CV

You can download my CV in PDF.

Education

• B.S. in Huazhong University of Science and Technology, 2015 - 2019
• Ph.D Candidate in ECE Department, Hong Kong University of Science and Technology, 2019 - Present

Work experience

• Research Intern: Jul. 2023 - Jan. 2024
  • Shanghai AI Lab, Shanghai, China
  • Mentor: Wenwei Zhang
  • Build an analytical hallucination annotation dataset in Large Language Models. Employing the dataset, we train hallucination annotators based on InternLM-7B/20B. Accepted in ACL 2024.
  • Scale analytical hallucination annotation progressively and improve the accuracy of the annotator with an iterative self-training framework. And apply the annotator for hallucination mitigation. Submitted to NeurIPS 2024.

Awards

• Area Chair Award (Language Modeling and Analysis) at AACL, 2023
• Silver medal (Top 2%) in Kaggle Competition: Stable Diffusion - Image to Prompts, 2023
• National Scholarship, Ministry of Education of P.R.China (0.2%), 2016, 2017, 2018
• Merit Student (3%), 2016, 2017, 2018
• Outstanding Scientific Research Achievement Award for University Students in Hubei Province, 2018
• Outstanding Undergraduates in Term of Academic Performance (1%), 2016
• Second Prize of Hubei Province in National Undergraduate Mathematics Competition, 2017

Publications

ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models

Ji, Z., Gu, Y., Zhang, W., Lyu, C., Lin, D., & Chen, K. (2024). ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models

ANAH: Analytical Annotation of Hallucinations in Large Language Models

Ji, Z., Gu, Y., Zhang, W., Lyu, C., Lin, D., & Chen, K. (2024). ANAH: Analytical Annotation of Hallucinations in Large Language Models. ACL 2024

Negative object presence evaluation (nope) to measure object hallucination in vision-language models

Lovenia, H., Dai, W., Cahyawijaya, S., Ji, Z., & Fung, P. (2024). Negative object presence evaluation (nope) to measure object hallucination in vision-language models. ACL ALVR 2024

Contrastive Learning for Inference in Dialogue. EMNLP 2023

Ishii, E., Xu, Y., Wilie, B., Ji, Z., Lovenia, H., Chung, W., & Fung, P. (2023). Contrastive Learning for Inference in Dialogue. EMNLP 2023

Towards Mitigating Hallucination in Large Language Models via Self-Reflection

Ji Z, Yu T, Xu Y, Lee N, Ishii E, Fung P. Towards Mitigating Hallucination in Large Language Models via Self-Reflection. arXiv preprint arXiv:2310.06271. 2023 Oct 10.

Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference

Xu, Y., Kong, D., Xu, D., Ji, Z., Pang, B., Fung, P. & Wu, Y.N.. (2023). Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference. ICML 2023

A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity

Bang Y, Cahyawijaya S, Lee N, Dai W, Su D, Wilie B, Lovenia H, Ji Z, Yu T, Chung W, Do QV. A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity. arXiv preprint arXiv:2302.04023. 2023 Feb 8.

NusaCrowd: Open Source Initiative for Indonesian NLP Resources

Cahyawijaya S, Lovenia H, Aji AF, Winata GI, Wilie B, Mahendra R, Wibisono C, Romadhony A, Vincentio K, Koto F, Santoso J. NusaCrowd: Open Source Initiative for Indonesian NLP Resources. arXiv preprint arXiv:2212.09648. 2022 Dec 19.

RHO (ρ): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding

Ji, Z., Liu, Z., Lee, N., Yu, T., Wilie, B., Zeng, M., & Fung, P. (2022). RHO ($\rho $): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding. arXiv preprint arXiv:2212.01588.

Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training

Dai W, Liu Z, Ji Z, Su D, Fung P. Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training. arXiv preprint arXiv:2210.07688. 2022 Oct 14.

VScript: Controllable Script Generation with Visual Presentation

Ji Z, Xu Y, Cheng I, Cahyawijaya S, Frieske R, Ishii E, Zeng M, Madotto A, Fung P. VScript: Controllable Script Generation with Audio-Visual Presentation. arXiv preprint arXiv:2203.00314. 2022 Mar 1.

Survey of hallucination in natural language generation

Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Yejin Bang, Andrea Madotto, and Pascale Fung. 2022. Survey of Hallucination in Natural Language Generation. ACM Comput. Surv. Just Accepted (November 2022). https://doi.org/10.1145/3571730

CrossNER: Evaluating Cross-Domain Named Entity Recognition

Liu, Zihan, et al. "CrossNER: Evaluating Cross-Domain Named Entity Recognition." arXiv preprint arXiv:2012.04373 (2020).

Model Generalization on COVID-19 Fake News Detection

Bang Y, Ishii E, Cahyawijaya S, Ji Z, Fung P. Model Generalization on COVID-19 Fake News Detection. arXiv preprint arXiv:2101.03841. 2021 Jan.

Multi-hop Question Generation with Graph Convolutional Network

Su D, Xu Y, Dai W, et al. Multi-hop Question Generation with Graph Convolutional Network[J]. arXiv preprint arXiv:2010.09240, 2020.

Impact of ionization equilibrium on electrokinetic flow of weak electrolytes in nanochannels

Ji, Z., Huang, Z., Chen, B., He, Y., Tsutsui, M. and Miao, X., 2018. Impact of ionization equilibrium on electrokinetic flow of weak electrolytes in nanochannels. Nanotechnology, 29(29), p.295402.

The impact of membrane surface charges on the ion transport in MoS2 nanopore power generators

Huang, Z., Zhang, Y., Hayashida, T., Ji, Z., He, Y., Tsutsui, M., Miao, X.S. and Taniguchi, M., 2017. The impact of membrane surface charges on the ion transport in MoS2 nanopore power generators. Applied Physics Letters, 111(26), p.263104.

Skills

• Python, Pytorch, C, JavaScript, HTML, MATLAB, Photoshop, Premiere Pro

Languages

Chinese (Mother Tongue), English (Full-Proficiency)

Service and leadership

• Reviewer: EMNLP, ACL