Selective Prediction

Follow this topic Ask about this topic

Selective prediction studies how models should decide whether to make a prediction, abstain, or escalate an uncertain case to a person or another system. Common approaches use confidence and uncertainty scores, ensembles or verifiers, and calibration methods such as conformal prediction to set risk–coverage trade-offs. Applications range from image classification and clinical triage to language-model question answering and agent actions, where benchmarks increasingly assess accepted-case errors, coverage, review costs, and subgroup outcomes. A central challenge is that useful confidence rankings do not by themselves guarantee safe decisions: calibration and risk guarantees can depend on data assumptions, shift across domains or groups, and sharply reduce coverage.

Latest papers

292 papers58 papers in the last four weeks, up 38% on the four weeks before. 0.3% of all new papers.

Jul 3, 2026

Aligning Language Models with Selective Prediction

Large language models (LLMs) are increasingly deployed as critical decision-making components in high-stakes real-world AI systems, rendering LLM reliability a foremost practical concern. In this paper, we focus on enhancing LLM reliability through selective prediction (SP), a strategy that allows an LLM to only predict for inputs where it is likely to be correct (i.e., coverage) and hence reduce the error rate (i.e., risk) on that portion of inputs -- flagging the remaining inputs for future human discretion. In other words, SP improves LLM reliability by balancing the risk-coverage trade-off and enabling seamless human-AI collaboration. To integrate SP into LLMs, we focus on the LLM post-training alignment stage and propose to align LLMs with SP performance metrics, in contrast with existing LLM alignment methods that focus primarily on correctness or calibration metrics. Specifically, we propose a novel alignment framework, Reinforcement Learning for Selection Reward (RLSR), which targets the area under the risk-coverage curve (AURC) -- a popular SP performance metric -- as its alignment objective. RLSR achieves substantially better risk-coverage trade-off compared to multiple alignment baselines on both in-domain and out-of-domain tasks.

Gaoxiang Luo, Yifan Wu, Sinian Zhang +2

Department of Computer Science and Engineering · 2Bioinformatics and Computational Biology Program · 3Division of Biostatistics and Health Data Science

RL for Language Models LLM Alignment Selective Prediction LLM Reliability Language Model Post-Training

Jul 3, 2026

Denoised Conformal Alignment for Reliable Selection of Conditional Average Treatment Effect Predictions

In selective deployment, practitioners act only on a model-chosen subset of individuals based on predicted conditional average treatment effects, but marginal conformal guarantees need not control reliability on that selected subset. We study reliable selection for black-box CATE predictors: selecting candidates whose CATE errors are below a tolerance while controlling the false discovery rate (FDR). Since CATE errors are unobservable, we construct doubly robust proxy errors from pseudo-outcomes; however, naive proxies can lose power under heteroskedasticity because variance overwhelms the reliability signal. We propose Denoised Conformal Alignment, which subtracts an estimated conditional variance component and combines conformal calibration with Benjamini--Hochberg selection. Our analysis shows that validity is governed by stability of proxy/oracle threshold labels, rather than pointwise perfection of the variance estimator. Experiments show substantially improved power while maintaining FDR control across challenging settings.

Xinyun Lu, Haoang Chi, Zhiheng Zhang

Shanghai University of Finance and Economics · Shanghai Jiao Tong University · National University of Defense Technology, Changsha, China +2

Causal Effect Estimation Selective Prediction FDR Control Conditional Average Treatment Effect Estimation Conformal Prediction Individualized Treatment Effect Estimation

Jul 3, 2026

Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification

Safety-critical applications require classifiers that are both robust and reliable. Adversarial training is a widely adopted defense for improving robustness in deep neural networks; however, its effect on the reliability of predictive uncertainty remains underexplored. We investigate this gap through the lens of selective classification, which has rarely been systematically analyzed alongside adversarial robustness. We introduce a unified benchmark for the robustness-uncertainty trade-off. It standardizes architectures, augmentations, threat models, and evaluation metrics across clean, adversarial, and common-corruption settings. Across a wide range of state-of-the-art adversarial training methods, we uncover a recurring failure mode: several approaches improve robust accuracy while degrading uncertainty ranking, leading to poorer selective behavior. To address this, we propose Evidential Adversarial Training (EV-AT), which models uncertainty through a Dirichlet distribution and combines (i) an evidence-based loss promoting clean accuracy and reliable uncertainty with (ii) a robust evidence-alignment loss matching clean and adversarial predictions in log Dirichlet-parameter space. Extensive experiments show that EV-AT shifts the Pareto frontier of robustness-uncertainty trade-offs beyond prior state-of-the-art adversarial training methods. Our source code is publicly available at https://github.com/NicolasSournac/Robustness_Meets_Uncertainty.EV-AT.

Nicolas Sournac, Ahmed Baha Ben Jmaa, Bertrand Braeckeveldt

Multitel Research & Innovation Center, Artificial Intelligence Department, Belgium · TRAIL – Trusted AI Labs, Belgium

Adversarial Training Evidential Deep Learning Uncertainty Quantification Selective Prediction Neural Network Robustness Adversarial Robustness

Jul 2, 2026

Efficient Waste Sorting for Circular Economy: A Confidence-guided comparison between One-Vs-All and One-Vs-Rest Classification Strategies with Human-in-the-Loop for Automated Waste Sorting

The complexity of waste disposal regulations across European countries poses significant challenges for the residents and hinders the transition to a Circular Economy. In Germany, the proper sorting and disposal of household waste remains challenging across municipalities. Consequently, substantially reducing incorrectly disposed waste is vital for improving waste management and advancing the Circular Economy. AI-based waste sorting solutions can support residents through user-friendly tools, such as mobile applications, that guide proper waste disposal. To be effective in supporting the Circular Economy, however, these solutions must be configurable to reflect the specific waste sorting scheme of individual municipalities in Germany. In the scope of this work, an evaluation and analysis are performed of two prominent classification strategies: OvA and OvR. The research uses a dataset constructed in alignment with the waste categories and sorting scheme of the city of Goslar in Germany. Moreover, this work aims to extend beyond the overall performance by examining the behavior of OvA and OvR classification strategies in identifying samples likely to be misclassified. These classification strategies are compared by applying varying confidence thresholds to identify uncertain samples for subsequent human review. This evaluation aims to balance the number of misclassifications against the human effort required for data annotation.

