papers

Publications (70)

cs.AI2024

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…

cs.CV2025

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…

cs.LG2025

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…

cs.CL2026

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…

cs.CL2024

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…

eess.AS2023

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…

cs.CL2026

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…

cs.CL2025

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…

cs.CY2025

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…

cs.CL2023

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…

cs.CL2023

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…

cs.CL2026

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…

cs.CV2026

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…

cs.CL2023

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…

cs.CY2025

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.…

cs.CL2026

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…

cs.CL2021

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…

cs.CL2026

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…

cs.CL2021

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…

cs.CL2023

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…

cs.CV2021

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…

cs.CV2026

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…

cs.CL2026

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…

cs.CY2025

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…

cond-mat.mtrl-sci2018

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…

cs.CL2023

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…

cs.AI2026

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…

cs.CL2026

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…

cs.LG2026

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…

cs.CL2026

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…

cond-mat.mes-hall2026

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…

cs.CL2026

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…

cs.CL2026

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…

cs.CL2026

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…

cs.CV2025

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…

cs.CV2026

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…

cs.CL2025

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…

cs.CL2025

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…

cs.CL2020

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…

cs.CL2023

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…

cs.CL2025

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…

cs.CL2024

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…

cs.CL2024

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…

cs.CL2026

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…

cs.CV2026

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…

cs.CL2022

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…

cs.CV2026

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…

cs.CL2021

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…

cs.CL2022

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…

cs.CL2024

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…

cs.CL2020

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…

cs.CL2020

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…

cs.CL2026

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…

cs.AI2026

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…

cs.CL2023

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…

cs.CV2025

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…

cs.CL2023

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.…

cs.CL2020

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…

cs.CL2024

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…

cond-mat.mtrl-sci2017

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…

cs.CL2024

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…

cs.CL2025

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…

cond-mat.mes-hall2020

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…

cs.CV2019

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…

cs.CL2020

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…

cs.CL2025

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…

cs.CV2024

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…

physics.optics2023

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…

cs.CL2021

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…

cs.IR2020

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…