7 citations · 23 across the 19 of their papers we have counts for
21 papers
Looped World Models
Hongyuan Adam Lu, Z. L. Victor Wei, Qun Zhang +28
Current world models face a fundamental tension: faithful long-horizon simulation demands deep computation, but deeper models are expensive to deploy and prone to compounding error…
Adam's Law: Textual Frequency Law on Large Language Models
Hongyuan Adam Lu, Z. L., Victor Wei +5
While textual frequency has been validated as relevant to human cognition in reading speed, its relatedness to Large Language Models (LLMs) is seldom studied. We propose a novel re…
VERHallu: Evaluating and Mitigating Event Relation Hallucination in Video Large Language Models
Zefan Zhang, Kehua Zhu, Shijie Jiang +3
Video Large Language Models (VideoLLMs) exhibit various types of hallucinations. Existing research has primarily focused on hallucinations involving the presence of events, objects…
Stephanie2: Thinking, Waiting, and Making Decisions Like Humans in Step-by-Step AI Social Chat
Hao Yang, Hongyuan Lu, Dingkang Yang +8
Instant-messaging human social chat typically progresses through a sequence of short messages. Existing step-by-step AI chatting systems typically split a one-shot generation into…
From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics
Bowen Cao, Dongdong Zhang, Yixia Li +8
Large language models now solve many benchmark math problems at near-expert levels, yet this progress has not fully translated into reliable performance in real-world applications.…
LNE-Blocking: An Efficient Framework for Contamination Mitigation Evaluation on Large Language Models
Ruijie Hou, Yueyang Jiao, Hanxu Hu +4
The problem of data contamination is now almost inevitable during the development of large language models (LLMs), with the training data commonly integrating those evaluation benc…
SLoW: Select Low-frequency Words! Automatic Dictionary Selection for Translation on Large Language Models
Hongyuan Lu, Zixuan Li, Zefan Zhang +1
There are more than 7,000 languages around the world, and current Large Language Models (LLMs) only support hundreds of languages. Dictionary-based prompting methods can enhance tr…
Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Models
Hongyuan Lu, Zixuan Li, Wai Lam
There are two shortages in the current Large Language Models (LLMs) era. The first is short of multilingual models, where most LLMs are English-centric and performance is limited o…
Clean Evaluations on Contaminated Visual Language Models
Hongyuan Lu, Shujie Miao, Wai Lam
How to evaluate large language models (LLMs) cleanly has been established as an important research era to genuinely report the performance of possibly contaminated LLMs. Yet, how t…
Toxic Subword Pruning for Dialogue Response Generation on Large Language Models
Hongyuan Lu, Wai Lam
How to defend large language models (LLMs) from generating toxic content is an important research area. Yet, most research focused on various model training techniques to remediate…
Stephanie: Step-by-Step Dialogues for Mimicking Human Interactions in Social Conversations
Hao Yang, Hongyuan Lu, Xinhua Zeng +7
In the rapidly evolving field of natural language processing, dialogue systems primarily employ a single-step dialogue paradigm. Although this paradigm is efficient, it lacks the d…
Unveiling the Generalization Power of Fine-Tuned Large Language Models
Haoran Yang, Yumeng Zhang, Jiaqi Xu +3
While Large Language Models (LLMs) have demonstrated exceptional multitasking abilities, fine-tuning these models on downstream, domain-specific datasets is often necessary to yiel…
Consecutive Batch Model Editing with HooK Layers
Shuaiyi Li, Yang Deng, Deng Cai +3
As the typical retraining paradigm is unacceptably time- and resource-consuming, researchers are turning to model editing to find an effective way that supports both consecutive an…
EPA: Easy Prompt Augmentation on Large Language Models via Multiple Sources and Multiple Targets
Hongyuan Lu, Wai Lam
Large language models (LLMs) have shown promising performance on various NLP tasks via task prompting. And their performance can be further improved by appending task demonstration…
Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying References
Tianyi Tang, Hongyuan Lu, Yuchen Eleanor Jiang +5
Most research about natural language generation (NLG) relies on evaluation benchmarks with limited references for a sample, which may result in poor correlations with human judgeme…
Chain-of-Symbol Prompting Elicits Planning in Large Langauge Models
Hanxu Hu, Hongyuan Lu, Huajian Zhang +3
In this paper, we take the initiative to investigate the performance of LLMs on complex planning tasks that require LLMs to understand a virtual spatial environment simulated via n…
Chain-of-Dictionary Prompting Elicits Translation in Large Language Models
Hongyuan Lu, Haoran Yang, Haoyang Huang +3
Large language models (LLMs) have shown surprisingly good performance in multilingual neural machine translation (MNMT) even when trained without parallel data. Yet, despite the fa…
Advancing Multilingual Pre-training: TRIP Triangular Document-level Pre-training for Multilingual Language Models
Hongyuan Lu, Haoyang Huang, Shuming Ma +3
Despite the success of multilingual sequence-to-sequence pre-training, most existing approaches rely on document-level monolingual corpora in many different languages, sentence-lev…
Revamping Multilingual Agreement Bidirectionally via Switched Back-translation for Multilingual Neural Machine Translation
Hongyuan Lu, Haoyang Huang, Shuming Ma +3
Despite the fact that multilingual agreement (MA) has shown its importance for multilingual neural machine translation (MNMT), current methodologies in the field have two shortages…
PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentation
Hongyuan Lu, Wai Lam
Curriculum Data Augmentation (CDA) improves neural models by presenting synthetic data with increasing difficulties from easy to hard. However, traditional CDA simply treats the ra…
Partner Personas Generation for Diverse Dialogue Generation
Hongyuan Lu, Wai Lam, Hong Cheng +1
Incorporating personas information allows diverse and engaging responses in dialogue response generation. Unfortunately, prior works have primarily focused on self personas and hav…