Pith. sign in

REVIEW 10 cited by

Large Language Model Safety: A Holistic Survey

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.17686 v1 pith:BM3VMQ63 submitted 2024-12-23 cs.AI cs.CL

Large Language Model Safety: A Holistic Survey

classification cs.AI cs.CL
keywords safetyfourintegrationlanguagellmssurveyassociatedcomprehensive
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The rapid development and deployment of large language models (LLMs) have introduced a new frontier in artificial intelligence, marked by unprecedented capabilities in natural language understanding and generation. However, the increasing integration of these models into critical applications raises substantial safety concerns, necessitating a thorough examination of their potential risks and associated mitigation strategies. This survey provides a comprehensive overview of the current landscape of LLM safety, covering four major categories: value misalignment, robustness to adversarial attacks, misuse, and autonomous AI risks. In addition to the comprehensive review of the mitigation methodologies and evaluation resources on these four aspects, we further explore four topics related to LLM safety: the safety implications of LLM agents, the role of interpretability in enhancing LLM safety, the technology roadmaps proposed and abided by a list of AI companies and institutes for LLM safety, and AI governance aimed at LLM safety with discussions on international cooperation, policy proposals, and prospective regulatory directions. Our findings underscore the necessity for a proactive, multifaceted approach to LLM safety, emphasizing the integration of technical solutions, ethical considerations, and robust governance frameworks. This survey is intended to serve as a foundational resource for academy researchers, industry practitioners, and policymakers, offering insights into the challenges and opportunities associated with the safe integration of LLMs into society. Ultimately, it seeks to contribute to the safe and beneficial development of LLMs, aligning with the overarching goal of harnessing AI for societal advancement and well-being. A curated list of related papers has been publicly available at https://github.com/tjunlp-lab/Awesome-LLM-Safety-Papers.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. APPSI-139: A Parallel Corpus of English Application Privacy Policy Summarization and Interpretation

    cs.CL 2026-04 conditional novelty 7.0

    APPSI-139 supplies a high-quality parallel corpus of privacy policies with expert summaries and labels, paired with TCSI-pp-V2, a hybrid framework that outperforms GPT-4o and LLaMA-3-70B on readability and reliability.

  2. Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents

    cs.AI 2026-05 unverdicted novelty 6.0

    Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.

  3. Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning

    cs.LG 2026-05 unverdicted novelty 6.0

    Distinguishable Deletion unifies knowledge erasure and refusal for LLM unlearning via an energy index that enforces boundaries during training and enables refusal at inference.

  4. State Contamination in Memory-Augmented LLM Agents

    cs.AI 2026-05 unverdicted novelty 6.0

    Toxic context can be laundered into memory summaries that stay below toxicity thresholds while still driving higher downstream toxicity in LLM agents compared to neutral baselines.

  5. LLM-Guided Prompt Evolution for Password Guessing

    cs.CR 2026-04 unverdicted novelty 6.0

    LLM-guided evolutionary prompt optimization using MAP-Elites and island models raises password cracking rates from 2.02% to 8.48% on a RockYou-derived test set across local, cloud, and ensemble LLM setups.

  6. Why Do Large Language Models Generate Harmful Content?

    cs.AI 2026-04 unverdicted novelty 6.0

    Causal mediation analysis shows harmful LLM outputs arise in late layers from MLP failures and gating neurons, with early layers handling harm context detection and signal propagation.

  7. Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs

    cs.AI 2026-06 unverdicted novelty 5.0

    A survey that maps safety risks in personalized LLMs, introduces a unified taxonomy, and highlights three structural inadequacies in existing research on user-invariant safety, isolated techniques, and short-term evaluations.

  8. Rethinking Fraud Safety Evaluation: Multi-Round Attacks Reveal Safety-Utility Tradeoffs in Graph-Context LLM Defenders

    cs.CR 2026-05 unverdicted novelty 5.0

    Graph-context LLM fraud defenders improve early refusal under replay and adaptive multi-round attacks compared to text baselines but increase benign over-refusal, with the cost localized to how the LLM consumes struct...

  9. A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook

    cs.SD 2026-05 unverdicted novelty 5.0

    A survey of Large Audio Language Models that establishes a taxonomy of trustworthiness vulnerabilities and proposes a Defense-in-Depth roadmap for audio intelligence.

  10. An Empirical Study of Multi-Generation Sampling for Jailbreak Detection in Large Language Models

    cs.CL 2026-04 unverdicted novelty 5.0

    Multi-generation sampling from LLMs uncovers more jailbreak behaviors than single generations, with the largest gains from one to moderate sample counts and diminishing returns thereafter.