Mohammed Fahad Ali, Dominique Briechle, Marit Briechle-Mathiszig +2

Institute for Software and Systems Engineering Clausthal University of Technology Germany

Selective Prediction Multiclass Classification

Jul 2, 2026

Beyond Supervised Clarification: Input Rewriting with LLMs for Dialogue Discourse Parsing

Rewriting inputs to improve frozen downstream models has become a common strategy in modern NLP pipelines. Prior work on incremental dialogue discourse parsing (DDP) shows that supervised clarification models can rewrite fragmentary or underspecified utterances, such as resolving ellipsis or references, to improve parsing accuracy. In this work, we revisit this idea under realistic deployment conditions, where no clarification supervision is available and the clarifier must rely on zero-shot prompting or feedback from a frozen parser. Across three Segmented Discourse Representation Theory (SDRT) datasets and multiple parsers, we find that last-utterance clarification is far less reliable than suggested by supervised settings. Parser-agnostic rewriting often introduces more regressions than repairs, as edits that enable fixes also disrupt discourse cues relied upon by the parser. A best-of-8 rewriting analysis further reveals a practical ceiling: a large fraction of errors are not repairable through input rewriting alone. A parser-aware clarifier trained with GRPO reduces regressions by up to 37% by learning conservative abstention, yet still fails to produce selectivity-aware clarifications that consistently improve parsing. Together, these findings recast clarification as a selective intervention problem. We identify rewritability prediction, deciding whether an utterance is repairable before intervention, as the key missing capability for input-side optimization of frozen discourse parsers, and a critical direction for improving agentic pipelines more broadly.

Yiming Liu, Ziyue Zhang, Zhichao Xu +4

University of Oklahoma · University of Utah · Lawrence Berkeley National Laboratory +1

Selective Prediction LLM Prompting

Jul 1, 2026

Evaluating Large Language Model Raters for German Open-Response Clinical Questions: A Physician-Annotated Benchmark Study of Agreement, Evaluator Bias, and Abstention

Background: Expert-annotated benchmarks for non-English open-response clinical questions are scarce. LLM-as-a-judge systems may scale evaluation but require validation. Objective: To introduce MedQADE, a standardized German open-response clinical benchmark with physician reference annotations, and evaluate LLM-as-a-judge alignment, self- and intra-family bias, and abstention. Methods: The benchmark contains 3,800 question-answer sets with answers from five student LLMs and annotations from 10 physicians. All 10 rated the 200-question core; two primary raters assessed each of 3,600 extension questions, with the tenth resolving disagreements. Nine LLM evaluators assessed all sets. We assessed physician reliability, student-model accuracy, evaluator alignment, bias, and abstention. Results: Physicians showed moderate-to-substantial agreement on answer correctness (unweighted mean pairwise Cohen's kappa = 0.612) but limited agreement on question difficulty (Krippendorff's alpha = 0.208 using squared numeric-score distances). Student-model accuracy was 17.8%-66.0% and generally decreased with physician-rated difficulty. Gemini 3 Flash approached the leave-one-out physician reference (kappa = 0.694 vs 0.709). Four of five models rated their own responses more favorably than out-of-family evaluators; five of six intra-family comparisons were positive. Physician abstention increased with perceived difficulty. Seven of nine LLM evaluators abstained in no more than 0.51% of evaluations; the two strongest evaluators assigned definitive labels to every response. Conclusions: Strong LLM evaluators approached physician agreement, but evaluator bias and low observed abstention warrant physician validation and further assessment of selective deferral before fully automated evaluation. These results do not establish clinical safety.

William Philipp, Finn Fassbender, Daniel Fister +12

Section for Clinical Research-IT, Institute of Medical Biometry and Statistics, University of Luebeck, Luebeck, Germany · Medical Faculty, University of Tübingen, Tübingen, Germany · German Medical Students’ Association (bvmd), Berlin, Germany +9

Multilingual Language Model Evaluation LLM-as-a-Judge Selective Prediction Clinical QA Language Model Bias Evaluation Clinical Language Model Evaluation

Jun 30, 2026

Uncertainty-Aware Last-Layer Adaptation of RETFound for Referable Diabetic Retinopathy Screening Under Dataset Shift

This paper presents a safety-centered empirical evaluation of uncertainty-aware last-layer adaptation for referable diabetic retinopathy screening using RETFound, a self-supervised vision-transformer retinal foundation model used here as a frozen feature encoder, and the public APTOS 2019 and DDR diabetic retinopathy fundus image datasets. We compare a cached-feature softmax head, post-hoc temperature scaling, variational Bayesian last-layer heads, a diagonal Laplace last-layer approximation, and an SNGP-style cached-feature head. On APTOS, uncertainty-aware operating points improved sensitivity and selective-referral behavior. The strongest APTOS selective-referral result deferred approximately 20 percent of cases and reduced accepted-case false negatives to zero while preserving high accepted-case specificity. However, threshold tuning also reduced false negatives at high false-positive cost, so false-negative reduction alone was not unique to Bayesian modeling. On DDR, native Bayesian heads qualitatively reproduced the APTOS direction but with weaker tradeoffs, while the APTOS-trained SNGP checkpoint transferred poorly and failed to provide useful external selective-referral behavior. These results highlight the value of safety-centered evaluation beyond aggregate accuracy: uncertainty-aware last-layer heads can improve internal safety-oriented operating points, but trustworthy retinal screening claims require explicit safety-coverage evaluation and second-dataset validation under shift.

