Evaluating Hallucinations in Chinese Large Language Models

2023/10/05 by Qinyuan Cheng, Cheng, Qinyuan, Tianxiang Sun +19 · 7 citations
Computer Science · Social Sciences · #Computation and Language (cs.CL) #Computational and Text Analysis Methods #FOS: Computer and information sciences #Sentiment Analysis and Opinion Mining #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2310.03368

openalex publication_date 2023/10/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper, we establish a benchmark named HalluQA (Chinese Hallucination Question-Answering) to measure the hallucination phenomenon in Chinese large language models. HalluQA contains 450 meticulously designed adversarial questions, spanning multiple domains, and takes into account Chinese historical culture, customs, and social phenomena. During the construction of HalluQA, we consider two types of hallucinations: imitative falsehoods and factual errors, and we construct adversarial samples based on GLM-130B and ChatGPT. For evaluation, we design an automated evaluation method using GPT-4 to judge whether a model output is hallucinated. We conduct extensive experiments on 24 large language models, including ERNIE-Bot, Baichuan2, ChatGLM, Qwen, SparkDesk and etc. Out of the 24 models, 18 achieved non-hallucination rates lower than 50%. This indicates that HalluQA is highly challenging. We analyze the primary types of hallucinations in different types of models and their causes. Additionally, we discuss which types of hallucinations should be prioritized for different types of models.

Cited by

• Acquiring Common Chinese Emotional Events Using Large Language Model
• MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMs
• Large Language Models Hallucination: A Comprehensive Survey
• A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models
• Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models
• DecompileBench: A Comprehensive Benchmark for Evaluating Decompilers in Real-World Scenarios
• HalluLens: LLM Hallucination Benchmark

Related

• Investigating Hallucination in Conversations for Low Resource Languages
• HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
• DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Models
• 🧜Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models
• Large Language Models Hallucination: A Comprehensive Survey