Copertina

Trust & Safety of LLMs and LLMs in Trust & Safety

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	You, Doohee, Chon, Dan
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Evaluating Deduplication Techniques for Economic Research Paper Titles with a Focus on Semantic Similarity using NLP and LLMs
di: You, Doohee, et al.
Pubblicazione: (2024)

Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense
di: Shen, Guobin, et al.
Pubblicazione: (2025)

Surviving the Unseen: Predictive Defense for Novel Multi-Turn Multimodal Attacks
di: You, Doohee
Pubblicazione: (2026)

Adjudicator: Correcting Noisy Labels with a KG-Informed Council of LLM Agents
di: You, Doohee, et al.
Pubblicazione: (2025)

Who Do LLMs Trust? Human Experts Matter More Than Other LLMs
di: Bajaj, Anooshka, et al.
Pubblicazione: (2026)

Building Trust: Foundations of Security, Safety and Transparency in AI
di: Sidhpurwala, Huzaifa, et al.
Pubblicazione: (2024)

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression
di: Hong, Junyuan, et al.
Pubblicazione: (2024)

Promoting Online Safety by Simulating Unsafe Conversations with LLMs
di: Hoffman, Owen, et al.
Pubblicazione: (2025)

Understanding and Preserving Safety in Fine-Tuned LLMs
di: Zhang, Jiawen, et al.
Pubblicazione: (2026)

From Logic to Language: A Trust Index for Problem Solving with LLMs
di: Rug, Tehseen, et al.
Pubblicazione: (2025)

SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering
di: Cao, Zouying, et al.
Pubblicazione: (2024)

Mapping the Trust Terrain: LLMs in Software Engineering -- Insights and Perspectives
di: Khati, Dipin, et al.
Pubblicazione: (2025)

ClawSafety: "Safe" LLMs, Unsafe Agents
di: Wei, Bowen, et al.
Pubblicazione: (2026)

Relationship-Aware Safety Unlearning for Multimodal LLMs
di: Anilkumar, Vishnu Narayanan, et al.
Pubblicazione: (2026)

LongSafety: Enhance Safety for Long-Context LLMs
di: Huang, Mianqiu, et al.
Pubblicazione: (2024)

AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use
di: Yang, Chenglin
Pubblicazione: (2026)

Classifier-free guidance in LLMs Safety
di: Smirnov, Roman
Pubblicazione: (2024)

Ensuring Safety and Trust: Analyzing the Risks of Large Language Models in Medicine
di: Yang, Yifan, et al.
Pubblicazione: (2024)

FESTA: Functionally Equivalent Sampling for Trust Assessment of Multimodal LLMs
di: Bhattacharya, Debarpan, et al.
Pubblicazione: (2025)

NomicLaw: Emergent Trust and Strategic Argumentation in LLMs During Collaborative Law-Making
di: Hota, Asutosh, et al.
Pubblicazione: (2025)

Know When to Trust the Skill: Delayed Appraisal and Epistemic Vigilance for Single-Agent LLMs
di: Unlu, Eren
Pubblicazione: (2026)

Building Trust in the Skies: A Knowledge-Grounded LLM-based Framework for Aviation Safety
di: Iyengar, Anirudh, et al.
Pubblicazione: (2026)

Enhancing Trust in LLMs: Algorithms for Comparing and Interpreting LLMs
di: Brown, Nik Bear
Pubblicazione: (2024)

Permissive Safety Through Trusted Inference: Verifiable Belief-Space Neural Safety Filters for Assured Interactive Robotics
di: Hu, Haimin
Pubblicazione: (2026)

Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments
di: Schnabl, Christoph, et al.
Pubblicazione: (2025)

Enhancing Trust and Safety in Digital Payments: An LLM-Powered Approach
di: Dahiphale, Devendra, et al.
Pubblicazione: (2024)

Trustful LLMs: Customizing and Grounding Text Generation with Knowledge Bases and Dual Decoders
di: Zhu, Xiaofeng, et al.
Pubblicazione: (2024)

Decomposed Trust: Privacy, Adversarial Robustness, Ethics, and Fairness in Low-Rank LLMs
di: Asante, Daniel Agyei, et al.
Pubblicazione: (2025)

Can LLMs Be Trusted for Evaluating RAG Systems? A Survey of Methods and Datasets
di: Brehme, Lorenz, et al.
Pubblicazione: (2025)

SAGE-Eval: Evaluating LLMs for Systematic Generalizations of Safety Facts
di: Yueh-Han, Chen, et al.
Pubblicazione: (2025)

Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs
di: Wang, Yifei, et al.
Pubblicazione: (2026)

JT-Safe: Intrinsically Enhancing the Safety and Trustworthiness of LLMs
di: Feng, Junlan, et al.
Pubblicazione: (2025)

Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs
di: Ferrand, Jean-Charles Noirot, et al.
Pubblicazione: (2025)

Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts
di: Chen, Hongyu, et al.
Pubblicazione: (2025)

SteeringSafety: A Systematic Safety Evaluation Framework of Representation Steering in LLMs
di: Siu, Vincent, et al.
Pubblicazione: (2025)

TrustGLM: Evaluating the Robustness of GraphLLMs Against Prompt, Text, and Structure Attacks
di: Zhang, Qihai, et al.
Pubblicazione: (2025)

Benchmarking Source-Sensitive Reasoning in Turkish: Humans and LLMs under Evidential Trust Manipulation
di: Karakaş, Sercan, et al.
Pubblicazione: (2026)

Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint Satisfaction
di: Curtis, Aidan, et al.
Pubblicazione: (2024)

Breaking the Safety-Capability Tradeoff: Reinforcement Learning with Verifiable Rewards Maintains Safety Guardrails in LLMs
di: Cho, Dongkyu Derek, et al.
Pubblicazione: (2025)

Safety Control of Service Robots with LLMs and Embodied Knowledge Graphs
di: Qi, Yong, et al.
Pubblicazione: (2024)