Publications (70)
Ethical Implications of ChatGPT in Higher Education: A Scoping Review
Ming Li, Ariunaa Enkhtur, Fei Cheng +1
This scoping review explores the ethical challenges of using ChatGPT in higher education. By reviewing recent academic articles in English, Chinese, and Japanese, we aimed to provi…
ArchCAD-400K: A Large-Scale CAD drawings Dataset and New Baseline for Panoptic Symbol Spotting
Ruifeng Luo, Zhengjie Liu, Tianxiao Cheng +13
Recognizing symbols in architectural CAD drawings is critical for various advanced engineering applications. In this paper, we propose a novel CAD data annotation engine that lever…
LightCL: Compact Continual Learning with Low Memory Footprint For Edge Device
Zeqing Wang, Fei Cheng, Kangye Ji +1
Continual learning (CL) is a technique that enables neural networks to constantly adapt to their dynamic surroundings. Despite being overlooked for a long time, this technology can…
Revisiting Anthropomorphic Reflection Markers in Large Language Model Reasoning
Yahan Yu, Noa Nakanishi, Fei Cheng
Large Language Models (LLMs) often produce explicit reflective traces during complex reasoning, accompanied by anthropomorphic markers such as wait, hmm, and alternatively. Althoug…
Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese
Yikun Sun, Zhen Wan, Nobuhiro Ueda +4
The creation of instruction data and evaluation benchmarks for serving Large language models often involves enormous human annotation. This issue becomes particularly pronounced wh…
Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognition
Qianying Liu, Zhuo Gong, Zhengdong Yang +8
Low-resource speech recognition has been long-suffering from insufficient training data. In this paper, we propose an approach that leverages neighboring languages to improve low-r…
Evaluation Framework for AI Creativity: A Case Study Based on Story Generation
Pharath Sathya, Yin Jou Huang, Fei Cheng
Evaluating creative text generation remains a challenge because existing reference-based metrics fail to capture the subjective nature of creativity. We propose a structured evalua…
AMR-RE: Abstract Meaning Representations for Retrieval-Based In-Context Learning in Relation Extraction
Peitao Han, Lis Kanashiro Pereira, Fei Cheng +2
Existing in-context learning (ICL) methods for relation extraction (RE) often prioritize language similarity over structural similarity, which can lead to overlooking entity relati…
Potential Societal Biases of ChatGPT in Higher Education: A Scoping Review
Ming Li, Ariunaa Enkhtur, Beverley Anne Yamamoto +2
Purpose:Generative Artificial Intelligence (GAI) models, such as ChatGPT, may inherit or amplify societal biases due to their training on extensive datasets. With the increasing us…
MultiTool-CoT: GPT-3 Can Use Multiple External Tools with Chain of Thought Prompting
Tatsuro Inaba, Hirokazu Kiyomaru, Fei Cheng +1
Large language models (LLMs) have achieved impressive performance on various reasoning tasks. To further improve the performance, we propose MultiTool-CoT, a novel framework that l…
Pushing the Limits of ChatGPT on NLP Tasks
Xiaofei Sun, Linfeng Dong, Xiaoya Li +8
Despite the success of ChatGPT, its performances on most NLP tasks are still well below the supervised baselines. In this work, we looked into the causes, and discovered that its s…
Persona Jailbreaking in Large Language Models
Jivnesh Sandhan, Fei Cheng, Tushar Sandhan +1
Large Language Models (LLMs) are increasingly deployed in domains such as education, mental health and customer support, where stable and consistent personas are critical for relia…
Jump-teaching: Combating Sample Selection Bias via Temporal Disagreement
Kangye Ji, Fei Cheng, Zeqing Wang +2
Sample selection is a straightforward technique to combat noisy labels, aiming to prevent mislabeled samples from degrading the robustness of neural networks. However, existing met…
Comprehensive Solution Program Centric Pretraining for Table-and-Text Hybrid Numerical Reasoning
Qianying Liu, Dongsheng Yang, Wenjie Zhong +2
Numerical reasoning over table-and-text hybrid passages, such as financial reports, poses significant challenges and has numerous potential applications. Noise and irrelevant varia…
A Framework for Developing University Policies on Generative AI Governance: A Cross-national Comparative Study
Ming Li, Qin Xie, Ariunaa Enkhtur +5
As generative AI (GAI) becomes increasingly embedded in higher education, universities worldwide are developing policies to govern its ethical, pedagogical, and institutional use.…
