Pith. sign in

REVIEW 10 cited by

Safeguarding Large Language Models: A 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 2406.02622 v1 pith:IQJXPRRF submitted 2024-06-03 cs.CR cs.AI

classification cs.CRcs.AI
keywords currentmechanismtechniquesattackschallengescomprehensiveethicalguardrail
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In the burgeoning field of Large Language Models (LLMs), developing a robust safety mechanism, colloquially known as "safeguards" or "guardrails", has become imperative to ensure the ethical use of LLMs within prescribed boundaries. This article provides a systematic literature review on the current status of this critical mechanism. It discusses its major challenges and how it can be enhanced into a comprehensive mechanism dealing with ethical issues in various contexts. First, the paper elucidates the current landscape of safeguarding mechanisms that major LLM service providers and the open-source community employ. This is followed by the techniques to evaluate, analyze, and enhance some (un)desirable properties that a guardrail might want to enforce, such as hallucinations, fairness, privacy, and so on. Based on them, we review techniques to circumvent these controls (i.e., attacks), to defend the attacks, and to reinforce the guardrails. While the techniques mentioned above represent the current status and the active research trends, we also discuss several challenges that cannot be easily dealt with by the methods and present our vision on how to implement a comprehensive guardrail through the full consideration of multi-disciplinary approach, neural-symbolic method, and systems development lifecycle.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

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

  1. Tailored untruths: How personalisation challenges LLM safeguards

    cs.CL 2025-10 conditional novelty 7.0 of 10

    A 1.6-million-text study of eight LLMs in four languages finds that adding demographic personae to disinformation prompts raises jailbreak rates from 78% to 82%.

  2. FairI Tales: Evaluation of Fairness in Indian Contexts with a Focus on Bias and Stereotypes

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A new India-focused benchmark shows that popular LLMs exhibit measurable negative bias against marginalized Indian identities and frequently reinforce caste, religion, region, and tribe stereotypes.

  3. Sword and Shield: Uses and Strategies of LLMs in Navigating Disinformation

    cs.HC 2025-06 conditional novelty 6.0 of 10

    In a 25-participant Werewolf-style game, all roles used an LLM chatbot strategically, as a sword for disinformation and a shield against it.

  4. Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows

    cs.CR 2026-07 conditional novelty 5.0 of 10

    A survey of 49 LLM fraud and trust-and-safety papers finds that fraud work reports almost no per-decision latency, cost, or calibration evidence, while moderation work reports more.

  5. Echoes of Human Malice in Agents: Benchmarking LLMs for Multi-Turn Online Harassment Attacks

    cs.AI 2025-10 conditional novelty 5.0 of 10

    Fine-tuning an LLM on synthetic toxic dialogues makes it harass in 95–97% of multi-turn conversations in Llama and ~99% in Gemini; memory and planning attacks also raise closed-source vulnerability.

  6. Speaking images. A novel framework for the automated self-description of artworks

    cs.CV 2025-05 conditional novelty 5.0 of 10

    A four-stage open-source AI pipeline turns a digitized artwork into a short video where a depicted person animates and narrates the scene.

  7. A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models

    cs.CL 2025-09 conditional novelty 4.0 of 10

    A structured literature survey concluding that reasoning capabilities do not automatically make LLMs more trustworthy and can introduce new vulnerabilities in safety, robustness, and privacy.

  8. Enhancing Robustness of LLM-Driven Multi-Agent Systems through Randomized Smoothing

    cs.AI 2025-07 reject novelty 4.0 of 10

    Randomized smoothing with adaptive sampling is claimed to give probabilistic robustness guarantees for LLM-driven multi-agent consensus, with simulations showing a 90.24% reduction in deviation from ideal consensus.

  9. A Survey on Model Extraction Attacks and Defenses for Large Language Models

    cs.CR 2025-06 conditional novelty 4.0 of 10

    A taxonomy of model extraction attacks and defenses for large language models, with proposed evaluation metrics and future research directions.

  10. LLM Harms: A Taxonomy and Discussion

    cs.CY 2025-12 unverdicted novelty 3.0 of 10

    This paper proposes a taxonomy of LLM harms in five categories and suggests mitigation strategies plus a dynamic auditing system for responsible development.

Pith tools