Karim Mardhani

University of Colorado Boulder Boulder, CO, USA

Bayesian Neural Networks Distribution Shift Robustness Selective Prediction Diabetic Retinopathy Grading Vision Foundation Model Adaptation

Jun 30, 2026

Teaching LLMs to Recommend and Defer in Underrepresented Epilepsy Care

Specialist epilepsy expertise is scarce in resource-constrained settings. Clinical decision-support systems must adapt to local prescribing practices and recognize when specialist review is needed. We study pediatric epilepsy care in Uganda, predicting anti-seizure medication regimens from longitudinal clinic notes. General-purpose language models achieve non-trivial agreement with physician prescriptions, but neurologists' review reveals Western prescribing defaults that do not account for local practices. We introduce MANANA, a non-parametric prompt-learning framework that learns local prescribing guidance from a small patient-level training set. MANANA turns prescription errors into auditable prompt memory, with single-agent and multi-agent variants, and improves over classical ML models, direct LLM prompting, and prompt-optimization baselines across two independently collected Ugandan cohorts. The learned prompt trajectory also provides a basis for estimating uncertainty. Bayesian prompt averaging (BPA) combines predictions across this trajectory to produce prescription likelihoods and a deferral signal. Using the same MANANA-Multi trajectory, BPA improves top-1 physician-regimen agreement from 66% to 70% on Cohort A and from 73% to 75% on Cohort B while preserving top-3 coverage. On Cohort B, its most confident half of cases achieves 95% precision, and its most confident quarter achieves 99% precision, supporting deferral of lower-confidence cases for specialist review. These results suggest a path toward locally adapted clinical LLM systems that learn from limited site-specific data and focus scarce specialist attention on uncertain cases.

Shreyas Rajesh, Kartik Sharma, Tonmoy Monsoor +8

Electrical and Computer Engineering, University of California, Los Angeles · Makerere University · St. Francis Hospital Nsambya +1

Prompt Learning Selective Prediction LLM Decision-Making Longitudinal EHR Modeling Medical LLMs Medication Recommendation

Jun 29, 2026

Know Before You Fetch: Calibrated Retrieval-Budget Allocation for Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) typically retrieves a fixed number of passages for every query. This is wasteful when the reader already knows the answer, and it can be harmful when irrelevant or partially relevant passages distract the reader. We formulate adaptive RAG as calibrated retrieval-budget allocation: given a query, decide whether to answer closed-book, retrieve a compact context (k=1), retrieve a full context (k=5), or abstain. The contribution is a probability interface rather than a new raw uncertainty signal. We calibrate sequence log-probability and prefix-logit uncertainty signals into probabilities of correctness, then use these probabilities for graded context selection, selective abstention, and explicit latency/token trade-offs. Across core QA experiments on TriviaQA, Natural Questions, and MS MARCO, with auxiliary PopQA motivation and Qwen/Llama family checks, diagnostic out-of-fold calibration improves probability quality dramatically: for sequence log-probability, ECE drops from 0.275 to 0.062 on TriviaQA, 0.643 to 0.009 on NQ, and 0.711 to 0.031 on MS MARCO. Graded retrieval improves full-context and passage-budget frontiers for both our signal and TARG-style prefix entropy/margin, while retrieval-call AUC remains essentially tied with binary gating because k=1 is still a retrieval call. Held-out train/validation/test threshold experiments report deployable operating points. At matched-accuracy frontier operating points, a measured cost model reveals that gating is not universally faster: it increases latency by about 27% on Qwen3-8B but saves about 8% on Qwen3-32B. These results support a nuanced view of adaptive RAG: calibrated confidence is best understood as a reusable interface for allocating retrieval budget under task and system constraints.

Zhe Dong, Fang Qin, Manish Shah +1

University of Maine at Presque Isle · Stanford University · Independent Researcher

Retrieval-Augmented Generation Selective Prediction Adaptive RAG Adaptive Retrieval Language Model Calibration

Jun 28, 2026

Budgeted Act-or-Defer Multi-Agent LLM Deliberation with Local Reliability Bounds

Multi-agent deliberation among LLMs can improve reasoning, but deployment requires deciding when the current answer is reliable enough to act on and when it should be escalated to human review. We formulate this as budgeted act-or-defer decision making. At each round, the system maps the debate prefix to a low-dimensional state, computes a

k

-nearest-neighbor lower confidence bound on state-conditional correctness using calibration data, and acts only when the bound exceeds a user-specified reliability threshold. The certificate controls wrong actions through the decomposition

β= δ+ α+ \varepsilon_{\mathrm{act}}

, separating calibration failure, residual action risk, and representation gap. The guarantee is conditional, not distribution-free: it relies on a valid local bias envelope and an action-region representation-gap bound, and each assumption is paired with falsification-style diagnostics. Because the same absolute wrong-action budget has different meanings across tasks of different difficulty, we set budgets relative to each task's final-round error using training data only, and evaluate safety by normalized budget usage

\mathrm{WA}/β

. On six benchmarks against nine baselines, the method uses 9--12% of the pre-declared budget on activated datasets, reaching up to 84% automation and 96% acted-on accuracy; on stress-test datasets, it defers rather than forcing unreliable automation. Rather than relying on per-task post-hoc threshold search, the method prospectively converts a user-declared wrong-action budget into an auditable act-or-defer operating point before deployment, under explicitly stated assumptions.

