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.

Increasing intelligence in AI agents can worsen collective outcomes

On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents

A Robust and Efficient Multi-Agent Reinforcement Learning Framework for Traffic Signal Control

XSkill: Continual Learning from Experience and Skills in Multimodal Agents

Can RL Improve Generalization of LLM Agents? An Empirical Study

Few-for-Many Personalized Federated Learning

LABSHIELD: A Multimodal Benchmark for Safety-Critical Reasoning and Planning in Scientific Laboratories

Normative Common Ground Replication (NormCoRe): Replication-by-Translation for Studying Norms in Multi-agent AI

Learning Transferable Sensor Models via Language-Informed Pretraining

Prototype-Based Knowledge Guidance for Fine-Grained Structured Radiology Reporting

Fair Learning for Bias Mitigation and Quality Optimization in Paper Recommendation

AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization

Social, Legal, Ethical, Empathetic and Cultural Norm Operationalisation for AI Agents

CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges

Automated Detection of Malignant Lesions in the Ovary Using Deep Learning Models and XAI

VisiFold: Long-Term Traffic Forecasting via Temporal Folding Graph and Node Visibility

Automating Skill Acquisition through Large-Scale Mining of Open-Source Agentic Repositories: A Framework for Multi-Agent Procedural Knowledge Extraction

A Semi-Decentralized Approach to Multiagent Control

DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answering

From Debate to Deliberation: Structured Collective Reasoning with Typed Epistemic Acts

An Automatic Text Classification Method Based on Hierarchical Taxonomies, Neural Networks and Document Embedding: The NETHIC Tool

Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Framework

Understanding Wikidata Qualifiers: An Analysis and Taxonomy

Anomaly detection in time-series via inductive biases in the latent space of conditional normalizing flows

CINDI: Conditional Imputation and Noisy Data Integrity with Flows in Power Grid Data

Gender Bias in Generative AI-assisted Recruitment Processes

When OpenClaw Meets Hospital: Toward an Agentic Operating System for Dynamic Clinical Workflows

Scaling Laws for Educational AI Agents

STAIRS-Former: Spatio-Temporal Attention with Interleaved Recursive Structure Transformer for Offline Multi-task Multi-agent Reinforcement Learning

Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks

LLMs can construct powerful representations and streamline sample-efficient supervised learning

VisDoT : Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought

The Density of Cross-Persistence Diagrams and Its Applications

See, Symbolize, Act: Grounding VLMs with Spatial Representations for Better Gameplay

Leveraging Large Language Models and Survival Analysis for Early Prediction of Chemotherapy Outcomes

AI Knows What's Wrong But Cannot Fix It: Helicoid Dynamics in Frontier LLMs Under High-Stakes Decisions

Expert Threshold Routing for Autoregressive Language Modeling with Dynamic Computation Allocation and Load Balancing

Multi-Agent Collaboration for Automated Design Exploration on High Performance Computing Systems

Examining Users' Behavioural Intention to Use OpenClaw Through the Cognition--Affect--Conation Framework

Verified Multi-Agent Orchestration: A Plan-Execute-Verify-Replan Framework for Complex Query Resolution

GPT4o-Receipt: A Dataset and Human Study for AI-Generated Document Forensics

Adversarial Reinforcement Learning for Detecting False Data Injection Attacks in Vehicular Routing

Speak or Stay Silent: Context-Aware Turn-Taking in Multi-Party Dialogue

Entropy Guided Diversification and Preference Elicitation in Agentic Recommendation Systems

Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment

Detecting Intrinsic and Instrumental Self-Preservation in Autonomous Agents: The Unified Continuation-Interest Protocol

The Artificial Self: Characterising the landscape of AI identity

TimeSqueeze: Dynamic Patching for Efficient Time Series Forecasting

Improving LLM Performance Through Black-Box Online Tuning: A Case for Adding System Specs to Factsheets for Trusted AI

FinRule-Bench: A Benchmark for Joint Reasoning over Financial Tables and Principles

RewardHackingAgents: Benchmarking Evaluation Integrity for LLM ML-Engineering Agents

LLM-Augmented Digital Twin for Policy Evaluation in Short-Video Platforms

Counterweights and Complementarities: The Convergence of AI and Blockchain Powering a Decentralized Future

AI Psychometrics: Evaluating the Psychological Reasoning of Large Language Models with Psychometric Validities

COMPASS: The explainable agentic framework for Sovereignty, Sustainability, Compliance, and Ethics

The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning

Mind the Sim2Real Gap in User Simulation for Agentic Tasks

Reversible Lifelong Model Editing via Semantic Routing-Based LoRA

Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios

PACED: Distillation at the Frontier of Student Competence

A Survey of Reasoning in Autonomous Driving Systems: Open Challenges and Emerging Paradigms

DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use

ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Language Models

The Epistemic Support-Point Filter: Jaynesian Maximum Entropy Meets Popperian Falsification