Better Generalizing to Unseen Concepts: An Evaluation Framework and An LLM-Based Auto-Labeled Pipeline for Biomedical Concept Recognition
Shanshan Liu, Noriki Nishida, Fei Cheng +6
Generalization to unseen concepts is a central challenge due to the scarcity of human annotations in Mention-agnostic Biomedical Concept Recognition (MA-BCR). This work makes two k…
Reverse Operation based Data Augmentation for Solving Math Word Problems
Qianying Liu, Wenyu Guan, Sujian Li +3
Automatically solving math word problems is a critical task in the field of natural language processing. Recent models have reached their performance bottleneck and require more hi…
A Joint Neural Baseline for Concept, Assertion, and Relation Extraction from Clinical Text
Fei Cheng, Ribeka Tanaka, Sadao Kurohashi
Clinical information extraction (e.g., 2010 i2b2/VA challenge) usually presents tasks of concept recognition, assertion classification, and relation extraction. Jointly modeling th…
Cross-lingual Adaption Model-Agnostic Meta-Learning for Natural Language Understanding
Qianying Liu, Fei Cheng, Sadao Kurohashi
Meta learning with auxiliary languages has demonstrated promising improvements for cross-lingual natural language processing. However, previous studies sample the meta-training and…
ComSearch: Equation Searching with Combinatorial Strategy for Solving Math Word Problems with Weak Supervision
Qianying Liu, Wenyu Guan, Jianhao Shen +2
Previous studies have introduced a weakly-supervised paradigm for solving math word problems requiring only the answer value annotation. While these methods search for correct valu…
ShipSRDet: An End-to-End Remote Sensing Ship Detector Using Super-Resolved Feature Representation
Shitian He, Huanxin Zou, Yingqian Wang +2
High-resolution remote sensing images can provide abundant appearance information for ship detection. Although several existing methods use image super-resolution (SR) approaches t…
Which Way Does Time Flow? A Psychophysics-Grounded Evaluation for Vision-Language Models
Shiho Matta, Lis Kanashiro Pereira, Peitao Han +2
Modern vision-language models (VLMs) excel at many multimodal tasks, yet their grasp of temporal information in video remains weak and has not been adequately evaluated. We probe t…
Can We Trust LLM Detectors?
Jivnesh Sandhan, Harshit Jaiswal, Fei Cheng +1
The rapid adoption of LLMs has increased the need for reliable AI text detection, yet existing detectors often fail outside controlled benchmarks. We systematically evaluate 2 domi…
Between Regulation and Accessibility: How Chinese University Students Navigate Global and Domestic Generative AI
Qin Xie, Ming Li, Fei Cheng
Despite the rapid proliferation of generative AI in higher education, students in China face significant barriers in accessing global tools like ChatGPT due to regulations and cons…
Single Crystalline Silver Films for Plasmonics: From Monolayer to Optically Thick Film
Fei Cheng, Chien-Ju Lee, Junho Choi +7
Epitaxial growth of single crystalline noble metals on dielectric substrates has received tremendous attention recently due to their technological potentials as low loss plasmonic…
Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision
Zhen Wan, Fei Cheng, Qianying Liu +3
Contrastive pre-training on distant supervision has shown remarkable effectiveness in improving supervised relation extraction tasks. However, the existing methods ignore the intri…
Tailoring the Curriculum: Student-Centered Reasoning Distillation via Dynamic Data-Model Compatibility
Jiahao Huang, Fei Cheng, Junfeng Jiang +1
Reasoning distillation transfers complex reasoning abilities from large language models (LLMs) to smaller ones, yet its success depends on how well the training data align with the…
Cross-lingual Embedding Clustering for Hierarchical Softmax in Low-Resource Multilingual Speech Recognition
Zhengdong Yang, Qianying Liu, Sheng Li +2
We present a novel approach centered on the decoding stage of Automatic Speech Recognition (ASR) that enhances multilingual performance, especially for low-resource languages. It u…
When and Why Does Unsupervised RL Succeed in Mathematical Reasoning? A Manifold Envelopment Perspective
Zelin Zhang, Fei Cheng, Chenhui Chu
Although outcome-based reinforcement learning (RL) significantly advances the mathematical reasoning capabilities of Large Language Models (LLMs), its reliance on computationally e…
