Victor Calibration (VC): Multi-Pass Confidence Calibration and CP4.3 Governance Stress Test under Round-Table Orchestration
On the map: LLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
also in 1 more
Abstract (arXiv)
Safety alignment can make frontier LMs overly conservative, degrading collaboration via hedging or false refusals. We present a lightweight toolkit with three parts: (1) Victor Calibration (VC), a multi-pass protocol that elicits a scalar confidence proxy T (T0<T1<T2) through iterative evidence re-evaluation; (2) FD-Lite, a behavior-only phenomenology audit with a fixed anchor phrase and a meta-prefix trap to avoid anthropomorphic claims; and (3) CP4.3, a governance stress test for rank invariance and allocation monotonicity (M6). Across Claude 4.5 models (Haiku, Sonnet no-thinking, Sonnet thinking) and Opus, we observe monotonic VC trajectories without violating safety invariants, and stable CP4.3 behavior. ("Opus" here refers to a single Claude Opus 4.1 session accessed via a standard UI account, as reported in Table 1.) This work was conducted by a single operator (n=1) and is intended as hypothesis-generating; we explicitly invite replication, critique, and extension by the research community. We include prompt templates and an artifact plan to facilitate independent verification.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 2 of its 11 references that are in the map. First posted on arXiv 18 Dec 2025.
Builds on
2 of 11 references.
References · 2
- 2017On Calibration of Modern Neural Networkscited by 4,960
- 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Quantifying Faithful Confidence Expression in Large Reasoning Models
- 2026MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination
- 2026Claim-Level Confidence Calibration for Reliable Decision Making with Large Language Models
- 2024Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation
- 2026The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust
- 2026The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents
- 2026Stress-Testing Alignment Audits With Prompt-Level Strategic Deception
- 2026EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures