paper-with-me

홈 › Papers

Evaluating Hallucinations in Chinese Large Language Models

2023-10-05 · Qinyuan Cheng, Tianxiang Sun, Wenwei Zhang, Siyin Wang, Xiangyang Liu, Mozhi Zhang, Junliang He, Mianqiu Huang, Zhangyue Yin, Kai Chen, Xipeng Qiu

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.

📄 PDF Abstract BibTeX arXiv:2310.03368

Code (3)

xiami2019/halluqa 공식 구현
IAAR-Shanghai/UHGEval
wangrongsheng/caregpt

Tasks

HallucinationQuestion Answering

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation

2023-11-26 · Xun Liang, Shichao Song, Simin Niu, Zhiyu Li 외

Large language models (LLMs) have emerged as pivotal contributors in contemporary natural language processing and are increasingly being applied across a diverse range of industries. However, these large-scale probabilis…

BenchmarkingHallucinationHallucination EvaluationText Generation

THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models

2024-05-08 · CVPR 2024 1 · Prannay Kaul, Zhizhong Li, Hao Yang, Yonatan Dukler 외

Mitigating hallucinations in large vision-language models (LVLMs) remains an open problem. Recent benchmarks do not address hallucinations in open-ended free-form responses, which we term "Type I hallucinations". Instead…

AttributeData AugmentationFormHallucination+1

Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Models

2024-06-24 · Mingrui Wu, Jiayi Ji, Oucheng Huang, Jiale Li 외

The issue of hallucinations is a prevalent concern in existing Large Vision-Language Models (LVLMs). Previous efforts have primarily focused on investigating object hallucinations, which can be easily alleviated by intro…

Common Sense ReasoningHallucinationObject

VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models

2024-06-24 · Yuxuan Wang, Yueqian Wang, Dongyan Zhao, Cihang Xie 외

Recent advancements in Multimodal Large Language Models (MLLMs) have extended their capabilities to video understanding. Yet, these models are often plagued by "hallucinations", where irrelevant or nonsensical content is…

HallucinationVideo Understanding

Are Large Language Models Good Fact Checkers: A Preliminary Study

2023-11-29 · Han Cao, Lingwei Wei, Mengyang Chen, Wei Zhou 외

Recently, Large Language Models (LLMs) have drawn significant attention due to their outstanding reasoning capabilities and extensive knowledge repository, positioning them as superior in handling various natural languag…

Fact CheckingFact Verification