Image de couverture de livre

Mind the Gap: Evaluating Model- and Agentic-Level Vulnerabilities in LLMs with Action Graphs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wicaksono, Ilham, Wu, Zekun, Patel, Rahul, King, Theo, Koshiyama, Adriano, Treleaven, Philip
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Mind the Gap: Comparing Model- vs Agentic-Level Red Teaming with Action-Graph Observability on GPT-OSS-20B
par: Wicaksono, Ilham, et autres
Publié: (2025)

HEARTS: A Holistic Framework for Explainable, Sustainable and Robust Text Stereotype Detection
par: King, Theo, et autres
Publié: (2024)

Personality as a Probe for LLM Evaluation: Method Trade-offs and Downstream Effects
par: Handa, Gunmay, et autres
Publié: (2025)

Knowledge Collapse in LLMs: When Fluency Survives but Facts Fail under Recursive Synthetic Training
par: Keisha, Figarri, et autres
Publié: (2025)

THaMES: An End-to-End Tool for Hallucination Mitigation and Evaluation in Large Language Models
par: Liang, Mengfei, et autres
Publié: (2024)

From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs
par: Jain, Navya, et autres
Publié: (2024)

Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features
par: Cho, Seonglae, et autres
Publié: (2026)

Stereotype Detection in LLMs: A Multiclass, Explainable, and Benchmark-Driven Approach
par: Wu, Zekun, et autres
Publié: (2024)

LibVulnWatch: A Deep Assessment Agent System and Leaderboard for Uncovering Hidden Vulnerabilities in Open-Source AI Libraries
par: Wu, Zekun, et autres
Publié: (2025)

Eliciting Personality Traits in Large Language Models
par: Hilliard, Airlie, et autres
Publié: (2024)

CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features
par: Cho, Seonglae, et autres
Publié: (2025)

The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models
par: Cho, Seonglae, et autres
Publié: (2026)

Assessing Bias in Metric Models for LLM Open-Ended Generation Bias Benchmarks
par: Demchak, Nathaniel, et autres
Publié: (2024)

MPF: Aligning and Debiasing Language Models post Deployment via Multi Perspective Fusion
par: Guan, Xin, et autres
Publié: (2025)

Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?
par: Shen, Hua, et autres
Publié: (2025)

Tool Calling is Linearly Readable and Steerable in Language Models
par: Wu, Zekun, et autres
Publié: (2026)

BERT vs GPT for financial engineering
par: Sharkey, Edward, et autres
Publié: (2024)

Agentic Medical Knowledge Graphs Enhance Medical Question Answering: Bridging the Gap Between LLMs and Evolving Medical Knowledge
par: Rezaei, Mohammad Reza, et autres
Publié: (2025)

JobFair: A Framework for Benchmarking Gender Hiring Bias in Large Language Models
par: Wang, Ze, et autres
Publié: (2024)

Cultural Alignment in Large Language Models Using Soft Prompt Tuning
par: Masoud, Reem I., et autres
Publié: (2025)

Bridging the Knowledge-Action Gap by Evaluating LLMs in Dynamic Dental Clinical Scenarios
par: Ma, Hongyang, et autres
Publié: (2026)

HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications
par: Kalra, Rishi, et autres
Publié: (2024)

Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs
par: Pathade, Chetan
Publié: (2025)

Agentic LLMs for Question Answering over Tabular Data
par: Tyagi, Rishit, et autres
Publié: (2025)

Mind the (Belief) Gap: Group Identity in the World of LLMs
par: Borah, Angana, et autres
Publié: (2025)

SAGED: A Holistic Bias-Benchmarking Pipeline for Language Models with Customisable Fairness Calibration
par: Guan, Xin, et autres
Publié: (2024)

Mind the Language Gap: Automated and Augmented Evaluation of Bias in LLMs for High- and Low-Resource Languages
par: Buscemi, Alessio, et autres
Publié: (2025)

Preserving Fairness and Safety in Quantized LLMs Through Critical Weight Protection
par: Hakim, Muhammad Alif Al, et autres
Publié: (2026)

Mind the Gap! Static and Interactive Evaluations of Large Audio Models
par: Li, Minzhi, et autres
Publié: (2025)

Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs
par: Sanz-Guerrero, Mario, et autres
Publié: (2025)

Mind the Style Gap: Meta-Evaluation of Style and Attribute Transfer Metrics
par: Pauli, Amalie Brogaard, et autres
Publié: (2025)

Mind the Gap Between Spatial Reasoning and Acting! Step-by-Step Evaluation of Agents With Spatial-Gym
par: Kaesberg, Lars Benedikt, et autres
Publié: (2026)

Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions
par: Masoud, Reem I., et autres
Publié: (2023)

Mind the Gap... or Not? How Translation Errors and Evaluation Details Skew Multilingual Results
par: Peter, Jan-Thorsten, et autres
Publié: (2025)

IndoSafety: Culturally Grounded Safety for LLMs in Indonesian Languages
par: Azmi, Muhammad Falensi, et autres
Publié: (2025)

GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs
par: Feng, Tao, et autres
Publié: (2026)

MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair
par: Liu, Simiao, et autres
Publié: (2026)

Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM
par: Xiong, Zhen, et autres
Publié: (2025)

Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge
par: Gou, Boyu, et autres
Publié: (2025)

Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs
par: Zhu, Wenhui, et autres
Publié: (2026)