Copertina

Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sun, Chung-En, Liu, Xiaodong, Yang, Weiwei, Weng, Tsui-Wei, Cheng, Hao, San, Aidan, Galley, Michel, Gao, Jianfeng
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Crafting Large Language Models for Enhanced Interpretability
di: Sun, Chung-En, et al.
Pubblicazione: (2024)

ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models
di: Sun, Chung-En, et al.
Pubblicazione: (2025)

Effective Skill Unlearning through Intervention and Abstention
di: Li, Yongce, et al.
Pubblicazione: (2025)

ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretability
di: Sun, Chung-En, et al.
Pubblicazione: (2025)

Steer2Edit: From Activation Steering to Component-Level Editing
di: Sun, Chung-En, et al.
Pubblicazione: (2026)

Teaching Language Models to Self-Improve through Interactive Demonstrations
di: Yu, Xiao, et al.
Pubblicazione: (2023)

Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models
di: Li, Miaoran, et al.
Pubblicazione: (2023)

Concept Bottleneck Large Language Models
di: Sun, Chung-En, et al.
Pubblicazione: (2024)

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

Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents
di: Sun, Chung-En, et al.
Pubblicazione: (2024)

LLM Agents Already Know When to Call Tools -- Even Without Reasoning
di: Sun, Chung-En, et al.
Pubblicazione: (2026)

MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
di: Song, Jialin, et al.
Pubblicazione: (2026)

Agentic-imodels: Evolving agentic interpretability tools via autoresearch
di: Singh, Chandan, et al.
Pubblicazione: (2026)

ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning
di: Yu, Xiao, et al.
Pubblicazione: (2024)

Rethinking Interpretability in the Era of Large Language Models
di: Singh, Chandan, et al.
Pubblicazione: (2024)

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
di: Liu, Fan, et al.
Pubblicazione: (2024)

Enhancing the Reasoning Capabilities of Small Language Models via Solution Guidance Fine-Tuning
di: Bi, Jing, et al.
Pubblicazione: (2024)

Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents
di: Yu, Xiao, et al.
Pubblicazione: (2025)

ReflCtrl: Controlling LLM Reflection via Representation Engineering
di: Yan, Ge, et al.
Pubblicazione: (2025)

ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks
di: Yu, Xiaodong, et al.
Pubblicazione: (2023)

Training Large Reasoning Models Efficiently via Progressive Thought Encoding
di: Zhang, Zeliang, et al.
Pubblicazione: (2026)

Foot-In-The-Door: A Multi-turn Jailbreak for LLMs
di: Weng, Zixuan, et al.
Pubblicazione: (2025)

SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants?
di: Dou, Yao, et al.
Pubblicazione: (2025)

Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
di: Yu, Xiao, et al.
Pubblicazione: (2025)

Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs' Instruction Following Capability
di: wang, Jiaming, et al.
Pubblicazione: (2025)

Self-Prompt Tuning: Enable Autonomous Role-Playing in LLMs
di: Kong, Aobo, et al.
Pubblicazione: (2024)

Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts
di: Zhang, Zeliang, et al.
Pubblicazione: (2024)

MIST: Jailbreaking Black-box Large Language Models via Iterative Semantic Tuning
di: Zheng, Muyang, et al.
Pubblicazione: (2025)

PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents
di: Yang, Ke, et al.
Pubblicazione: (2026)

MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
di: Lu, Pan, et al.
Pubblicazione: (2023)

Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning
di: Xu, Xin, et al.
Pubblicazione: (2025)

PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization
di: Wang, Yidan, et al.
Pubblicazione: (2025)

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

Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimization
di: Zeng, Yongcheng, et al.
Pubblicazione: (2025)

Mitigating Jailbreaks with Intent-Aware LLMs
di: Yeo, Wei Jie, et al.
Pubblicazione: (2025)

AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation
di: Wang, Zijun, et al.
Pubblicazione: (2024)

Provable Defense Framework for LLM Jailbreaks via Noise-Augumented Alignment
di: Cheng, Zehua, et al.
Pubblicazione: (2026)

Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weighting
di: Luo, Yifan, et al.
Pubblicazione: (2024)

Braille-to-Speech Generator: Audio Generation Based on Joint Fine-Tuning of CLIP and Fastspeech2
di: Xu, Chun, et al.
Pubblicazione: (2024)

Language Models as Inductive Reasoners
di: Yang, Zonglin, et al.
Pubblicazione: (2022)