[2607.28196] Fidelity Is Not Safety: Gently-Compressed LLMs Pass Every Data-Free Quality Guard Yet Invent Procedure Steps in Agentic Execution

Skip to main content

Search arXiv

Press Enter to search · Advanced search

-->

Computer Science > Computation and Language

arXiv:2607.28196 (cs)

[Submitted on 30 Jul 2026]

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

Authors:I. Kennedy, T.Kennedy<br>View a PDF of the paper titled Fidelity Is Not Safety: Gently-Compressed LLMs Pass Every Data-Free Quality Guard Yet Invent Procedure Steps in Agentic Execution, by I. Kennedy and 1 other authors

View PDF<br>HTML (experimental)

Abstract:Practitioners accept a compressed language model once it clears a stack of data-cheap quality guards: perplexity within a small factor of the original, downstream accuracy (for example MMLU) inside a confidence interval, and data-free output-fidelity signals that compare the compressed and original network's internal representations under random probe inputs. This stack has a blind spot. Across three model families, gently-compressed models clear every guard and then invent procedure steps that were never in the instructions when they run a standard operating procedure (SOP) as an agent. The effect is operator-specific: coherent low-rank (SVD) truncation induces it, and magnitude pruning matched to the same perplexity does not. One dissociation isolates the cause. The same compressed weights that CI-win a paired output-fidelity test CI-fail the invented-step canary. The governing axis is the coherence of the compression error times its rate; the magnitude of the damage does not predict it. The data-free fidelity probe is a fidelity oracle by construction, so it cannot see this axis. We characterize the blindspot and dissociation with paired confidence intervals on a pre-registered, powered canary across three architectures. Operator-specificity replicates on all three, and the perplexity-guard evasion appears where the model admits in-guard low-rank headroom. We then give a data-free screen: a two-axis statistic of the compression error (coherent-fraction and error-rate) that flags the failing builds with fixed thresholds across architectures and matches the coherence-times-rate mechanism. Perplexity, MMLU, and fidelity acceptance do not certify agent safety. Screen gently-compressed low-rank builds before agentic deployment

Subjects:

Computation and Language (cs.CL)

Cite as:<br>arXiv:2607.28196 [cs.CL]

(or<br>arXiv:2607.28196v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2607.28196

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Trevor Kennedy Mr [view email]<br>[v1]<br>Thu, 30 Jul 2026 13:33:09 UTC (13 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Fidelity Is Not Safety: Gently-Compressed LLMs Pass Every Data-Free Quality Guard Yet Invent Procedure Steps in Agentic Execution, by I. Kennedy and 1 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.CL

next >

new<br>recent<br>| 2026-07

Change to browse by:

cs

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more...