Daily Arxiv

전 세계에서 발간되는 인공지능 관련 논문을 정리하는 페이지 입니다.
본 페이지는 Google Gemini를 활용해 요약 정리하며, 비영리로 운영 됩니다.
논문에 대한 저작권은 저자 및 해당 기관에 있으며, 공유 시 출처만 명기하면 됩니다.

AI/ML in 3GPP 5G Advanced -- Services and Architecture

CookAnything: A Framework for Flexible and Consistent Multi-Step Recipe Image Generation

Dynamic Correction of Erroneous State Estimates via Diffusion Bayesian Exploration

Concept-Guided Backdoor Attack on Vision Language Models

On the Holographic Geometry of Deterministic Computation

Decoding inner speech with an end-to-end brain-to-text neural interface

Physics-informed Neural Operator Learning for Nonlinear Grad-Shafranov Equation

MindEval: Benchmarking Language Models on Multi-turn Mental Health Support

LAET: A Layer-wise Adaptive Ensemble Tuning Framework for Pretrained Language Models

FAST-CAD: A Fairness-Aware Framework for Non-Contact Stroke Diagnosis

Designing LLM-based Multi-Agent Systems for Software Engineering Tasks: Quality Attributes, Design Patterns and Rationale

SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control

MOSS: Efficient and Accurate FP8 LLM Training with Microscaling and Automatic Scaling

Data-Augmented Deep Learning for Downhole Depth Sensing and Field Validation

Chinese Discharge Drug Recommendation in Metabolic Diseases with Large Language Models

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability

Orders in Chaos: Enhancing Large-Scale MoE LLM Serving with Data Movement Forecasting

Reinforce-Ada: An Adaptive Sampling Framework under Non-linear RL Objectives

TempoControl: Temporal Attention Guidance for Text-to-Video Models

AortaDiff: A Unified Multitask Diffusion Framework For Contrast-Free AAA Imaging

SoREX: Towards Self-Explainable Social Recommendation with Relevant Ego-Path Extraction

The AI Productivity Index (APEX)

Uncovering Grounding IDs: How External Cues Shape Multimodal Binding

Pushing Toward the Simplex Vertices: A Simple Remedy for Code Collapse in Smoothed Vector Quantization

V-CECE: Visual Counterfactual Explanations via Conceptual Edits

Momentum-constrained Hybrid Heuristic Trajectory Optimization Framework with Residual-enhanced DRL for Visually Impaired Scenarios

HARP: Hallucination Detection via Reasoning Subspace Projection

Rethinking Sparse Autoencoders: Select-and-Project for Fairness and Control from Encoder Features Alone

IPA: An Information-Reconstructive Input Projection Framework for Efficient Foundation Model Adaptation

Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders

ORFuzz: Fuzzing the "Other Side" of LLM Safety -- Testing Over-Refusal

Retro-Expert: Collaborative Reasoning for Interpretable Retrosynthesis

A Survey on Diffusion Language Models

CodeNER: Code Prompting for Named Entity Recognition

ReSem3D: Refinable 3D Spatial Constraints via Fine-Grained Semantic Grounding for Generalizable Robotic Manipulation

VERIRAG: A Post-Retrieval Auditing of Scientific Study Summaries

SustainDiffusion: Optimising the Social and Environmental Sustainability of Stable Diffusion Models

LittleBit: Ultra Low-Bit Quantization via Latent Factorization

Real-Time Execution of Action Chunking Flow Policies

AURA: A Diagnostic Framework for Tracking User Satisfaction of Interactive Planning Agents

Enhancing SPARQL Query Rewriting for Complex Ontology Alignments

Exploring Ordinal Bias in Action Recognition for Instructional Videos

Robust Weight Imprinting: Insights from Neural Collapse and Proxy-Based Aggregation

Experiments with Large Language Models on Retrieval-Augmented Generation for Closed-Source Simulation Software

SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models

Large Language Models: An Applied Econometric Framework

Edge-Only Universal Adversarial Attacks in Distributed Learning

Image-Guided Semantic Pseudo-LiDAR Point Generation for 3D Object Detection

Detecting the Future: All-at-Once Event Sequence Forecasting with Horizon Matching