Training Language Models via Neural Cellular Automata

Where Do Flow Semantics Reside? A Protocol-Native Tabular Pretraining Paradigm for Encrypted Traffic Classification

InFusionLayer: a CFA-based ensemble tool to generate new classifiers for learning and modeling

Revisiting Sharpness-Aware Minimization: A More Faithful and Effective Implementation

Toward Epistemic Stability: Engineering Consistent Procedures for Industrial LLM Hallucination Reduction

Gated Adaptation for Continual Learning in Human Activity Recognition

Safety Under Scaffolding: How Evaluation Conditions Shape Measured Safety

AMB-DSGDN: Adaptive Modality-Balanced Dynamic Semantic Graph Differential Network for Multimodal Emotion Recognition

Targeted Bit-Flip Attacks on LLM-Based Agents

Evaluating Progress in Graph Foundation Models: A Comprehensive Benchmark and New Insights

HTM-EAR: Importance-Preserving Tiered Memory with Hybrid Routing under Saturation

Architecture-Aware LLM Inference Optimization on AMD Instinct GPUs: A Comprehensive Benchmark and Deployment Study

The DMA Streaming Framework: Kernel-Level Buffer Orchestration for High-Performance AI Data Paths

How to Count AIs: Individuation and Liability for AI Agents

A Governance and Evaluation Framework for Deterministic, Rule-Based Clinical Decision Support in Empiric Antibiotic Prescribing

RedFuser: An Automatic Operator Fusion Framework for Cascaded Reductions on AI Accelerators

Defining AI Models and AI Systems: A Framework to Resolve the Boundary Problem

Prompts and Prayers: the Rise of GPTheology

DeliberationBench: A Normative Benchmark for the Influence of Large Language Models on Users' Views

Assessing Cognitive Biases in LLMs for Judicial Decision Support: Virtuous Victim and Halo Effects

Measuring and Eliminating Refusals in Military Large Language Models

FERRET: Framework for Expansion Reliant Red Teaming

Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment

GATech at AbjadMed: Bidirectional Encoders vs. Causal Decoders: Insights from 82-Class Arabic Medical Classification

SENS-ASR: Semantic Embedding injection in Neural-transducer for Streaming Automatic Speech Recognition

SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks

Leveraging Wikidata for Geographically Informed Sociocultural Bias Dataset Creation: Application to Latin America

A Retrieval-Augmented Language Assistant for Unmanned Aircraft Safety Assessment and Regulatory Compliance

Automated evaluation of LLMs for effective machine translation of Mandarin Chinese to English

Empathy Is Not What Changed: Clinical Assessment of Psychological Safety Across GPT Model Generations

There Are No Silly Questions: Evaluation of Offline LLM Capabilities from a Turkish Perspective

Context Over Compute Human-in-the-Loop Outperforms Iterative Chain-of-Thought Prompting in Interview Answer Quality

Evaluating Adjective-Noun Compositionality in LLMs: Functional vs Representational Perspectives

CEI: A Benchmark for Evaluating Pragmatic Reasoning in Language Models

TAMUSA-Chat: A Domain-Adapted Large Language Model Conversational System for Research and Responsible Deployment

PoultryLeX-Net: Domain-Adaptive Dual-Stream Transformer Architecture for Large-Scale Poultry Stakeholder Modeling

Consistency in Language Models: Current Landscape, Challenges, and Future Directions

Created by

Haebom

Category

Empty

저자

Jekaterina Novikova, Carol Anderson, Borhane Blili-Hamelin, Subhabrata Majumdar

개요

본 논문은 최첨단 언어 모델이 다양한 상황에서 일관성을 유지하는 데 어려움을 겪는다는 점을 지적하며, AI 언어 시스템에서의 일관성 연구 현황을 조사합니다. 논리적 규칙 준수를 포함하는 형식적 일관성과 도덕적 및 사실적 일관성과 같은 비형식적 일관성 모두를 탐구하며, 일관성 측정에 대한 현재 접근 방식을 분석하고, 정의 표준화, 다국어 평가 및 일관성 향상 방법론의 중요한 연구 격차를 파악합니다. 도메인 특정 작업에서 언어 모델의 적용에 있어 일관성을 보장하면서 유용성과 적응성을 유지하기 위해 강력한 벤치마크와 학제 간 접근 방식이 시급함을 강조합니다.

시사점, 한계점

•

시사점: AI 언어 모델의 일관성 문제를 체계적으로 분석하고, 향후 연구 방향을 제시함으로써 더욱 신뢰할 수 있고 안전한 언어 모델 개발에 기여할 수 있습니다. 일관성 측정을 위한 표준화된 벤치마크 개발의 필요성을 강조합니다.

•

한계점: 일관성의 정의 표준화, 다국어 평가 방법론 및 일관성 향상을 위한 구체적인 기술적 해결책 제시가 부족합니다. 단순히 문제점을 제기하는 수준에 그칠 수 있으며, 실제적인 해결책 제시에는 추가적인 연구가 필요합니다.

Made with Slashpage