1 citations · 1 across the 15 of their papers we have counts for
18 papers
NLData2Opt: Benchmarking Parameter Derivation and Prediction for Modeling Optimization Problems from Natural Language and Data
Lijia Liu, Kyohei Atarashi, Jiyi Li +3
Formulating optimization problems from raw inputs of problem descriptions and data is time-consuming and costly. While Large Language Models (LLMs) offer a promising way to automat…
Disentangling Steering Vectors
Takeru Hiramatsu, Kyohei Atarashi, Koh Takeuchi +1
Activation steering has emerged as a lightweight, inference-time approach to control the behavior of Large Language Models (LLMs). However, traditional steering vectors used to int…
Estimating Learners' Skill Acquisition Without Temporal Information
Ryosuke Nagai, Kyohei Atarashi, Koh Takeuchi +2
Recent research in educational data mining, especially knowledge tracing, has focused on predicting learners' future knowledge states to support adaptive instruction. However, in m…
Long-Term Outlier Prediction Through Outlier Score Modeling
Yuma Aoki, Joon Park, Koh Takeuchi +6
This study addresses an important gap in time series outlier detection by proposing a novel problem setting: long-term outlier prediction. Conventional methods primarily focus on i…
Evaluating Cross-Modal Reasoning Ability and Problem Characteristics with Multimodal Item Response Theory
Shunki Uebayashi, Kento Masui, Kyohei Atarashi +5
Multimodal Large Language Models (MLLMs) have recently emerged as general architectures capable of reasoning over diverse modalities. Benchmarks for MLLMs should measure their abil…
Adaptive Quality-Diversity Trade-offs for Large-Scale Batch Recommendation
Clémence Réda, Tomas Rigaux, Hiba Bederina +3
A core research question in recommender systems is to propose batches of highly relevant and diverse items, that is, items personalized to the user's preferences, but which also mi…
Robust Anomaly Detection Under Normality Distribution Shift in Dynamic Graphs
Xiaoyang Xu, Xiaofeng Lin, Koh Takeuchi +2
Anomaly detection in dynamic graphs is a critical task with broad real-world applications, including social networks, e-commerce, and cybersecurity. Most existing methods assume th…
Counterfactual Evaluation for Blind Attack Detection in LLM-based Evaluation Systems
Lijia Liu, Takumi Kondo, Kyohei Atarashi +4
This paper investigates defenses for LLM-based evaluation systems against prompt injection. We formalize a class of threats called blind attacks, where a candidate answer is crafte…
Dynamic Feature Selection from Variable Feature Sets Using Features of Features
Katsumi Takahashi, Koh Takeuchi, Hisashi Kashima
Machine learning models usually assume that a set of feature values used to obtain an output is fixed in advance. However, in many real-world problems, a cost is associated with me…
Exploring Causes and Mitigation of Hallucinations in Large Vision Language Models
Yaqi Sun, Kyohei Atarashi, Koh Takeuchi +1
Large Vision-Language Models (LVLMs) integrate image encoders with Large Language Models (LLMs) to process multi-modal inputs and perform complex visual tasks. However, they often…
Emulating Retrieval Augmented Generation via Prompt Engineering for Enhanced Long Context Comprehension in LLMs
Joon Park, Kyohei Atarashi, Koh Takeuchi +1
This paper addresses the challenge of comprehending very long contexts in Large Language Models (LLMs) by proposing a method that emulates Retrieval Augmented Generation (RAG) thro…
Neural Double Auction Mechanism
Tsuyoshi Suehara, Koh Takeuchi, Hisashi Kashima +3
Mechanism design, a branch of economics, aims to design rules that can autonomously achieve desired outcomes in resource allocation and public decision making. The research on mech…
Cognitive Biases in Large Language Models: A Survey and Mitigation Experiments
Yasuaki Sumita, Koh Takeuchi, Hisashi Kashima
Large Language Models (LLMs) are trained on large corpora written by humans and demonstrate high performance on various tasks. However, as humans are susceptible to cognitive biase…
AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses
Xiaotian Lu, Jiyi Li, Koh Takeuchi +1
Question answering (QA) tasks have been extensively studied in the field of natural language processing (NLP). Answers to open-ended questions are highly diverse and difficult to q…
Learning Neural Strategy-Proof Matching Mechanism from Examples
Ryota Maruo, Koh Takeuchi, Hisashi Kashima
Designing two-sided matching mechanisms is challenging when practical demands for matching outcomes are difficult to formalize and the designed mechanism must satisfy theoretical c…
Learning Fair and Preferable Allocations through Neural Network
Ryota Maruo, Koh Takeuchi, Hisashi Kashima
The fair allocation of indivisible resources is a fundamental problem. Existing research has developed various allocation mechanisms or algorithms to satisfy different fairness not…
Evaluating Saliency Explanations in NLP by Crowdsourcing
Xiaotian Lu, Jiyi Li, Zhen Wan +3
Deep learning models have performed well on many NLP tasks. However, their internal mechanisms are typically difficult for humans to understand. The development of methods to expla…
Estimating Treatment Effects Under Heterogeneous Interference
Xiaofeng Lin, Guoxi Zhang, Xiaotian Lu +3
Treatment effect estimation can assist in effective decision-making in e-commerce, medicine, and education. One popular application of this estimation lies in the prediction of the…