Mengdie Flora Wang, Haochen Xie, Guanghui Wang +2

1AWS Generative AI Innovation Center, USA · General Motors (GM), USA

AI Agent Reliability Multi-Agent LLM Systems Selective Prediction LLM Decision-Making LLM Agent Reliability Multi-Agent Deliberation

Jun 27, 2026

HKVLM: Faithful Query--Region Binding for Frozen-Detector Visual Grounding

Visual grounding often fails even when the target object is present in the proposal pool, because the language-side referent is bound to the wrong region. We study this binding failure under frozen perception and ask whether an explicit query--region alignment hook, together with a perception-grounded abstention mechanism, can improve faithful grounding without retraining the detector or the vision-language backbone. HKVLM freezes a language-aligned open-vocabulary detector for localization and learns a lightweight hook that maps referential query embeddings to detector proposals in a shared space; a verifier abstains when no region sufficiently supports the query. We prove an exact proposal-level diagnostic decomposition,

(1-\mathrm{SeeErr})(1-\mathrm{SayErr})

, separating proposal-coverage failures from conditional binding failures, and a monotonicity result that characterizes the faithfulness--recall trade-off induced by abstention. Across RefCOCO, RefCOCO+, RefCOCOg, and POPE, HKVLM improves over untrained and trained matched-perception binding controls and substantially reduces hallucination through abstention. Strong coordinate-decoding and end-to-end fine-tuned baselines remain much higher in raw grounding accuracy, and a reasoning-stress set exposes binding as the main current bottleneck. We therefore present HKVLM as a diagnostic and mechanism-level study of query--region binding under frozen perception, not as an absolute localization leader.

Bo Ma

Auckland University of Technology

Selective Prediction Cross-Modal Alignment Object Hallucination in VLMs Vision-Language Grounding

Jun 25, 2026

Risk-Aware Selective Multimodal Driver Monitoring with Driver-State World Modeling

Continuous driver monitoring in automated vehicles requires low-latency inference while avoiding unsafe decisions under uncertain driver states. Large vision-language models provide broad multimodal priors, but their latency and limited reliability in this setting make them unsuitable as always-on in-cabin monitors. We propose a cost-aware selective inference framework for deployable multimodal driver monitoring. The core system is a lightweight RGB-physiological student that combines in-cabin visual observations with window-level HR/EDA signals, and a learned gate that decides when to accept the fast prediction or abstain for safety intervention. Additional controls show that the learned scores contain sample-level information beyond scenario priors, while exact physiological synchronization remains a limitation. To incorporate predictive evidence, we further study a compact driver-state world modeling module that rolls out latent driver-state features and estimates future fast-model errors and counterfactual system-level action costs. On scenario-induced driver-demand recognition, the RGB-physiological student improves over RGB-only and physiology-only baselines, reaching 0.7440 Macro-F1 and 0.9099 balanced accuracy with 11.39M parameters and 3.08ms inference latency. Cost-aware selective inference reduces unsafe false negatives from 17.37% under always-fast inference to approximately 5% across seeds, while maintaining deployment-level latency. While driver-state world modeling offers valuable predictive signals, worst-group evaluations highlight persistent operating-point calibration drift. Ultimately, reliable edge driver monitoring requires advancing not only perception backbones, but also risk-aware selective control and group-robust calibration.

Daosheng Qiu, Haozhuang Chi, Hao Su +4

Hubei University, Wuhan, China · Nanyang Technological University, Singapore · Osaka University, Osaka, Japan

Selective Prediction World Models Cost-Aware Inference Driver Monitoring Multimodal Sensor Fusion

Jun 23, 2026

Beyond Logprobs: A Multi-Signal Confidence Engine for LLM-Based Document Field Extraction

In high-stakes document processing pipelines, including financial reconciliation, compliance verification, and procurement automation, an LLM extraction that is silently wrong is more dangerous than one that is visibly absent. The central challenge is not extraction accuracy alone but reliable confidence estimation: knowing, field by field, whether an extraction can be trusted for automation or deferred to human review. Token-level log-probabilities, verbalized confidence, and multi-sample self-consistency all collapse toward all-positive behaviour at practical thresholds, offering no reliable separation between trustworthy and untrustworthy extractions. We present ExtractConf, a cross-domain, field-agnostic confidence engine that grounds confidence estimation in two structurally different readings of the same document. A field-guided Hunter call extracts each field under schema-slot completion pressure; a document-guided Mapper call scans holistically and surfaces values grounded in document content. This asymmetry yields different failure modes: Hunter hallucinates values for absent fields, while Mapper misses visually non-salient ones. Their disagreement is independently informative. ExtractConf fuses cross-call disagreement, LLM-internal uncertainty, OCR, image quality, and spatial layout into a classifier requiring no domain-specific rules or retraining. On DocILE (55-field invoices, 26% failure rate), it achieves 0.928 ROC AUC and reduces selective prediction risk by 70% over logprob-mean. At 80% coverage, accuracy reaches 99.1%, enabling a practical human-in-the-loop workflow. Zero-shot transfer to CORD receipts achieves 0.858 AUC; lightweight Lasso recalibration reduces ECE by 89% and Brier by 43%, confirming the signals generalise across document domains.

