Hallucination Benchmark

Hallucination benchmarks are crucial for evaluating the reliability of large language and vision models (LLMs and LVLMs), which are prone to generating factually incorrect or inconsistent outputs. Current research focuses on developing more robust and comprehensive benchmarks, including those based on knowledge graphs, entity-relationship models, and automatically generated datasets, to better assess various types of hallucinations across different model architectures and tasks. These efforts aim to improve the accuracy and trustworthiness of LLMs and LVLMs, ultimately leading to more reliable applications in diverse fields. The development of high-quality benchmarks is essential for advancing the field and ensuring responsible deployment of these powerful technologies.

Papers

November 5, 2024

V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization
Yuxi Xie, Guanzhen Li, Xiao Xu, Min-Yen Kan
Large Vision Language Model Direct Preference Optimization Mitigating Hallucination Direct Preference Hallucination Benchmark

October 30, 2024

Unified Triplet-Level Hallucination Evaluation for Large Vision-Language Models
Junjie Wu, Tsz Ting Chung, Kai Chen, Dit-Yan Yeung
Full Model Hallucination Evaluation Object Hallucination Hallucination Benchmark Large Vision Language Relation Hallucination

October 21, 2024

Mitigating Object Hallucination via Concentric Causal Attention
Yun Xing, Yiheng Li, Ivan Laptev, Shijian Lu
Large Vision Language Model Mitigating Hallucination Causal Attention Object Hallucination Hallucination Benchmark

October 13, 2024

LongHalQA: Long-Context Hallucination Evaluation for MultiModal Large Language Models
Han Qiu, Jiaxing Huang, Peng Gao, Qin Qi, Xiaoqin Zhang, Ling Shao, Shijian Lu
Language Model Multimodal Large Language Model Hallucination Evaluation Large Scale Multimodal Hallucination Benchmark

September 30, 2024

HELPD: Mitigating Hallucination of LVLMs by Hierarchical Feedback Learning with Vision-enhanced Penalty Decoding
Fan Yuan, Chi Qin, Xiaogang Xu, Piji Li
Large Vision Language Model Content Hallucination Hierarchical Learning Constrained Decoding Multimodal Hallucination Hallucination Benchmark Hierarchical Policy Learning Gradient Penalty

July 15, 2024

GraphEval: A Knowledge-Graph Based LLM Hallucination Evaluation Framework
Hannah Sansford, Nicholas Richardson, Hermina Petric Maretic, Juba Nait Saada
Large Language Model Natural Language Inference Hallucination Evaluation Language Model Hallucination Hallucination Benchmark

June 24, 2024

Evaluating the Quality of Hallucination Benchmarks for Large Vision-Language Models
Bei Yan, Jie Zhang, Zheng Yuan, Shiguang Shan, Xilin Chen
Large Vision Language Model Content Hallucination Quality Issue Hallucination Benchmark Hallucination Evaluation Benchmark

June 16, 2024

AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models
Xiyang Wu, Tianrui Guan, Dianqi Li, Shuaiyi Huang, Xiaoyu Liu, Xijun Wang, Ruiqi Xian, Abhinav Shrivastava, Furong Huang, Jordan Lee Boyd-Graber, Tianyi Zhou, Dinesh Manocha
Vision Language Model Large Vision Language Model Automatic Generation Model Hallucination LLM Hallucination Hallucination Benchmark

June 11, 2024

HalluDial: A Large-Scale Benchmark for Automatic Dialogue-Level Hallucination Evaluation
Wen Luo, Tianshu Shen, Wei Li, Guangyue Peng, Richeng Xuan, Houfeng Wang, Xi Yang
Hallucination Evaluation Hallucination Benchmark

April 16, 2024

Prescribing the Right Remedy: Mitigating Hallucinations in Large Vision-Language Models via Targeted Instruction Tuning
Rui Hu, Yahan Tu, Jitao Sang
Large Vision Language Model Instruction Tuning Mitigating Hallucination Model Hallucination Hallucination Benchmark

March 8, 2024

ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models
Jio Oh, Soyeon Kim, Junseok Seo, Jindong Wang, Ruochen Xu, Xing Xie, Steven Euijong Whang
Large Language Model New Benchmark LLM Benchmark Relational Database Entity Relation Hallucination Benchmark Hallucination Evaluation Benchmark

March 6, 2024

Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem
Yuhong Sun, Zhangyue Yin, Qipeng Guo, Jiawen Wu, Xipeng Qiu, Hui Zhao
Large Language Model Natural Language Processing Question Answering Math Word Problem LLM Hallucination Hallucination Benchmark

March 3, 2024

In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
Shiqi Chen, Miao Xiong, Junteng Liu, Zhengxuan Wu, Teng Xiao, Siyang Gao, Junxian He
Large Language Model Internal Representation Mitigating Hallucination Node Feature Sharpness Alert System Hallucination Benchmark

January 11, 2024

Hallucination Benchmark in Medical Visual Question Answering
Jinge Wu, Yunsoo Kim, Honghan Wu
Visual Question Answering Vision Model Medical Visual Question Answering Type II Hallucination Vision Assistant Hallucination Benchmark

January 6, 2024

The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models
Junyi Li, Jie Chen, Ruiyang Ren, Xiaoxue Cheng, Wayne Xin Zhao, Jian-Yun Nie, Ji-Rong Wen
Large Language Model Empirical Study Content Hallucination Hallucination Detection LLM Hallucination False Premise Hallucination Hallucination Benchmark

December 31, 2023

RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models
Cheng Niu, Yuanhao Wu, Juno Zhu, Siliang Xu, Kashun Shum, Randy Zhong, Juntong Song, Tong Zhang
Mitigating Hallucination Hallucination Detection Retrieval Augmented Language Model Kg Rag Multimodal Hallucination Hallucination Benchmark

Hallucination Benchmark

Papers

V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization

Unified Triplet-Level Hallucination Evaluation for Large Vision-Language Models

Mitigating Object Hallucination via Concentric Causal Attention

LongHalQA: Long-Context Hallucination Evaluation for MultiModal Large Language Models

HELPD: Mitigating Hallucination of LVLMs by Hierarchical Feedback Learning with Vision-enhanced Penalty Decoding

GraphEval: A Knowledge-Graph Based LLM Hallucination Evaluation Framework

Evaluating the Quality of Hallucination Benchmarks for Large Vision-Language Models

AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models

HalluDial: A Large-Scale Benchmark for Automatic Dialogue-Level Hallucination Evaluation

Prescribing the Right Remedy: Mitigating Hallucinations in Large Vision-Language Models via Targeted Instruction Tuning

ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models

Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem

In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation

Hallucination Benchmark in Medical Visual Question Answering

The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models

RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models