support this, we construct a dataset based on publicly available dialogue datasets and evaluate it using various baseline methods. Experimental results demonstrate that methods incorporating Chain-of-Thought (CoT) reasoning can enhance performance in dialogue fact verification. Despite this, the best F1-score achieved on the HybriDialogue, an open-domain dialogue dataset, is only 0.75, indicating that the benchmark remains a challenging task for future research. Our dataset and code will be public on GitHub.