Nitesh Kumar

1Perfios Software Solutions Pvt. Ltd.

Selective Prediction Document Information Extraction LLM Reliability LLM Uncertainty Estimation

Jun 22, 2026

Selective Time Series Forecasting via Metalearning

Deep learning methods have achieved state-of-the-art in time series forecasting, yet their accuracy varies considerably across samples, as some instances remain inherently difficult to predict. Reject option mechanisms, which allow models to abstain from high-risk predictions, are well established in classification and regression but underexplored in forecasting. Existing abstention strategies typically rely on proxies, such as the width of the prediction interval or learned confidence scores derived from forecasts. However, these approaches are inherently tied to the training domain, limiting their ability to generalize. We propose a selective forecasting framework that addresses this limitation by modeling the empirical percentile of forecasting errors, that is, a scale-invariant statistic, based on structural characteristics extracted from recent lags via metalearning. By decoupling the rejection decision from the forecast itself and grounding it in domain-agnostic features, the framework enables effective abstention transfer across heterogeneous time series. Experiments in both in-domain and transfer learning settings show that rejecting samples predicted as challenging consistently improves forecasting accuracy across coverage levels.

Ricardo Inácio, Vitor Cerqueira, Marília Barandas +1

Faculdade de Engenharia da Universidade do Porto, Porto, Portugal · University of Coimbra, Portugal · Fraunhofer Portugal AICOS, Portugal

Selective Prediction Time Series Forecasting

Jun 21, 2026

Interpretable Uncertainty Routing Separating Emotion Ambiguity from Distribution Shift in Facial Expression Recognition

Facial expression recognition (FER) is inherently ambiguous: human annotators frequently disagree, and models deployed in real environments face distribution shift. Crucially, these two conditions demand different downstream actions, as ambiguous in-distribution faces should be reported with their ambiguity whereas out-of-distribution inputs should be rejected. However, a single uncertainty score conflates the two. In this study, uncertainty decomposition into aleatoric and epistemic components for FER is investigated, and Uncertainty-Aware Routing (UAR), an inference-time routing mechanism that exploits the separation, is introduced. Specifically, aleatoric and epistemic uncertainties are obtained from a Deep Ensemble of fully fine-tuned DINOv2 models and are each validated against an independent external signal: aleatoric against human annotator disagreement, and epistemic against distribution shift induced by image corruptions. The proposed dual-validation protocol reveals that aleatoric recovers annotator disagreement with Spearman correlation 0.66 (95% CI: 0.64-0.68), and epistemic detects corruption-induced shifts, achieving average AUROC of 0.699 at the highest corruption severity. UAR retains approximately 1.8 times more ambiguous in-distribution faces than single-uncertainty routing at a matched out-of-distribution rejection rate. A strong label-distribution-learning baseline achieves comparable disagreement recovery but cannot separate ambiguity from shift and therefore cannot route, establishing that the value of decomposition lies in the separation enabling interpretable and differentiated action selection.

Keito Inoshita, Takato Ueno

Faculty of Business and Commerce, Kansai University, Suita, Japan · Data Science and AI Innovation Research Promotion Center, Shiga University, Hikone, Japan · Graduate School of Data Science, Shiga University, Hikone, Japan

Uncertainty Quantification Selective Prediction Facial Expression Recognition Aleatoric Uncertainty OOD Detection Uncertainty Decomposition+1

Jun 20, 2026

The Score Granularity Gap in Black-Box LLM Classification: A Comparative Study of Confidence Constructions

Large language models (LLMs) are increasingly deployed as black-box classifiers in pipelines that automate confident decisions and route uncertain ones to human review. Such selective prediction needs a confidence score that an operator can threshold at a chosen risk level. Prior work asks whether LLM confidence is well calibrated or well ranked; we ask a complementary, deployment-oriented question that has been largely overlooked: at what resolution can the score be thresholded? We call the answer the score granularity gap. Through a controlled comparison of seven ways to build a confidence score, from a single verbalized number, to token probabilities, to querying the model many times and combining the answers, across 25 model-dataset pairs (9 LLMs, 3 benchmarks), we find that single-shot verbalized confidence, once correctly converted to a class probability, ranks cases surprisingly well, yet takes only a handful of distinct values. It therefore offers an operator only a few coarse thresholds, no matter how well it ranks. We show which constructions widen this gap, at what inference cost, and with what effect on ranking, notably that multi-query aggregation helps weak models but can degrade already-strong ones. We translate these trade-offs into concrete deployment guidance.

Ao Sun, Tian Sun, Jiaxing Geng

LLM Evaluation Selective Prediction Confidence Estimation in Language Models Language Model Calibration LLM Uncertainty Estimation

Jun 19, 2026

Rejections Based on Predictive Uncertainty Enable Reliable Routine Soil Spectroscopy

Soil properties relevant to agricultural and environmental applications are conventionally measured using elaborate laboratory methods involving physical and chemical processing. While highly accurate, these conventional methods are costly and time-consuming. In contrast, optical spectroscopy paired with machine learning enables rapid and cost-effective predictions of multiple soil properties. However, spectroscopic modelling is often considered unreliable, as the predictive accuracy varies between soil properties and individual samples. To balance this trade-off between cost and reliability, we introduce reject-to-remeasure: an AI-based measurement framework that combines probabilistic modelling with uncertainty-guided rejection. In this framework, soil samples are first analysed using spectroscopy, after which predictions are rejected if their predictive uncertainty exceeds predefined quality constraints. Rejected samples are subsequently remeasured using conventional laboratory procedures. On a regional visible-near-infrared spectral soil library from Québec, we demonstrate that reject-to-remeasure with modern foundation models (TabPFNv2.5 and TabICLv2) can facilitate the integration of optical spectroscopy into routine laboratory workflows while meeting user-defined accuracy requirements and reducing measurement costs.