Variational Learning of Gaussian Process Latent Variable Models through Stochastic Gradient Annealed Importance Sampling

SOAP: Enhancing Spatio-Temporal Relation and Motion Information Capturing for Few-Shot Action Recognition

A Scene-aware Models Adaptation Scheme for Cross-scene Online Inference on Mobile Devices

Towards Data-efficient Customer Intent Recognition with Prompt-based Learning Paradigm

GTM: Simulating the World of Tools for AI Agents

Self-Transparency Failures in Expert-Persona LLMs: How Instruction-Following Overrides Honesty

Learning the Value of Value Learning

OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe

ToolMind Technical Report: A Large-Scale, Reasoning-Enhanced Tool-Use Dataset

Debate over Mixed-knowledge: A Robust Multi-Agent Reasoning Framework for Incomplete Knowledge Graph Question Answering

Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives

Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models

Generalized Parallel Scaling with Interdependent Generations

SOCK: A Benchmark for Measuring Self-Replication in Large Language Models

KNARsack: Teaching Neural Algorithmic Reasoners to Solve Pseudo-Polynomial Problems

IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks

FedIFL: A federated cross-domain diagnostic framework for motor-driven systems with inconsistent fault modes

Enhancing Large Language Models through Neuro-Symbolic Integration and Ontological Reasoning

Rolling in the deep of cognitive and AI biases

Enhancing Retrieval-Augmented Generation with Entity Linking for Educational Platforms

Training-Time Action Conditioning for Efficient Real-Time Chunking

Whatever Remains Must Be True: Filtering Drives Reasoning in LLMs, Shaping Diversity

AQUA-Net: Adaptive Frequency Fusion and Illumination Aware Network for Underwater Image Enhancement

M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG

MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution

Trusted AI Agents in the Cloud

Impugan: Learning Conditional Generative Models for Robust Data Imputation

Zoom in, Click out: Unlocking and Evaluating the Potential of Zooming for GUI Grounding

Measuring the Effect of Background on Classification and Feature Importance in Deep Learning for AV Perception

World Models That Know When They Don't Know: Controllable Video Generation with Calibrated Uncertainty

Natural Language Summarization Enables Multi-Repository Bug Localization by LLMs in Microservice Architectures

Neural Coherence : Find higher performance to out-of-distribution tasks from few samples

Sparse Attention Post-Training for Mechanistic Interpretability

Optimizing Medical Question-Answering Systems: A Comparative Study of Fine-Tuned and Zero-Shot Large Language Models with RAG Framework

NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generation

Phase-OTDR Event Detection Using Image-Based Data Transformation and Deep Learning

Approximation of Box Decomposition Algorithm for Fast Hypervolume-Based Multi-Objective Optimization

Probing the effectiveness of World Models for Spatial Reasoning through Test-time Scaling

3D Path Planning for Robot-assisted Vertebroplasty from Arbitrary Bi-plane X-ray via Differentiable Rendering

Mechanistic Interpretability of Antibody Language Models Using SAEs

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding

Efficient Text Classification with Conformal In-Context Learning

Big Tech-Funded AI Papers Have Higher Citation Impact, Greater Insularity, and Larger Recency Bias

Bayesian Active Inference for Intelligent UAV Anti-Jamming and Adaptive Trajectory Planning

Faithfulness metric fusion: Improving the evaluation of LLM trustworthiness across domains

Retrieving Semantically Similar Decisions under Noisy Institutional Labels: Robust Comparison of Embedding Methods

InverseCrafter: Efficient Video ReCapture as a Latent Domain Inverse Problem

Feasibility of AI-Assisted Programming for End-User Development

Grounded Multilingual Medical Reasoning for Question Answering with Large Language Models

Modular Jets for Supervised Pipelines: Diagnosing Mirage vs Identifiability

A Comprehensive Framework for Automated Quality Control in the Automotive Industry

