Calibrate What You SHIP: Post-Selection Risk Control for Verifier-Guided Text-to-Image Generation

• URL: http://arxiv.org/abs/2608.21748v1
• Date: Sat, 22 Aug 2026 03:05:44 GMT
• Title: Calibrate What You SHIP: Post-Selection Risk Control for Verifier-Guided Text-to-Image Generation
• Abstract summary: We introduce SHIP, Selection-aware Held-out calibration of Inference Policies.<n> SHIP runs or replays the complete deployed policy on held-out prompts, evaluates the image it actually releases using an independent target judge, and selects the most permissive threshold whose risk upper bound satisfies a prescribed budget.<n>Experiments across fixed, sequential, and adaptive T2I inference procedures show that policy-level calibration recovers lower-risk operating points while exposing policy-dependent tradeoffs among risk, coverage, and compute.
• Score: 10.591500152032529
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Verifier-guided text-to-image systems increasingly use test-time search to select, refine, or stop among multiple candidates, yet release thresholds are often calibrated on individual images. This creates a candidate-to-policy calibration mismatch: search changes both which prompts receive an output and which candidate is released, so candidate-level risk control need not imply control of released-output risk. We formalize this estimand shift through prompt reweighting and within-prompt selection, and introduce SHIP, Selection-aware Held-out calibration of Inference Policies. SHIP runs or replays the complete deployed policy on held-out prompts, evaluates the image it actually releases using an independent target judge, and selects the most permissive threshold whose risk upper bound satisfies a prescribed budget. For replayable policies with a prespecified threshold grid, simultaneous confidence control provides finite-sample validity. Experiments across fixed, sequential, and adaptive T2I inference procedures show that policy-level calibration recovers lower-risk operating points while exposing policy-dependent tradeoffs among risk, coverage, and compute. On GenEval2 with FLUX at N=16, a pooled-candidate threshold yields released risk 0.310, whereas SHIP reduces it to 0.162. Across 200 cached-stream splits, the fixed-grid certificate has no target crossing. Reliable inference-time scaling therefore requires calibrating the output distribution induced by the complete deployed policy.

Related papers

• SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute [62.3458279176813]
  Self-Verifying Refinement is an oracle-free multi-turn reinforcement learning framework.<n>It learns to use self-verification as a compute-control policy.<n>It achieves a macro-average accuracy of 0.563 with only 2.99 inference turns on average.
  arXiv  Detail & Related papers  (2026-07-30T16:20:58Z)
• PromptShift-CRC: Drift-Aware Conformal Risk Control for Foundation Models Under Prompt and Domain Shift [0.0]
  Foundation models are now used in settings where the prompts they receive can change quickly.<n>Conformal prediction and conformal risk control give model-agnostic ways to control error, but they work best when the calibration data still look like the future data.<n>This paper develops PromptShift CRC, a drift-aware conformal risk control method for foundation-model outputs under prompt and domain shift.
  arXiv  Detail & Related papers  (2026-06-14T18:45:56Z)
• Risk-Controlled Post-Processing of Decision Policies [38.38357747696667]
  We study risk-controlled post-processing: given a deterministic baseline policy, choose a new policy that maximizes agreement with the baseline subject to a chance constraint on a user-specified loss.<n>We show that the optimal policy has a threshold structure: it follows the baseline except on contexts where switching to the fallback policy yields a large reduction in conditional violation risk.<n>Experiments on a COVID-19 radiograph diagnosis task, an LLM routing problem, and a synthetic multiclass decision task show that targeted post-processing can meet or nearly meet risk budgets while preserving substantially more agreement with the baseline than score-blind random mixing
  arXiv  Detail & Related papers  (2026-05-07T16:03:24Z)
• DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding [59.16244104797919]
  We propose **Disagreement-Aware Alignment via Risk-Constrained Decoding (DARC)**.<n>DARC frames response selection as distributionally robust, risk-sensitive decision making.<n>Experiments on alignment benchmarks show that DARC reduces disagreement and tail risk while maintaining competitive average quality.
  arXiv  Detail & Related papers  (2026-03-09T09:21:29Z)
• LEC: Linear Expectation Constraints for False-Discovery Control in Selective Prediction and Routing Systems [95.35293543918762]
  Large language models (LLMs) often generate unreliable answers, while uncertainty methods fail to fully distinguish correct from incorrect predictions.<n>We address this issue through the lens of false discovery rate (FDR) control, ensuring that among all accepted predictions, the proportion of errors does not exceed a target risk level.<n>We propose LEC, which reinterprets selective prediction as a constrained decision problem by enforcing a Linear Expectation Constraint.
  arXiv  Detail & Related papers  (2025-12-01T11:27:09Z)
• SAFER: Risk-Constrained Sample-then-Filter in Large Language Models [38.97678256807034]
  We introduce a two-stage risk control framework comprising abstention-aware sampling and conformalized filtering.<n>We show that SAFER is compatible with various task-specific admission criteria and calibration-test split ratios.
  arXiv  Detail & Related papers  (2025-10-11T12:12:41Z)
• Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty [49.19257648205146]
  We propose an unsupervised conformal inference framework for generation.<n>Our gates achieve close-to-nominal coverage and provide tighter, more stable thresholds than split UCP.<n>The result is a label-free, API-compatible gate for test-time filtering.
  arXiv  Detail & Related papers  (2025-09-26T23:40:47Z)
• COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees [51.5976496056012]
  COIN is an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question.<n>COIN estimates the empirical error rate on a calibration set and applies confidence interval methods to establish a high-probability upper bound on the true error rate.<n>We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data.
  arXiv  Detail & Related papers  (2025-06-25T07:04:49Z)
• Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking [57.42241521034744]
  We propose the concept of certified error control of candidate set pruning for relevance ranking. Our method successfully prunes the first-stage retrieved candidate sets to improve the second-stage reranking speed.
  arXiv  Detail & Related papers  (2022-05-19T16:00:13Z)

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.