Jonas Schmidinger, Robin Gebbers, Marc-Olivier Gasser +3

Joint Lab Artificial Intelligence and Data Science, Osnabrück University, Osnabrück, Germany. · Department of Agromechatronics, Leibniz Institute for Agricultural Engineering and Bioeconomy (ATB), Potsdam, Germany. · Research and Development Institute for the Agri-environment (IRDA), Qu´ebec City, Canada. +1

Uncertainty Quantification Selective Prediction

Jun 18, 2026

GroundControl: Anticipating Navigation Failures in Vision-Language Agents via Trajectory-Consistent Uncertainty Estimates

Vision-language navigation agents achieve competitive average success on benchmark tasks, yet failures often arise through predictable trajectory-level breakdowns such as oscillation, stagnation, or inefficient detours. Reliable deployment, therefore, requires uncertainty signals that anticipate emerging failure dynamics during execution rather than reflect only instantaneous action entropy. We introduce GroundControl, a trajectory-consistent uncertainty estimator defined as statistical deviation from nominal goal-directed distance-to-goal dynamics aggregated over an episode. GroundControl models distance evolution using a constant-velocity Kalman filter and combines normalized innovation statistics with complementary trajectory features capturing progress, monotonicity, path efficiency, and oscillatory behavior. The resulting uncertainty score reflects geometric and temporal inconsistency in navigation behavior rather than local prediction dispersion. To evaluate uncertainty quality independently of task success, we formalize Selective Risk--Coverage Navigation (SRCN), a protocol that measures how effectively an uncertainty score ranks episodes by failure or inefficiency using risk--coverage curves and AURC / E-AURC summaries. Across five EB-Navigation splits (

N=300

episodes), trajectory-consistent uncertainty achieves near-oracle ordering under success-based selective risk, with weighted-average

\mathrm{E\text{-}AURC}_{\mathrm{SR}}=0.0024

for the GPT-4o model, substantially outperforming entropy-, conformal-, and heuristic baselines. Under SPL-based selective evaluation, GroundControl consistently achieves the lowest AURC and E-AURC across models and navigation splits. These results show that modeling deviation from goal-directed dynamics provides an interpretable and robust signal for anticipating navigation failures in vision-language agents.

Nastaran Darabi, Divake Kumar, Sina Tayebati +2

University of Illinois at Chicago (UIC)

Uncertainty Estimation for VLA Models Selective Prediction Vision-Language Navigation Agent Trajectory Analysis

Jun 18, 2026

Confidence-Aware Automated Assessment of Student-Drawn Scientific Models

Student-generated drawings are widely used in science education to assess learners' conceptual understanding in modeling-based tasks aligned with the Next Generation Science Standards (NGSS). However, scoring such drawings requires expert human judgment to interpret complex visual representations, making large-scale assessment costly to implement and sustain in classroom settings. In this work, we study automated scoring of student-generated scientific drawings using a vision-based model. We evaluate a Vision Transformer (ViT) with parameter-efficient adaptation and propose a confidence-aware scoring framework that derives response-level confidence from test-time predictive distributions. This confidence signal enables selective automation by scoring high-confidence responses automatically while deferring uncertain cases for human review. Experiments on six NGSS-aligned middle school assessment items show that the proposed approach improves scoring reliability while supporting a practical trade-off between automated coverage and scoring risk, highlighting the value of confidence-aware methods for trustworthy educational assessment.

Luyang Fang, Yingchuan Zhang, Jongchan Park +3

AI4STEM Education Center, Athens, GA, USA · Department of Statistics, University of Georgia, Athens, GA, USA

Selective Prediction Vision Transformer Educational Technology Science Education Automated Grading

Jun 15, 2026

Abstention-Aware Personalized Object Rearrangement via Uncertainty-Guided LLM Assistance

Robotic assistance in household environments requires not only predicting where objects should be placed, but also reasoning about when objects should not be placed at all. Existing approaches to personalized object rearrangement primarily focus on placement decisions under the assumption of clean observations and complete actionability, limiting their applicability in realistic, cluttered, and partially erroneous settings. In this paper, we introduce APOLLO, a hybrid framework for abstention-aware personalized object rearrangement that combines a lightweight, personalized embedding model (PEM) with selective large language model (LLM) assistance. PEM is trained for each user-environment pair using a small number of demonstrations, operates entirely on CPU, and produces uncertainty estimates, which are used to selectively invoke LLM-based reasoning only for ambiguous decisions, balancing efficiency, privacy, and reasoning capability. To evaluate this formulation beyond existing benchmarks, we introduce APOR, a synthetic, LLM-generated dataset that captures room-level, multi-furniture environments, diverse organizational profiles, explicit abstention behavior, and noisy partial scene context. Extensive experiments on both PARSEC and APOR provide initial evidence that APOLLO improves over prior LLM-based baselines in controlled benchmark settings while substantially reducing LLM usage. Code is available at https://github.com/PaInt-Lab/APOLLO.