Dango: A Strictly L1-Only Large Language Model for Studying Second Language Acquisition
Shiho Matta, Yin Jou Huang, Fei Cheng +3
We introduce Dango, a 1.8B-parameter large language model designed for controlled studies of L1-to-L2 (Japanese-to-English) transfer in second language acquisition (SLA). While pre…
Highly nonlinear Moiré exciton and trion polaritons
Arnab Barman Ray, Trevor Ollis, Fei Cheng +3
Moiré multi-layers of transition metal dichalcogenides have been shown to exhibit optical responses that are endowed with a richness that is absent in single monolayers. Much of t…
Memorization, Emergence, and Explaining Reversal Failures: A Controlled Study of Relational Semantics in LLMs
Yihua Zhu, Qianying Liu, Jiaxin Wang +5
Autoregressive LLMs perform well on relational tasks that require linking entities via relational words (e.g., father/son, friend), but it is unclear whether they learn the logical…
Reasoning Depth and Environment Complexity: A Controlled Study of RLVR Data Allocation across Logical Reasoning Tasks
Yihua Zhu, Qianying Liu, Fei Cheng +4
Reinforcement learning with verifiable rewards (RLVR) has become central to post-training reasoning models, yet a key limitation of existing studies is their narrow view of the rea…
Language Lives in Sparse Dimensions: Toward Interpretable and Efficient Multilingual Control for Large Language Models
Chengzhi Zhong, Fei Cheng, Qianying Liu +3
Large language models exhibit strong multilingual capabilities despite limited exposure to non-English data. Prior studies show that English-centric large language models map multi…
SAMCL: Empowering SAM to Continually Learn from Dynamic Domains with Extreme Storage Efficiency
Zeqing Wang, Kangye Ji, Di Wang +2
Segment Anything Model (SAM) struggles in open-world scenarios with diverse domains. In such settings, naive fine-tuning with a well-designed learning module is inadequate and ofte…
Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs
Peitao Han, Fei Cheng, Lis K. Pereira +2
The Arrow-of-Time (AoT) task, determining whether a video plays forward or backward by recognizing temporal irreversibility, is one humans solve with near-perfect accuracy, yet fro…
CAPE: Context-Aware Personality Evaluation Framework for Large Language Models
Jivnesh Sandhan, Fei Cheng, Tushar Sandhan +1
Psychometric tests, traditionally used to assess humans, are now being applied to Large Language Models (LLMs) to evaluate their behavioral traits. However, existing studies follow…
Strategy Adaptation in Large Language Model Werewolf Agents
Fuya Nakamori, Yin Jou Huang, Fei Cheng
This study proposes a method to improve the performance of Werewolf agents by switching between predefined strategies based on the attitudes of other players and the context of con…
A System for Worldwide COVID-19 Information Aggregation
Akiko Aizawa, Frederic Bergeron, Junjie Chen +26
The global pandemic of COVID-19 has made the public pay close attention to related news, covering various domains, such as sanitation, treatment, and effects on education. Meanwhil…
Dynamically Updating Event Representations for Temporal Relation Classification with Multi-category Learning
Fei Cheng, Masayuki Asahara, Ichiro Kobayashi +1
Temporal relation classification is a pair-wise task for identifying the relation of a temporal link (TLINK) between two mentions, i.e. event, time, and document creation time (DCT…
SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language Models
Zhen Wan, Chao-Han Huck Yang, Yahan Yu +8
We introduce Speech-based Intelligence Quotient (SIQ) as a new form of human cognition-inspired evaluation pipeline for voice understanding large language models, LLM Voice, design…
Investigating Cost-Efficiency of LLM-Generated Training Data for Conversational Semantic Frame Analysis
Shiho Matta, Yin Jou Huang, Fei Cheng +2
Recent studies have demonstrated that few-shot learning allows LLMs to generate training data for supervised models at a low cost. However, the quality of LLM-generated data may no…
AcTED: Automatic Acquisition of Typical Event Duration for Semi-supervised Temporal Commonsense QA
Felix Virgo, Fei Cheng, Lis Kanashiro Pereira +3
We propose a voting-driven semi-supervised approach to automatically acquire the typical duration of an event and use it as pseudo-labeled data. The human evaluation demonstrates t…
EmplifAI: a Fine-grained Dataset for Japanese Empathetic Medical Dialogues in 28 Emotion Labels
