2 citations · 2 across the 10 of their papers we have counts for
12 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…
New result on Lane-Emden conjecture with exponents in a disk
Haoyang Lu, Zhitao Zhang
We obtain new results on Lane-Emden conjecture to prove a Liouville theorem for the Lane-Emden system $$\begin{cases} -Δu=v^p,& x\in \mathbb{R}^N,\\ -Δv=u^q,& x\in \mathbb{R}^N,\en…
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…
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…
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…
Unpacking the Implicit Norm Dynamics of Sharpness-Aware Minimization in Tensorized Models
Tianxiao Cao, Kyohei Atarashi, Hisashi Kashima
Sharpness-Aware Minimization (SAM) has been proven to be an effective optimization technique for improving generalization in overparameterized models. While prior works have explor…
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…
Probability Bounding: Post-Hoc Calibration via Box-Constrained Softmax
Kyohei Atarashi, Satoshi Oyama, Hiromi Arai +1
Many studies have observed that modern neural networks achieve high accuracy while producing poorly calibrated probabilities, making calibration a critical practical issue. In this…
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…
Factorization Machines with Regularization for Sparse Feature Interactions
Kyohei Atarashi, Satoshi Oyama, Masahito Kurihara
Factorization machines (FMs) are machine learning predictive models based on second-order feature interactions and FMs with sparse regularization are called sparse FMs. Such regula…