Pith. sign in

REVIEW 6 cited by

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2411.17713 v1 pith:WILDKNTL submitted 2024-11-18 cs.DC cs.AI

Igor Fedorov , Kate Plawiak , Lemeng Wu , Tarek Elgamal , Naveen Suda , Eric Smith , Hongyuan Zhan , Jianfeng Chi
show 12 more authors
Yuriy Hulovatyy Kimish Patel Zechun Liu Changsheng Zhao Yangyang Shi Tijmen Blankevoort Mahesh Pasupuleti Bilge Soran Zacharie Delpierre Coudert Rachad Alao Raghuraman Krishnamoorthi Vikas Chandra
This is my paper · ORCID
classification cs.DCcs.AI
keywords guardllamab-int4compactefficientachievingandroidapproximately
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper presents Llama Guard 3-1B-INT4, a compact and efficient Llama Guard model, which has been open-sourced to the community during Meta Connect 2024. We demonstrate that Llama Guard 3-1B-INT4 can be deployed on resource-constrained devices, achieving a throughput of at least 30 tokens per second and a time-to-first-token of 2.5 seconds or less on a commodity Android mobile CPU. Notably, our experiments show that Llama Guard 3-1B-INT4 attains comparable or superior safety moderation scores to its larger counterpart, Llama Guard 3-1B, despite being approximately 7 times smaller in size (440MB).

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. When Are Sparse Feature Interventions Actually Localized? Matched Evaluation for SAE-Based Safety Control

    cs.AI 2026-07 conditional novelty 6.5 of 10

    SAE safety ablations are regime-dependent and baseline-dependent: medium-k heads can look efficient, but surface-matched dense steering often beats them and high-k collapses coherence.

  2. MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation

    cs.CR 2025-10 conditional novelty 6.0 of 10

    Special tokens that structure LLM conversations can be injected and swapped for lookalike words to bypass both built-in safety and external content filters.

  3. WebGuard: Building a Generalizable Guardrail for Web Agents

    cs.AI 2025-07 conditional novelty 6.0 of 10

    WebGuard introduces an action-level risk dataset for web agents and shows that a fine-tuned 7B model improves risk-prediction accuracy from about 38% to 80% and high-risk recall from 20% to 76%, still below deployment...

  4. Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment

    cs.CV 2025-10 conditional novelty 5.0 of 10

    Risk-adaptive activation steering, guided by a prototype-similarity risk score computed on the first three response tokens, substantially reduces multimodal jailbreak success rates across four MLLMs while preserving utility.

  5. Benchmarking Large Language Models for Cryptanalysis and Side-Channel Vulnerabilities

    cs.CL 2025-05 conditional novelty 5.0 of 10

    Seven LLMs succeed only on ciphers common in pretraining data, and few-shot examples help mostly for easy ciphers, in a new 4,509-sample cryptanalysis benchmark.

  6. Agentic Web: Weaving the Next Web with AI Agents

    cs.AI 2025-07 conditional novelty 3.0 of 10

    A position paper defines the Agentic Web as the next web era and proposes a three-dimensional conceptual framework for understanding and building it.

Pith tools