:: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Authors:	Feldman, Shai, Romano, Yaniv
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	https://arxiv.org/abs/2605.06605
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Robust Conformal Prediction Using Privileged Information
by: Feldman, Shai, et al.
Published: (2024)

Conformal Prediction with Corrupted Labels: Uncertain Imputation and Robust Re-weighting
by: Feldman, Shai, et al.
Published: (2025)

Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs
by: Davidov, Hen, et al.
Published: (2025)

Valid Best-Model Identification for LLM Evaluation via Low-Rank Factorization
by: Tolochinsky, Elad, et al.
Published: (2026)

Label Noise Robustness of Conformal Prediction
by: Einbinder, Bat-Sheva, et al.
Published: (2022)

Automating Deception: Scalable Multi-Turn LLM Jailbreaks
by: Kumarappan, Adarsh, et al.
Published: (2025)

Semi-Supervised Hypothesis Testing by Betting on Predictions
by: Tenzer, Yaniv, et al.
Published: (2026)

Multi-Turn Jailbreaks Are Simpler Than They Seem
by: Yang, Xiaoxue, et al.
Published: (2025)

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

Adaptive Budget Allocation in LLM-Augmented Surveys
by: Ye, Zikun, et al.
Published: (2026)

Not All Turns Matter: Credit Assignment for Multi-Turn Jailbreaking
by: He, Zhida, et al.
Published: (2026)

Uncertainty Quantification and Data Efficiency in AI: An Information-Theoretic Perspective
by: Simeone, Osvaldo, et al.
Published: (2025)

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

Multi-Task Combinatorial Bandits for Budget Allocation
by: Ge, Lin, et al.
Published: (2024)

Online Learning with Improving Agents: Multiclass, Budgeted Agents and Bandit Learners
by: Ashkezari, Sajad, et al.
Published: (2026)

Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach
by: Bar, Yarin, et al.
Published: (2024)

ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestration
by: Hamri, May, et al.
Published: (2026)

Star Elastic: Many-in-One Reasoning LLMs with Efficient Budget Control
by: Taghibakhshi, Ali, et al.
Published: (2026)

Robust Conformal Outlier Detection under Contaminated Reference Data
by: Bashari, Meshi, et al.
Published: (2025)

Knowledge-Driven Multi-Turn Jailbreaking on Large Language Models
by: Li, Songze, et al.
Published: (2026)

Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning
by: Jali, Neharika, et al.
Published: (2026)

Pivotal Auto-Encoder via Self-Normalizing ReLU
by: Goldenstein, Nelson, et al.
Published: (2024)

Learning a Continue-Thinking Token for Enhanced Test-Time Scaling
by: Ringel, Liran, et al.
Published: (2025)

Semi-Supervised Risk Control via Prediction-Powered Inference
by: Einbinder, Bat-Sheva, et al.
Published: (2024)

Mitigating Many-Shot Jailbreaking
by: Ackerman, Christopher M., et al.
Published: (2025)

Jailbreak Attack Initializations as Extractors of Compliance Directions
by: Levi, Amit, et al.
Published: (2025)

Efficient Budget Allocation for Large-Scale LLM-Enabled Virtual Screening
by: Li, Zaile, et al.
Published: (2024)

SINR-Aware Deep Reinforcement Learning for Distributed Dynamic Channel Allocation in Cognitive Interference Networks
by: Cohen, Yaniv, et al.
Published: (2024)

Testing For Distribution Shifts with Conditional Conformal Test Martingales
by: Shaer, Shalev, et al.
Published: (2026)

Building Math Agents with Multi-Turn Iterative Preference Learning
by: Xiong, Wei, et al.
Published: (2024)

Synthetic-Powered Multiple Testing with FDR Control
by: Lee, Yonghoon, et al.
Published: (2026)

LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation
by: Shen, Yiqun, et al.
Published: (2025)

X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
by: Rahman, Salman, et al.
Published: (2025)

AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models
by: Reddy, Aashray, et al.
Published: (2025)

Jailbreaking Large Language Models in Infinitely Many Ways
by: Goldstein, Oliver, et al.
Published: (2025)

Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models
by: Francis-Meretzki, Shelly, et al.
Published: (2026)

Aligning LLMs Toward Multi-Turn Conversational Outcomes Using Iterative PPO
by: Jiang, Daniel R., et al.
Published: (2025)

Early Time Classification with Accumulated Accuracy Gap Control
by: Ringel, Liran, et al.
Published: (2024)

TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards
by: Xiong, Xiqiao, et al.
Published: (2025)

Cascaded Transfer: Learning Many Tasks under Budget Constraints
by: Campagne, Eloi, et al.
Published: (2026)