Hierarchical Group-Conditional Conformal Risk Control for Selective Prediction in Language Models

• URL: http://arxiv.org/abs/2607.24562v1
• Date: Mon, 27 Jul 2026 15:31:59 GMT
• Title: Hierarchical Group-Conditional Conformal Risk Control for Selective Prediction in Language Models
• Abstract summary: Conformal risk control (CRC) gives rigorous marginal risk guarantees for selective prediction with abstention.<n>Under mild shift in group composition, standard CRC violates the budget in up to 47% of trials.<n>We propose HG-CRC, a posthoc calibration framework enforcing simultaneous risk guarantees across all nodes of a user-defined group hierarchy.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models serve heterogeneous populations structured by domain, topic difficulty, and linguistic style. Conformal risk control (CRC) gives rigorous marginal risk guarantees for selective prediction with abstention, but marginal guarantees do not imply per-group ones: a model can meet the population budget while systematically over-exposing subgroups to errors. Under mild shift in group composition, standard CRC violates the budget in up to 47% of trials. We propose HG-CRC (Hierarchical Group-Conditional CRC), a post-hoc calibration framework enforcing simultaneous risk guarantees across all nodes of a user-defined group hierarchy. It applies a Bonferroni correction over nodes and a leaf-first policy that uses the most specific applicable threshold, falling back to coarser nodes when a finer one is uncertified or rejects the example. It needs only a held-out calibration set, with no retraining. We evaluate on three models (Qwen3-4B, Llama-3.1-8B-Instruct, Gemma-3-4B) and two benchmarks (ARC Challenge, MMLU-Pro) across eight configurations probing IID generalization, heterogeneity, mixture/domain/prompt/difficulty shift, label noise, and quantization. Main result: HG-CRC reaches an empirical 0% violation rate and WGER=0 on ARC Challenge for high-accuracy models (Qwen3-4B, Llama-3.1-8B). At 500 bootstrap trials these zeros are empirical upper bounds (true rate up to 0.6%), not certified. Results are benchmark-specific: on MMLU-Pro these models abstain entirely or (Llama) retain WGER=0.014. Gemma-3-4B, poorly calibrated here, degrades gracefully by abstaining. Participation cost vs. global CRC is 22 to 37 points. Ablations show hierarchical depth clears the budget: removing difficulty level returns violations to about 11%. Bonferroni is needed for the theoretical guarantee, though its empirical effect matters only with many nodes.

Related papers

• Certified Optimal Measurement Reduction over Quantum Context Landscapes [0.0]
  We use RANGE to compress molecular context dictionaries by 4.3-6.1x at 0.2-2.1-7.7 in shots within their own settings by up to 35qubit a fockproxy-co-Fockproxy-Fockproxy-Fockproxy-Fockproxy-Fockproxy-Fockproxy-Fockproxy-Fockproxy-Fockpro xy-Fockproxy-Fockproxy-Fockproxy-Fockproxy-Fockproxy-Fockproxy-Fockproxy-Fockproxy-Fockproxy-Fockpro xy-Fockproxy-Fockproxy-Fockproxy
  arXiv  Detail & Related papers  (2026-07-18T16:06:52Z)
• Modeling Normal Is All You Need: Joint Latent Clustering for Anomaly Detection in Multimodal Cyber-Physical Systems [47.027290803102666]
  Normal behaviour is the union of many imbalanced, curved, thin-fringed operating regimes.<n>We model the normal law with a jointly learned latent representation plus explicit Gaussian-mixture mode clustering.<n>We evaluate under a deliberately fair protocol: raw point-wise metrics with no point adjustment, a trivial-detector difficulty split, prevalence-matched F1, and train-normal-only calibration.
  arXiv  Detail & Related papers  (2026-07-07T10:10:00Z)
• When Can Conformal Risk Control Certify LLM Outputs? Bounds, Impossibility, and Adaptation for Structured Generation [0.11280931253550518]
  Large language models (LLMs) deployed for structured generation (NER, extraction, QA, and classification) lack formal reliability guarantees.<n>We characterize when conformal risk control (CRC) can certify structured LLM outputs and when it provably cannot.
  arXiv  Detail & Related papers  (2026-06-27T19:25:07Z)
• BOKBO (Best of K Bad Options): Calibrated Abstention for VLA Policies [1.3918848543076061]
  Test-time scaling for vision-suite-action (VLA) policies, methods such as RoboMonkey, SEAL, MG-Select, and V-GPS, samples K candidate action chunks at inference and executes the verifier-best.<n>We propose BOKBO, the first conformal abstention layer for K-sample VLA inference, providing finite-sample distribution-free guarantees on executed-violation rate.
  arXiv  Detail & Related papers  (2026-05-28T23:39:09Z)
• Federated Naive Bayes with Real Mixture of Gaussians and Institutional Governance Regularization for Network Intrusion Detection [0.0]
  Federated learning for intrusion detection rests on a flawed premise: that every participating institution contributes equally to the shared model.<n>In practice, a financial institution with mature security controls and low vulnerability exposure produces fundamentally different data than a government agency running with weaker controls and higher vulnerability exposure.<n>Treating their local models as models discard information that organisations already collect through standard risk management audits.
  arXiv  Detail & Related papers  (2026-05-18T16:54:49Z)
• Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data [55.84428098924793]
  We propose Constrained Uniform Top-K Sampling (CUTS), a parameter-free decoding strategy enforcing structure-preserving exploration.<n>We integrate this into Mixed-CUTS, a training framework synergizing exploitative and exploratory rollouts to amplify intra-group advantage variance.<n> Notably, Mixed-CUTS improves Pass@1 accuracy on the challenging AIME25 benchmark by up to 15.1% over standard GRPO.
  arXiv  Detail & Related papers  (2026-04-20T16:43:28Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• 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)
• Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness [61.45587642780908]
  We propose a three-step approach for parameter-efficient fine-tuning of image-text foundation models.<n>Our method improves its two key components: minority samples identification and the robust training algorithm.<n>Our theoretical analysis shows that our PPA enhances minority group identification and is Bayes optimal for minimizing the balanced group error.
  arXiv  Detail & Related papers  (2025-03-12T15:46:12Z)
• Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization [61.39201891894024]
  Group distributionally robust optimization (group DRO) can minimize the worst-case loss over pre-defined groups. We reformulate the group DRO framework by proposing Q-Diversity. Characterized by an interactive training mode, Q-Diversity relaxes the group identification from annotation into direct parameterization.
  arXiv  Detail & Related papers  (2023-05-20T07:02:27Z)

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.