Wan Jou She, Lis Kanashiro Pereira, Fei Cheng +3
This paper introduces EmplifAI, a Japanese empathetic dialogue dataset designed to support patients coping with chronic medical conditions. They often experience a wide range of po…
CylindTrack: Depth-Aware Cylindrical Motion Modeling for Panoramic Multi-Object Tracking
Buyin Deng, Kai Luo, Lingxin Huang +5
Multi-Object Tracking (MOT) is a core capability for embodied perception, and panoramic cameras are attractive for embodied systems because their 360° field of view reduces blind…
Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problems
Yibin Shen, Qianying Liu, Zhuoyuan Mao +3
To solve Math Word Problems, human students leverage diverse reasoning logic that reaches different possible equation solutions. However, the mainstream sequence-to-sequence approa…
Evolving Cache Schedules for Fast Diffusion Policy Inference
Siying Wang, Kangye Ji, Di Wang +1
Diffusion policies achieve strong visuomotor control by iteratively denoising action chunks, but repeated denoising makes real-time deployment computationally demanding. Cache-base…
OCHADAI-KYOTO at SemEval-2021 Task 1: Enhancing Model Generalization and Robustness for Lexical Complexity Prediction
Yuki Taya, Lis Kanashiro Pereira, Fei Cheng +1
We propose an ensemble model for predicting the lexical complexity of words and multiword expressions (MWEs). The model receives as input a sentence with a target word or MWEand ou…
Textual Enhanced Contrastive Learning for Solving Math Word Problems
Yibin Shen, Qianying Liu, Zhuoyuan Mao +2
Solving math word problems is the task that analyses the relation of quantities and requires an accurate understanding of contextual natural language information. Recent studies sh…
LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs
LLM-jp, :, Akiko Aizawa +80
This paper introduces LLM-jp, a cross-organizational project for the research and development of Japanese large language models (LLMs). LLM-jp aims to develop open-source and stron…
Predicting Event Time by Classifying Sub-Level Temporal Relations Induced from a Unified Representation of Time Anchors
Fei Cheng, Yusuke Miyao
Extracting event time from news articles is a challenging but attractive task. In contrast to the most existing pair-wised temporal link annotation, Reimers et al.(2016) proposed t…
Pre-training via Leveraging Assisting Languages and Data Selection for Neural Machine Translation
Haiyue Song, Raj Dabre, Zhuoyuan Mao +3
Sequence-to-sequence (S2S) pre-training using large monolingual data is known to improve performance for various S2S NLP tasks in low-resource settings. However, large monolingual…
Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial Reasoning
Chuang Ma, Qianying Liu, Tomoyuki Obuchi +6
Multimodal large language models (MLLMs) remain unreliable on spatial multiple-choice questions, and their failures are often attributed to poorly attended visual information. In t…
BenchTrace: A Benchmark for Testing Reflection Ability and Controlled Evolution in LLM Agents
Jiahao Huang, Fei Cheng, Junfeng Jiang +2
Self-evolving agents improve over time by reflecting on past failures, but existing evaluation is limited in two ways: it measures only task scores, leaving reflection quality unkn…
Rescue Implicit and Long-tail Cases: Nearest Neighbor Relation Extraction
Zhen Wan, Qianying Liu, Zhuoyuan Mao +3
Relation extraction (RE) has achieved remarkable progress with the help of pre-trained language models. However, existing RE models are usually incapable of handling two situations…
HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation
Yuxin Wen, Qing Shuai, Di Kang +34
We present HY-Motion 1.0, a series of state-of-the-art, large-scale, motion generation models capable of generating 3D human motions from textual descriptions. HY-Motion 1.0 repres…
GPT-RE: In-context Learning for Relation Extraction using Large Language Models
Zhen Wan, Fei Cheng, Zhuoyuan Mao +4
In spite of the potential for ground-breaking achievements offered by large language models (LLMs) (e.g., GPT-3), they still lag significantly behind fully-supervised baselines (e.…
Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction
Ranran Haoran Zhang, Qianying Liu, Aysa Xuemo Fan +5
Joint entity and relation extraction aims to extract relation triplets from plain text directly. Prior work leverages Sequence-to-Sequence (Seq2Seq) models for triplet sequence gen…
Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?
