Silent Commitment Failure in Instruction-Tuned Language Models: Evidence of Governability Divergence Across Architectures

• URL: http://arxiv.org/abs/2603.21415v1
• Date: Sun, 22 Mar 2026 21:50:28 GMT
• Title: Silent Commitment Failure in Instruction-Tuned Language Models: Evidence of Governability Divergence Across Architectures
• Abstract summary: We introduce governability -- the degree to which a model's errors are detectable before output commitment and correctable once detected.<n>We show benchmark accuracy does not predict governability, correction capacity varies independently of detection, and identical governance scaffolds produce opposite effects across models.<n>We propose a Detection and Correction Matrix classifying model-task combinations into four regimes: Governable, Monitor Only, Steer Blind, and Ungovernable.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As large language models are deployed as autonomous agents with tool execution privileges, a critical assumption underpins their security architecture: that model errors are detectable at runtime. We present empirical evidence that this assumption fails for two of three instruction-following models evaluable for conflict detection. We introduce governability -- the degree to which a model's errors are detectable before output commitment and correctable once detected -- and demonstrate it varies dramatically across models. In six models across twelve reasoning domains, two of three instruction-following models exhibited silent commitment failure: confident, fluent, incorrect output with zero warning signal. The remaining model produced a detectable conflict signal 57 tokens before commitment under greedy decoding. We show benchmark accuracy does not predict governability, correction capacity varies independently of detection, and identical governance scaffolds produce opposite effects across models. A 2x2 experiment shows a 52x difference in spike ratio between architectures but only +/-0.32x variation from fine-tuning, suggesting governability is fixed at pretraining. We propose a Detection and Correction Matrix classifying model-task combinations into four regimes: Governable, Monitor Only, Steer Blind, and Ungovernable.