Sam Collin, Ali Ayub

Concordia University, Montreal, Quebec H3G 1M8, Canada

Selective Prediction Robot Task Planning Robot Manipulation Benchmarks

Jun 15, 2026

Look Again Before You Abstain:Budgeted Conformal Evidence Acquisition for Reliable Vision-Language Model

Large vision-language models (LVLMs) hallucinate: they assert visual details that the image does not support. A principled remedy is selective prediction with a distribution-free guarantee-verify each claim and abstain when the claim is not grounded, so that the hallucination rate among asserted claims is provably bounded. We show, however, that this guarantee is bought at a brutal price: to keep the hallucination rate below

5\%

on a balanced object-existence benchmark, a state-of-the-art conformal filter must abstain on more than

80\%

of claims. We argue that abstention is wasteful when more visual evidence is cheaply available, and introduce Budgeted Conformal Evidence Acquisition (BCEA), which replaces the binary answer/abstain decision with a three-way choice: answer, abstain, or acquire additional visual evidence by re-examining the image (zooming, cropping, or applying a claim-specific intervention) under a bounded compute budget. We make two observations. First, acquisition that is plugged naively into a calibrated filter breaks the statistical guarantee -- realized risk overshoots the target by up to

17

points -- because the acquisition step destroys the exchangeability that conformal calibration relies on. Second, folding the entire acquisition policy into the score function and re-calibrating on post-acquisition scores restores the finite-sample guarantee while still recovering coverage. BCEA further uses structured, claim-type-specific interventions. Across the POPE benchmark and COCO-constructed existence and spatial-relation claims, on four open VLMs, BCEA controls the hallucination rate at the target level and consistently improves coverage over a guaranteed-abstention baseline.

Jian Xu, Delu Zeng, John Paisley +1

RIKEN iTHEMS · RIKEN AIP · South China University of Technology +1

VLM Hallucination Mitigation Active Perception Hallucination Detection in VLMs Selective Prediction Object Hallucination in VLMs Conformal Prediction+3

Jun 14, 2026

Adapt or Calibrate? How Local Labels Buy Certified Coverage in Medical VQA

An answer from a vision-language model (VLM) to a medical image question can be accepted without review only under a threshold bounding the error of accepted answers, and certifying that bound costs local labels. We ask what such labels can certify for nine confidence estimators on five general-purpose open-weight VLMs and three medical VQA benchmarks under Learn-then-Test, with the question as the exchangeable unit. Estimators trained on natural images transfer poorly: the best pooled certificate covers 11.5% of SLAKE answers at a 20% error tolerance and nothing on PATH-VQA. With 1,000 labeled SLAKE questions, adapting a probe on half of them raises pooled certified coverage from 6.8% to 37.6% (0.0% to 30.6% with the image as the unit), above the best threshold-only estimator (11.3%). On PATH-VQA, adaptation certifies 11.4% with 2,500 labels; thresholds alone certify nothing. Yet for strong single models, small budgets are better spent on the threshold. A question-only classifier recovers much of adaptation's ranking gain but certifies far less. Neither procedure yields a pooled certificate at 10%, and nothing is certified at 5%. A blank image removes 61% of correct answers, yet on GMAI-MMBench no trained probe is less confident on answers unchanged by image replacement.

Reza Khanmohammadi, Kundan Thind, Mohammad M. Ghassemi

Michigan State University East Lansing, MI, USA · Henry Ford Health Detroit, MI, USA

VLM Evaluation Confidence Estimation for VLMs Selective Prediction Medical VQA Language Model Calibration Medical VLMs

Jun 14, 2026

When Correct Edges Cannot Be Verified: A Provenance Gap in Incomplete KGQA and a Provenance-Favoring Completion Policy

Incomplete Knowledge Graph Question Answering (IKGQA) requires completing missing edges to continue reasoning. A growing line of work verifies completed edges against retrieved text, treating textual support as a proxy for edge quality. We ask a question that, to our knowledge, has not been systematically tested: does textual verifiability actually track correctness? Exploiting the gold deleted triples provided by the standard random-deletion protocol, we measure both. The finding is counterintuitive: among gold-correct completed edges, 76-96% have no supporting passage even under exhaustive retrieval, robustly across deletion rates (20%/40%), datasets (CWQ/WebQSP), and relation types (structural, commonsense, long-tail). Most Freebase-style facts simply do not occur as head-tail co-mentions in text. Textual faithfulness therefore measures provenance, not correctness -- separated by a paradigm-level gap no in-corpus retrieval closes. This reframes edge completion. Since most completed edges -- correct or not -- are causally redundant for the answer (95-97% of correct answers do not depend on any unsupported edge), the central question shifts from "is the edge correct?" to "admit or abstain under provenance uncertainty?" Within this framing we present TGComplete, a provenance-favoring admission policy that retrieves evidence at a reasoning breakpoint, verifies a candidate through a lightweight loop, and abstains when support is absent. Against the generate-to-complete baseline GoG, it attains higher edge precision against gold (15-21% vs 3-14%), with no statistically detectable EM loss and 3.1-7.4 times higher strict faithfulness of admitted edges -- at the cost of lower recall. We position TGComplete not as uniformly better, but as a principled point on a precision/provenance-recall trade-off, appropriate when auditability matters.

