🛰️ Daily AI Frontier
‹ back to 2026-07-30

Fidelity Is Not Safety: Gently-Compressed LLMs Pass Every Data-Free Quality Guard Yet Invent Procedure Steps in Agentic Execution

Research Efficiency & Systems

Ranking

Overall 90
Content 100
Popularity 66

Observed public metrics from 1 member.

Merged summary

TL;DR - Gently compressed LLMs can pass standard quality and fidelity checks yet invent procedural steps during agentic execution. A data-free compression-error screen identifies risky low-rank builds before deployment.

  • SVD truncation caused invented SOP steps across three model families; perplexity-matched magnitude pruning did not.
  • Perplexity, MMLU, and representation-based fidelity tests failed to predict this behavior.
  • Risk correlated with compression-error coherence multiplied by error rate, not overall damage magnitude.
  • Fixed thresholds for coherent-error fraction and error rate flagged failing builds across architectures.

Sources (1)

Fidelity Is Not Safety: Gently-Compressed LLMs Pass Every Data-Free Quality Guard Yet Invent Procedure Steps in Agentic Execution

arXiv cs.CL I. Kennedy, T. Kennedy 2026-07-30 arXiv:2607.28196
Public signals Hugging Face upvotes 1
Providers: Hugging Face · Upvotes 1 OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-08-28 14:31:41.874245 UTC

TL;DR - Gently compressed LLMs can pass standard quality and fidelity checks yet invent procedural steps during agentic execution. A data-free compression-error screen identifies risky low-rank builds before deployment.

  • SVD truncation caused invented SOP steps across three model families; perplexity-matched magnitude pruning did not.
  • Perplexity, MMLU, and representation-based fidelity tests failed to predict this behavior.
  • Risk correlated with compression-error coherence multiplied by error rate, not overall damage magnitude.
  • Fixed thresholds for coherent-error fraction and error rate flagged failing builds across architectures.
item →