Chengzhi Zhong, Fei Cheng, Qianying Liu +5
In this study, we investigate whether non-English-centric LLMs, despite their strong performance, `think' in their respective dominant language: more precisely, `think' refers to h…
Tailoring Semiconductor Lateral Multi-junctions for Giant Photoconductivity Enhancement
Yutsung Tsai, Zhaodong Chu, Yimo Han +9
Semiconductor heterostructures have played a critical role as the enabler for new science and technology. The emergence of transition metal dichalcogenides (TMDs) as atomically thi…
Reformulating Domain Adaptation of Large Language Models as Adapt-Retrieve-Revise: A Case Study on Chinese Legal Domain
Zhen wan, Yating Zhang, Yexiang Wang +2
While large language models (LLMs) like GPT-4 have recently demonstrated astonishing zero-shot capabilities in general domain tasks, they often generate content with hallucinations…
Assessing Agentic Large Language Models in Multilingual National Bias
Qianying Liu, Katrina Qiyao Wang, Fei Cheng +1
Large Language Models have garnered significant attention for their capabilities in multilingual natural language processing, while studies on risks associated with cross biases ar…
Epitaxial Growth of Two-dimensional Insulator Monolayer Honeycomb BeO
Hui Zhang, Madisen Holbrook, Fei Cheng +7
The emergence of two-dimensional (2D) materials launched a fascinating frontier of flatland electronics. Most crystalline atomic layer materials are based on layered van der Waals…
Random Occlusion-recovery for Person Re-identification
Di Wu, Kun Zhang, Fei Cheng +4
As a basic task of multi-camera surveillance system, person re-identification aims to re-identify a query pedestrian observed from non-overlapping multiple cameras or across differ…
Adversarial Training for Commonsense Inference
Lis Pereira, Xiaodong Liu, Fei Cheng +2
We propose an AdversariaL training algorithm for commonsense InferenCE (ALICE). We apply small perturbations to word embeddings and minimize the resultant adversarial risk to regul…
Causal Tree Extraction from Medical Case Reports: A Novel Task for Experts-like Text Comprehension
Sakiko Yahata, Zhen Wan, Fei Cheng +3
Extracting causal relationships from a medical case report is essential for comprehending the case, particularly its diagnostic process. Since the diagnostic process is regarded as…
Generalized W-Net: Arbitrary-style Chinese Character Synthesization
Haochuan Jiang, Guanyu Yang, Fei Cheng +1
Synthesizing Chinese characters with consistent style using few stylized examples is challenging. Existing models struggle to generate arbitrary style characters with limited examp…
All-dielectric hybrid VIS-NIR dual-function metasurface
Pei Xiong, Daniel K. Nikolov, Fei Cheng +2
Metasurfaces are a promising technology that can serve as a compact alternative to conventional optics while providing multiple functions depending on the properties of the inciden…
JaMIE: A Pipeline Japanese Medical Information Extraction System
Fei Cheng, Shuntaro Yada, Ribeka Tanaka +2
We present an open-access natural language processing toolkit for Japanese medical information extraction. We first propose a novel relation annotation schema for investigating the…
A Hybrid Bandit Framework for Diversified Recommendation
Qinxu Ding, Yong Liu, Chunyan Miao +2
The interactive recommender systems involve users in the recommendation procedure by receiving timely user feedback to update the recommendation policy. Therefore, they are widely…