Image de couverture de livre

Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sun, Chung-En, Liu, Xiaodong, Yang, Weiwei, Weng, Tsui-Wei, Cheng, Hao, San, Aidan, Galley, Michel, Gao, Jianfeng
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Crafting Large Language Models for Enhanced Interpretability
par: Sun, Chung-En, et autres
Publié: (2024)

ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models
par: Sun, Chung-En, et autres
Publié: (2025)

Effective Skill Unlearning through Intervention and Abstention
par: Li, Yongce, et autres
Publié: (2025)

ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretability
par: Sun, Chung-En, et autres
Publié: (2025)

Steer2Edit: From Activation Steering to Component-Level Editing
par: Sun, Chung-En, et autres
Publié: (2026)

Teaching Language Models to Self-Improve through Interactive Demonstrations
par: Yu, Xiao, et autres
Publié: (2023)

Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models
par: Li, Miaoran, et autres
Publié: (2023)

Concept Bottleneck Large Language Models
par: Sun, Chung-En, et autres
Publié: (2024)

SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
par: Feng, Mingqian, et autres
Publié: (2026)

Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents
par: Sun, Chung-En, et autres
Publié: (2024)

LLM Agents Already Know When to Call Tools -- Even Without Reasoning
par: Sun, Chung-En, et autres
Publié: (2026)

MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
par: Song, Jialin, et autres
Publié: (2026)

Agentic-imodels: Evolving agentic interpretability tools via autoresearch
par: Singh, Chandan, et autres
Publié: (2026)

ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning
par: Yu, Xiao, et autres
Publié: (2024)

Rethinking Interpretability in the Era of Large Language Models
par: Singh, Chandan, et autres
Publié: (2024)

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
par: Liu, Fan, et autres
Publié: (2024)

Enhancing the Reasoning Capabilities of Small Language Models via Solution Guidance Fine-Tuning
par: Bi, Jing, et autres
Publié: (2024)

Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents
par: Yu, Xiao, et autres
Publié: (2025)

ReflCtrl: Controlling LLM Reflection via Representation Engineering
par: Yan, Ge, et autres
Publié: (2025)

ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks
par: Yu, Xiaodong, et autres
Publié: (2023)

Training Large Reasoning Models Efficiently via Progressive Thought Encoding
par: Zhang, Zeliang, et autres
Publié: (2026)

Foot-In-The-Door: A Multi-turn Jailbreak for LLMs
par: Weng, Zixuan, et autres
Publié: (2025)

SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants?
par: Dou, Yao, et autres
Publié: (2025)

Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
par: Yu, Xiao, et autres
Publié: (2025)

Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs' Instruction Following Capability
par: wang, Jiaming, et autres
Publié: (2025)

Self-Prompt Tuning: Enable Autonomous Role-Playing in LLMs
par: Kong, Aobo, et autres
Publié: (2024)

Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts
par: Zhang, Zeliang, et autres
Publié: (2024)

MIST: Jailbreaking Black-box Large Language Models via Iterative Semantic Tuning
par: Zheng, Muyang, et autres
Publié: (2025)

PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents
par: Yang, Ke, et autres
Publié: (2026)

MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
par: Lu, Pan, et autres
Publié: (2023)

Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning
par: Xu, Xin, et autres
Publié: (2025)

PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization
par: Wang, Yidan, et autres
Publié: (2025)

Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models
par: Tsui, Ken
Publié: (2025)

Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimization
par: Zeng, Yongcheng, et autres
Publié: (2025)

Mitigating Jailbreaks with Intent-Aware LLMs
par: Yeo, Wei Jie, et autres
Publié: (2025)

AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation
par: Wang, Zijun, et autres
Publié: (2024)

Provable Defense Framework for LLM Jailbreaks via Noise-Augumented Alignment
par: Cheng, Zehua, et autres
Publié: (2026)

Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weighting
par: Luo, Yifan, et autres
Publié: (2024)

Braille-to-Speech Generator: Audio Generation Based on Joint Fine-Tuning of CLIP and Fastspeech2
par: Xu, Chun, et autres
Publié: (2024)

Language Models as Inductive Reasoners
par: Yang, Zonglin, et autres
Publié: (2022)