REVIEW 9 cited by
Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle
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
Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle
read the original abstract
Recent innovations in language model training have demonstrated that it is possible to create highly performant models that are small enough to run on a smartphone. As these models are deployed in an increasing number of domains, it is critical to ensure that they are aligned with human preferences and safety considerations. In this report, we present our methodology for safety aligning the Phi-3 series of language models. We utilized a "break-fix" cycle, performing multiple rounds of dataset curation, safety post-training, benchmarking, red teaming, and vulnerability identification to cover a variety of harm areas in both single and multi-turn scenarios. Our results indicate that this approach iteratively improved the performance of the Phi-3 models across a wide range of responsible AI benchmarks. Finally, we include additional red teaming strategies and evaluations that were used to test the safety behavior of Phi-3.5-mini and Phi-3.5-MoE, which were optimized for multilingual capabilities.
Forward citations
Cited by 9 Pith papers
-
Redefining AI Red Teaming in the Agentic Era: From Weeks to Hours
An agentic red teaming system automates creation of adversarial testing workflows from natural language goals, unifying ML and generative AI attacks and achieving 85% success rate on Meta Llama Scout with no custom hu...
-
Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
TPCs allow term-by-term progressive polynomial evaluation on LLM activations for flexible safety monitoring that supports both stronger guardrails and low-cost adaptive cascades.
-
EinSort: Sorting is All We Need for Tensorizing LLM
Sorting tensor indices enables an adaptive tensorization method that discovers low-rank structure in LLM weights and KV caches, yielding better reconstruction quality than baselines.
-
Mask the Target: A Plug-and-Play Regularizer Against LoRA Forgetting
A plug-and-play KL regularizer that masks the target token and renormalizes probabilities to improve the learning-forgetting trade-off in LoRA adaptation of LLMs.
-
Standing on the Shoulders of Giants: Stabilized Knowledge Distillation for Cross--Language Code Clone Detection
Reasoning-oriented knowledge distillation from DeepSeek-R1 plus response stabilization improves reliability and often performance of compact models for cross-language code clone detection on pairs like Python-Java and...
-
Multilingual Refusal Alignment for Safer Large Language Models
English-only safety alignment fails to transfer cross-lingually, while multilingual DPO training on the new RefusEU dataset improves safety across 12 European languages without degrading Global MMLU performance.
-
A Scheduling Framework for Efficient MoE Inference on Edge GPU-NDP Systems
On simulated GPU-NDP-DIMM hardware, scheduling MoE experts with tensor parallelism, load balancing, and prefill-driven pre-fetching cuts end-to-end latency by 2.41x on average versus MoNDE.
-
Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
Phi-4-Mini achieves strong math and coding performance with only 3.8B parameters via high-quality synthetic data, while Phi-4-Multimodal uses Mixture-of-LoRAs to integrate modalities and top speech recognition leaderboards.
-
Securing LLMs in the Wild: Privacy and Security Challenges at the Edge
Edge LLM security is framed as a Security-Efficiency Paradox, with a three-wall constraint model, a composite SOES score, and a small FP/INT4 benchmark of six models.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.