Alert button
Picture for Tiezheng Yu

Tiezheng Yu

Alert button

Towards Mitigating Hallucination in Large Language Models via Self-Reflection

Oct 10, 2023
Ziwei Ji, Tiezheng Yu, Yan Xu, Nayeon Lee, Etsuko Ishii, Pascale Fung

Figure 1 for Towards Mitigating Hallucination in Large Language Models via Self-Reflection
Figure 2 for Towards Mitigating Hallucination in Large Language Models via Self-Reflection
Figure 3 for Towards Mitigating Hallucination in Large Language Models via Self-Reflection
Figure 4 for Towards Mitigating Hallucination in Large Language Models via Self-Reflection
Viaarxiv icon

Improving Query-Focused Meeting Summarization with Query-Relevant Knowledge

Sep 05, 2023
Tiezheng Yu, Ziwei Ji, Pascale Fung

Figure 1 for Improving Query-Focused Meeting Summarization with Query-Relevant Knowledge
Figure 2 for Improving Query-Focused Meeting Summarization with Query-Relevant Knowledge
Figure 3 for Improving Query-Focused Meeting Summarization with Query-Relevant Knowledge
Figure 4 for Improving Query-Focused Meeting Summarization with Query-Relevant Knowledge
Viaarxiv icon

Instruct-Align: Teaching Novel Languages with to LLMs through Alignment-based Cross-Lingual Instruction

May 23, 2023
Samuel Cahyawijaya, Holy Lovenia, Tiezheng Yu, Willy Chung, Pascale Fung

Figure 1 for Instruct-Align: Teaching Novel Languages with to LLMs through Alignment-based Cross-Lingual Instruction
Figure 2 for Instruct-Align: Teaching Novel Languages with to LLMs through Alignment-based Cross-Lingual Instruction
Figure 3 for Instruct-Align: Teaching Novel Languages with to LLMs through Alignment-based Cross-Lingual Instruction
Figure 4 for Instruct-Align: Teaching Novel Languages with to LLMs through Alignment-based Cross-Lingual Instruction
Viaarxiv icon

A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity

Feb 28, 2023
Yejin Bang, Samuel Cahyawijaya, Nayeon Lee, Wenliang Dai, Dan Su, Bryan Wilie, Holy Lovenia, Ziwei Ji, Tiezheng Yu, Willy Chung, Quyet V. Do, Yan Xu, Pascale Fung

Figure 1 for A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
Figure 2 for A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
Figure 3 for A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
Figure 4 for A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
Viaarxiv icon

NusaCrowd: Open Source Initiative for Indonesian NLP Resources

Dec 20, 2022
Samuel Cahyawijaya, Holy Lovenia, Alham Fikri Aji, Genta Indra Winata, Bryan Wilie, Rahmad Mahendra, Christian Wibisono, Ade Romadhony, Karissa Vincentio, Fajri Koto, Jennifer Santoso, David Moeljadi, Cahya Wirawan, Frederikus Hudi, Ivan Halim Parmonangan, Ika Alfina, Muhammad Satrio Wicaksono, Ilham Firdausi Putra, Samsul Rahmadani, Yulianti Oenang, Ali Akbar Septiandri, James Jaya, Kaustubh D. Dhole, Arie Ardiyanti Suryani, Rifki Afina Putri, Dan Su, Keith Stevens, Made Nindyatama Nityasya, Muhammad Farid Adilazuarda, Ryan Ignatius, Ryandito Diandaru, Tiezheng Yu, Vito Ghifari, Wenliang Dai, Yan Xu, Dyah Damapuspita, Cuk Tho, Ichwanul Muslim Karo Karo, Tirana Noor Fatyanosa, Ziwei Ji, Pascale Fung, Graham Neubig, Timothy Baldwin, Sebastian Ruder, Herry Sujaini, Sakriani Sakti, Ayu Purwarianti

Figure 1 for NusaCrowd: Open Source Initiative for Indonesian NLP Resources
Figure 2 for NusaCrowd: Open Source Initiative for Indonesian NLP Resources
Figure 3 for NusaCrowd: Open Source Initiative for Indonesian NLP Resources
Figure 4 for NusaCrowd: Open Source Initiative for Indonesian NLP Resources
Viaarxiv icon

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

Dec 03, 2022
Ziwei Ji, Zihan Liu, Nayeon Lee, Tiezheng Yu, Bryan Wilie, Min Zeng, Pascale Fung

Figure 1 for RHO ($ρ$): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding
Figure 2 for RHO ($ρ$): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding
Figure 3 for RHO ($ρ$): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding
Figure 4 for RHO ($ρ$): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding
Viaarxiv icon

Casual Conversations v2: Designing a large consent-driven dataset to measure algorithmic bias and robustness

Nov 10, 2022
Caner Hazirbas, Yejin Bang, Tiezheng Yu, Parisa Assar, Bilal Porgali, Vítor Albiero, Stefan Hermanek, Jacqueline Pan, Emily McReynolds, Miranda Bogen, Pascale Fung, Cristian Canton Ferrer

Figure 1 for Casual Conversations v2: Designing a large consent-driven dataset to measure algorithmic bias and robustness
Figure 2 for Casual Conversations v2: Designing a large consent-driven dataset to measure algorithmic bias and robustness
Figure 3 for Casual Conversations v2: Designing a large consent-driven dataset to measure algorithmic bias and robustness
Figure 4 for Casual Conversations v2: Designing a large consent-driven dataset to measure algorithmic bias and robustness
Viaarxiv icon

Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values

Oct 14, 2022
Yejin Bang, Tiezheng Yu, Andrea Madotto, Zhaojiang Lin, Mona Diab, Pascale Fung

Figure 1 for Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values
Figure 2 for Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values
Figure 3 for Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values
Figure 4 for Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values
Viaarxiv icon

Kaggle Competition: Cantonese Audio-Visual Speech Recognition for In-car Commands

Jul 06, 2022
Wenliang Dai, Samuel Cahyawijaya, Tiezheng Yu, Elham J Barezi, Pascale Fung

Figure 1 for Kaggle Competition: Cantonese Audio-Visual Speech Recognition for In-car Commands
Figure 2 for Kaggle Competition: Cantonese Audio-Visual Speech Recognition for In-car Commands
Figure 3 for Kaggle Competition: Cantonese Audio-Visual Speech Recognition for In-car Commands
Figure 4 for Kaggle Competition: Cantonese Audio-Visual Speech Recognition for In-car Commands
Viaarxiv icon