Copertina

ObjexMT: Objective Extraction and Metacognitive Calibration for LLM-as-a-Judge under Multi-Turn Jailbreaks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kim, Hyunjun, Ha, Junwoo, Yu, Sangyoon, Park, Haon
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

X-Teaming Evolutionary M2S: Automated Discovery of Multi-turn to Single-turn Jailbreak Templates
di: Kim, Hyunjun, et al.
Pubblicazione: (2025)

M2S: Multi-turn to Single-turn jailbreak in Red Teaming for LLMs
di: Ha, Junwoo, et al.
Pubblicazione: (2025)

sudo rm -rf agentic_security
di: Lee, Sejin, et al.
Pubblicazione: (2025)

Entropic Context Shaping: Information-Theoretic Filtering for Context-Aware LLM Agents
di: Kim, Hyunjun
Pubblicazione: (2026)

ELITE: Enhanced Language-Image Toxicity Evaluation for Safety
di: Lee, Wonjun, et al.
Pubblicazione: (2025)

RankJudge: A Multi-Turn LLM-as-a-Judge Synthetic Benchmark Generator
di: Tang, Zhenwei, et al.
Pubblicazione: (2026)

Defensive M2S: Training Guardrail Models on Compressed Multi-turn Conversations
di: Kim, Hyunjun
Pubblicazione: (2026)

Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple LLM Judges
di: Tang, Yuqi, et al.
Pubblicazione: (2025)

LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet
di: Li, Nathaniel, et al.
Pubblicazione: (2024)

Attention-Aware GNN-based Input Defense against Multi-Turn LLM Jailbreak
di: Huang, Zixuan, et al.
Pubblicazione: (2025)

Many-Turn Jailbreaking
di: Yang, Xianjun, et al.
Pubblicazione: (2025)

MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation
di: Singh, Jyotika, et al.
Pubblicazione: (2026)

SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
di: Feng, Mingqian, et al.
Pubblicazione: (2026)

Eliciting and Analyzing Emergent Misalignment in State-of-the-Art Large Language Models
di: Panpatil, Siddhant, et al.
Pubblicazione: (2025)

Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection
di: Wei, Zhipeng, et al.
Pubblicazione: (2024)

AdvPrefix: An Objective for Nuanced LLM Jailbreaks
di: Zhu, Sicheng, et al.
Pubblicazione: (2024)

MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models
di: Kwan, Wai-Chung, et al.
Pubblicazione: (2024)

KnowMT-Bench: Benchmarking Knowledge-Intensive Long-Form Question Answering in Multi-Turn Dialogues
di: Chen, Junhao, et al.
Pubblicazione: (2025)

AIDG: A Formal Decomposition of Information Extraction and Containment Asymmetries in Multi-Turn LLM Dialogue
di: Sakhawat, Adib, et al.
Pubblicazione: (2026)

DrawingBench: Evaluating Spatial Reasoning and UI Interaction Capabilities of Large Language Models through Mouse-Based Drawing Tasks
di: Kim, Hyunjun, et al.
Pubblicazione: (2025)

A Finite-Calibration Regime Map for LLM Judge Panels
di: Zhu, Bin, et al.
Pubblicazione: (2026)

PARL-MT: Learning to Call Functions in Multi-Turn Conversation with Progress Awareness
di: Chai, Huacan, et al.
Pubblicazione: (2025)

MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games
di: Eisenstein, Jacob, et al.
Pubblicazione: (2026)

Emerging Vulnerabilities in Frontier Models: Multi-Turn Jailbreak Attacks
di: Gibbs, Tom, et al.
Pubblicazione: (2024)

Are LLM-Judges Robust to Expressions of Uncertainty? Investigating the effect of Epistemic Markers on LLM-based Evaluation
di: Lee, Dongryeol, et al.
Pubblicazione: (2024)

FairJudge: An Adaptive, Debiased, and Consistent LLM-as-a-Judge
di: Yang, Bo, et al.
Pubblicazione: (2026)

THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models
di: Ma, Zhiqing, et al.
Pubblicazione: (2026)

HELEA: Hard-Negative Benchmark and LLM-based Reranking for Robust Entity Alignment
di: Jang, Yoonjin, et al.
Pubblicazione: (2026)

Adaptive Stopping for Multi-Turn LLM Reasoning
di: Zhou, Xiaofan, et al.
Pubblicazione: (2026)

MacroBench: A Novel Testbed for Web Automation Scripts via Large Language Models
di: Kim, Hyunjun, et al.
Pubblicazione: (2025)

ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction
di: Zeng, Xingshan, et al.
Pubblicazione: (2025)

Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles
di: Sun, Xiongtao, et al.
Pubblicazione: (2024)

Efficient LLM-Jailbreaking via Multimodal-LLM Jailbreak
di: Ji, Haoxuan, et al.
Pubblicazione: (2024)

Calibrate, Don't Curate: Label-Efficient Estimation from Noisy LLM Judges
di: Li, Yanran
Pubblicazione: (2026)

ClarifyMT-Bench: Benchmarking and Improving Multi-Turn Clarification for Conversational Large Language Models
di: Luo, Sichun, et al.
Pubblicazione: (2025)

TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning
di: Kong, Yaxuan, et al.
Pubblicazione: (2026)

Counterfactual Graph for Multi-Agent LLM Calibration
di: Huang, Jiatan, et al.
Pubblicazione: (2026)

Jailbreaking on Text-to-Video Models via Scene Splitting Strategy
di: Lee, Wonjun, et al.
Pubblicazione: (2025)

Not the Example, but the Process: How Self-Generated Examples Enhance LLM Reasoning
di: Gwak, Daehoon, et al.
Pubblicazione: (2026)

A Comprehensive Evaluation of LLM Unlearning Robustness under Multi-Turn Interaction
di: Pan, Ruihao, et al.
Pubblicazione: (2026)