Cognitive bias in LLM reasoning compromises interpretation of clinical oncology notes

Created by

Haebom

Category

Empty

저자

Matthew W. Kenaston (Mayo Clinic College of Medicine and Science, Phoenix, AZ), Umair Ayub (Mayo Clinic College of Medicine and Science, Phoenix, AZ), Mihir Parmar (School of Computing and AI, Arizona State University, Tempe, AZ), Muhammad Umair Anjum (Mayo Clinic College of Medicine and Science, Phoenix, AZ), Syed Arsalan Ahmed Naqvi (Mayo Clinic College of Medicine and Science, Phoenix, AZ), Priya Kumar (Mayo Clinic College of Medicine and Science, Phoenix, AZ), Samarth Rawal (Mayo Clinic College of Medicine and Science, Phoenix, AZ), Aadel A. Chaudhuri (Department of Radiation Oncology, Mayo Clinic, Rochester, MN), Yousef Zakharia (Mayo Clinic Comprehensive Cancer Center, Phoenix, AZ), Elizabeth I. Heath (Department of Oncology, Mayo Clinic, Rochester, MN), Tanios S. Bekaii-Saab (Mayo Clinic Comprehensive Cancer Center, Phoenix, AZ), Cui Tao (Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester, MN), Eliezer M. Van Allen (Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA), Ben Zhou (School of Computing and AI, Arizona State University, Tempe, AZ), YooJung Choi (School of Computing and AI, Arizona State University, Tempe, AZ), Chitta Baral (School of Computing and AI, Arizona State University, Tempe, AZ), Irbaz Bin Riaz (Mayo Clinic College of Medicine and Science, Phoenix, AZ, Mayo Clinic Comprehensive Cancer Center, Phoenix, AZ, Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester, MN)

개요

본 연구는 임상 벤치마크에서 높은 성능을 보이는 대규모 언어 모델(LLM)이 잘못된 추론을 통해 정확한 결론에 도달할 수 있다는 문제점을 지적하며, 이는 종양학 의사 결정 지원에서 안전 문제로 이어질 수 있음을 강조한다. 이를 위해, 두 개의 코호트 후향적 연구를 통해 GPT-4의 Chain-of-Thought 응답에서 나타나는 추론 오류의 계층적 분류 체계를 개발하고 임상적 관련성을 검증했다. 유방암 및 췌장암 데이터를 활용하여 600개의 추론 과정을 분석, 계산 오류를 인지 편향 프레임워크에 매핑하는 3단계 분류 체계를 정의하고, 전이성 질환을 포함한 전립선암 상담 기록 822개의 응답을 통해 이를 검증했다. 연구 결과, 추론 오류는 해석의 23%에서 발생했으며, 확인 편향과 닻 내림 편향이 가장 흔하게 나타났다. 이러한 오류는 지침과 일치하지 않고 잠재적으로 해로운 권고로 이어졌으며, 특히 진행성 질환 관리에서 두드러졌다. 또한, 최첨단 언어 모델을 사용한 자동 평가자는 오류의 존재는 감지했지만, 하위 유형을 신뢰성 있게 분류하지 못했다.

시사점, 한계점

•

시사점:

◦

LLM은 유창하지만 임상적으로 안전하지 않은 권고를 할 수 있다.

◦

추론 오류는 정확도 기반 평가로 포착되지 않으며, 안전 문제로 이어진다.

◦

개발된 분류 체계는 임상 적용 전 추론 충실도를 평가하고 개선하기 위한 일반화 가능한 프레임워크를 제공한다.

◦

특히 진행성 질환 관리에서 추론 오류가 지침 불일치 및 잠재적 유해 권고로 이어진다.

•

한계점:

◦

자동 평가자는 오류 존재는 감지했지만, 오류 하위 유형을 신뢰성 있게 분류하지 못함.

◦

연구가 특정 암 유형 및 데이터셋에 국한되어 일반화에 한계가 있을 수 있음.

◦

LLM의 추론 오류를 완화하기 위한 구체적인 개선 방안 제시 부족.

Made with Slashpage