Related papers

• Calibrating Interpretability Instruments Before Trusting Their Verdicts [1.0829694003408499]
  Causal claims about large language model (LLM) internals rest on measurements.<n>These measurements fail in specific, diagnosable ways that return a plausible number instead of an error.<n>This note documents six such failures from a causal interpretability program on refusal and moral representation.
  arXiv  Detail & Related papers  (2026-09-13T19:37:02Z)
• The Knowing-Saying Gap: When Probes See Errors that Confidence Misses [20.46211358172975]
  Linear probes detect corrupted context in language models with near-perfect accuracy, yet this does not translate into reliable failure prediction.<n>Across multi-hop arithmetic chains, probes that detect corruption turn out to be uninformative about final answer correctness.<n>As a real-time monitor, probe-based interventions are sharply model and error-type dependent.
  arXiv  Detail & Related papers  (2026-07-21T12:13:10Z)
• CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs [100.38986535324284]
  We introduce textbfCIAware-Bench, a benchmark for measuring textbfcontrol textbfintervention (CI) awareness across frontier models.<n>CIAware-Bench tests whether models can distinguish their own trajectories from those modified by a control intervention.
  arXiv  Detail & Related papers  (2026-06-09T16:24:16Z)
• A Universal Cliff and a Design Fingerprint: Cross-Section Defect Detection Under LLM Orchestration [0.0]
  Production language-model systems answer a request byspanning it across an invisible orchestration of worker agents.<n>We ask what this does to a class of defect no single worker can see.<n>We vary only the model -- ten systems across five generations from one developer and five providers from distinct alignment paradigms.
  arXiv  Detail & Related papers  (2026-05-25T05:09:48Z)
• Epistemic Observability in Language Models [0.0]
  We find that models report highest confidence precisely when they are fabricating.<n>We prove, under formal assumptions, that this is not a capability gap but an observational one.<n>We construct a tensor interface that escapes the impossibility by exporting computational byproducts.
  arXiv  Detail & Related papers  (2026-03-20T21:59:34Z)
• Engineering Verifiable Modularity in Transformers via Per-Layer Supervision [0.0]
  Ablating an attention head identified as critical for capitalization produces minimal behavioral change because distributed redundancy compensates for damage.<n>We demonstrate that architectural interventions can expose hidden modularity.<n>This es tablishes a methodology for transforming interpretability from passive observation to active control.
  arXiv  Detail & Related papers  (2026-03-08T05:18:14Z)
• Certainty-Validity: A Diagnostic Framework for Discrete Commitment Systems [0.0]
  "Machine learning evaluation metrics" assume that all errors are equivalent discrete commitment systems.<n>"ConfidentIncorrect" behavior is where models hallucinate structure in ambiguous data.<n>"Good training" for reasoning systems must be defined not by accuracy but by maximizing the Certainty-Validity Score.
  arXiv  Detail & Related papers  (2026-02-10T21:53:02Z)
• Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know" [47.930782177987446]
  Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations.<n>We evaluate three task-equivalent prompting regimes: Direct, Assistive, and Incremental, across different model scales and multi-hop QA benchmarks.<n>Because factual knowledge is stable while hallucinations are agreement, cross-regime provides a precise signal of internal uncertainty.
  arXiv  Detail & Related papers  (2026-02-04T18:39:58Z)
• When Models Know When They Do Not Know: Calibration, Cascading, and Cleaning [10.585100830578934]
  A promising approach is to use confidence, computed from the model's internal signals, to reflect its ignorance.<n>We propose a simple, effective, and universal training-free method that applies to both vision and language models.<n>Our results demonstrate that enabling models to recognize when they do not know is a practical step toward more efficient, reliable, and trustworthy AI.
  arXiv  Detail & Related papers  (2026-01-12T19:59:03Z)
• Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs [63.82840470917859]
  We show that the decoding mechanism of dLLMs can be used as a powerful tool for model attribution.<n>We propose a novel information extraction scheme called the Directed Decoding Map (DDM), which captures structural relationships between decoding steps and better reveals model-specific behaviors.
  arXiv  Detail & Related papers  (2025-10-02T06:25:10Z)
• Probing for Arithmetic Errors in Language Models [86.8227317662622]
  Internal activations in language models can be used to detect arithmetic errors.<n>We show that simple probes can accurately decode both the model's predicted output and the correct answer from hidden states.<n>We train lightweight error detectors that predict model correctness with over 90% accuracy.
  arXiv  Detail & Related papers  (2025-07-16T16:27:50Z)
• SecureBERT and LLAMA 2 Empowered Control Area Network Intrusion Detection and Classification [2.824211356106516]
  We develop two distinct models for CAN intrusion detection: CAN-SecureBERT and CAN-LLAMA2. Can-LLAMA2 model surpasses the state-of-the-art models by achieving an exceptional performance 0.999993 in terms of balanced accuracy, precision detection rate, F1 score, and a remarkably low false alarm rate of 3.10e-6.
  arXiv  Detail & Related papers  (2023-11-19T23:49:08Z)
• Tracking the risk of a deployed model and detecting harmful distribution shifts [105.27463615756733]
  In practice, it may make sense to ignore benign shifts, under which the performance of a deployed model does not degrade substantially. We argue that a sensible method for firing off a warning has to both (a) detect harmful shifts while ignoring benign ones, and (b) allow continuous monitoring of model performance without increasing the false alarm rate.
  arXiv  Detail & Related papers  (2021-10-12T17:21:41Z)
• Auditing AI models for Verified Deployment under Semantic Specifications [65.12401653917838]
  AuditAI bridges the gap between interpretable formal verification and scalability. We show how AuditAI allows us to obtain controlled variations for verification and certified training while addressing the limitations of verifying using only pixel-space perturbations.
  arXiv  Detail & Related papers  (2021-09-25T22:53:24Z)
• Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning [123.3472310767721]
  Prediction credibility measures are fundamental in statistics and machine learning. These measures should account for the wide variety of models used in practice. The framework developed in this work expresses the credibility as a risk-fit trade-off.
  arXiv  Detail & Related papers  (2020-11-24T19:52:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.