arXiv Machine Learning August 11, 2026 By Yang Xiao

Wrong Design Intent Is Worse Than Never Conditioning: A Derangement-Control Diagnosis of Header Conditioning in CAD Program Completion

Read the original on arXiv Machine Learning →

arXiv:2607. 23191v3 Announce Type: replace Abstract: Fine-tuned code LLMs are routinely conditioned on a design-intent specification, but the correctness axis of such a signal -- a wrong intent rather than an absent one -- has not been tested, and the benefit of conditioning is usually scored with the same detector that defines the signal.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 6

Wrong Design Intent Can Be Worse Than None: A Derangement-Control Diagnosis of Header Conditioning in CAD Program Completion

arXiv:2607. 23191v2 Announce Type: replace Abstract: Fine-tuned code LLMs are often conditioned on a design-intent header to steer parametric CAD generation, but whether the model reads that header's content has been tested neither under execution-level scoring nor with a causal control.

By Yang Xiao

llms fine-tuning safety

arXiv Machine Learning

Jul 28

Wrong Design Intent Is Worse Than None: A Derangement-Control Diagnosis of Header Conditioning in CAD Program Completion

arXiv:2607. 23191v1 Announce Type: new Abstract: Fine-tuned code LLMs can be conditioned on a lightweight design-intent header to steer parametric CAD generation, but whether the model actually reads the header's content has not been tested under a metric independent of the conditioning itself, nor with a causal control.

By Yang Xiao

llms fine-tuning

arXiv Machine Learning

Jun 25

Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models

arXiv:2606. 24952v1 Announce Type: cross Abstract: A central aspiration of mechanistic interpretability is controllability: if we know where a behavior is represented in a model's activations, we should be able to modify it.

By Cosimo Galeone, Anna Ettorre, Minsu Park, Giuseppe Ettorre, Daniele Ligorio

llms fine-tuning safety

arXiv Machine Learning

Jun 30

Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring

arXiv:2606. 30449v1 Announce Type: new Abstract: Probes on model internals could help monitor agentic systems if they identify harmful text or tool actions before those actions are generated.

By Max Fomin, Elad David, Amit LeVi

llms agents fine-tuning

arXiv AI

Jul 9

Specification Grounding Drives Test Effectiveness for LLM Code

arXiv:2607. 06636v1 Announce Type: cross Abstract: Large language models frequently generate code that appears correct on typical inputs yet fails on edge cases, invalid inputs, and other specification-defined corner conditions.

By Amin Haeri, Mahdi Ghelichi

llms benchmarks

arXiv AI

6d ago

Harness-IF: Evaluating Instruction Following Across Instruction Surfaces in Coding Agents

arXiv:2608. 11727v1 Announce Type: new Abstract: When a coding agent obeys a rule, it may simply have been going to do that anyway.

By Zining Huang, Haoran Que, Hong Zeng, Ge Zhang, Zuo Wang, Jin Chen, Haodong Wang, Zhongfei Hou, Changxin Pu, Shen Yan, Wenhao Huang

agents benchmarks

Related stories

Wrong Design Intent Can Be Worse Than None: A Derangement-Control Diagnosis of Header Conditioning in CAD Program Completion

Wrong Design Intent Is Worse Than None: A Derangement-Control Diagnosis of Header Conditioning in CAD Program Completion

Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models

Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring

Specification Grounding Drives Test Effectiveness for LLM Code

Harness-IF: Evaluating Instruction Following Across Instruction Surfaces in Coding Agents