Yongqi Kang, Yu Fu, Yong Zhao

Sichuan University

Data Provenance Selective Prediction Knowledge Graph Question Answering KG Completion

Jun 14, 2026

Mitigating Visual Hallucinations in Multimodal Systems through Retrieval-Augmented Reliability-Aware Inference

Multimodal large language models (MLLMs) have demonstrated strong capabilities in vision-language understanding and natural-language response generation. However, these systems can still produce overconfident predictions and hallucination-like outputs, particularly when the visual evidence is weak, ambiguous, or semantically inconsistent. Most existing approaches focus on improving multimodal representation alignment or retrieval-augmented generation, while providing limited mechanisms to quantify instance-level prediction reliability or identify incorrect visual outputs. This work proposes a retrieval-augmented reliability-aware inference framework for trustworthy multimodal visual understanding. The proposed framework constructs an external visual evidence database using pretrained visual embeddings and nearest-neighbor retrieval over normalized feature representations. Retrieved evidence is used to estimate prediction trustworthiness through multiple reliability indicators, including similarity strength, class-support agreement, evidence margin, entropy-based uncertainty, and an aggregate reliability score. Based on these signals, a decision gate determines whether the system should accept the prediction, answer with caution, or abstain/fallback when evidence is insufficient. A multimodal response-generation layer then produces a final user-facing response conditioned on the reliability decision. Experiments on ImageNet-100 demonstrate that the proposed reliability-aware framework improves accepted prediction accuracy from 85.84% to 88.88% at 89.04% coverage. The hallucination-like accepted wrong-answer rate is reduced from 14.16% to 11.12%. These results show that integrating retrieval evidence, reliability estimation, and selective decision gating can improve calibration and reduce overconfident visual errors without retraining large multimodal models.

Pratheswaran Hariharan, Haiping Xu, Donghui Yan

Computer and Information Science University of Massachusetts, Dartmouth, MA · Mathematics and Data Science University of Massachusetts, Dartmouth, MA

Probability Calibration Selective Prediction VLM Hallucination Mitigation Image Classification Multimodal Understanding

Jun 13, 2026

False Sense of Safety in Selective Signal Classification: Auditing Bound Tightness and Exchangeability for Risk Control

Selective prediction with distribution-free risk control promises that, with confidence 1-delta over the calibration draw, the error rate of accepted inputs stays below a user budget alpha. We audit this promise on signal-domain detectors -- machine anomalous-sound detection (ASD) and AI-generated-image forensics -- for four calibration rules: uncertified empirical thresholding (NAIVE) and certified Hoeffding, Clopper-Pearson (CP), and betting (WSR) upper confidence bounds. We report three findings. (i) NAIVE thresholding, common in practice, exceeds its declared budget in 49-73% of synthetic trials (n=200 calibration points) and in up to 68% of real-data splits: a false sense of safety rather than a broken theorem, since the rule never had a certificate. (ii) Tightness matters: CP and WSR certify substantial coverage where Hoeffding certifies none, with zero observed budget overruns under exchangeable splits. (iii) Under grouped deployment (unseen machine types or generators), certified rules overrun in 9-30% of trials -- far above delta -- showing the failure lies in the broken exchangeability premise, not in the bounds; a conservative per-group threshold restores validity at a severe coverage cost.

Jingwen Zhou, Mingzhe Wang

Xidian University, Xi’an, China

Selective Prediction Anomaly Detection

Jun 11, 2026

Capability Minimization as a Safety Primitive: Risk-Aware Causal Gating for Least-Privilege LLM Agents

Modern decision systems increasingly rely on learned components whose outputs may be confident yet wrong, exposing downstream actions to costly errors. We introduce Risk-Aware Causal Gating (RACG), a framework that decides whether to act on, defer, or abstain from a model's prediction by combining causal effect estimation with calibrated risk control. RACG models the causal pathway from candidate actions to outcomes and gates each decision according to an estimated counterfactual risk rather than raw predictive confidence. To make gating reliable, we derive distribution-free bounds on the probability of acting under high-risk conditions and show how these bounds translate into operating thresholds that satisfy user-specified safety constraints. We further propose an adaptive gating policy that adjusts to distribution shift by monitoring discrepancies between predicted and realized outcomes, tightening the gate when causal assumptions appear violated. Across simulated interventions and real-world decision benchmarks, RACG reduces high-cost errors substantially while preserving most of the utility of an ungated policy, and it outperforms confidence-based and selective-prediction baselines at matched abstention rates. Our results indicate that explicitly separating causal risk from predictive uncertainty yields decision systems that are both safer and more transparent, offering a principled mechanism for trustworthy automation in high-stakes settings.

Laxmipriya Ganesh Iyer, Rahul Suresh Babu

Independent Researcher

Selective Prediction Causal Inference LLM Agent Safety Decision-Making under Uncertainty

Jun 10, 2026

Towards Provably Fair Machine Learning: Bayesian Approaches For Consistent and Transparent Predictions

ML classifiers deployed in high-stakes domains produce predictions whose quality varies systematically across subgroups. For granular subgroups defined by intersections of multiple features, predictions are often inconsistent with the observed data: the model's outputs contradict the evidence available for that subgroup. This problem is exacerbated by regularisation, which improves aggregate performance by collapsing small subgroups into larger groups, disproportionately affecting demographic minorities. We define two requirements for consistent prediction: determinism (identical individuals receive identical predictions) and statistical consistency (we cannot reject, at significance level alpha, the hypothesis that the predictions for a subgroup were drawn from the Bayesian optimal target distribution inferred for that subgroup). From these requirements we derive the Fair Bayesian classifier, which enforces both across every group and subgroup simultaneously and abstains whenever no consistent deterministic prediction is possible. On three benchmark datasets (Adult, COMPAS, and Bank Marketing), standard classifiers produce statistically inconsistent predictions for a substantial proportion of subgroups. Our classifier achieves zero consistency error by construction while exceeding baseline accuracy and multicalibration on every dataset tested. Statistical consistency provides a principled foundation for prediction quality with direct implications for algorithmic fairness. Minority demographics are disproportionately concentrated in small subgroups, precisely where frequentist inference is least reliable; addressing this inference problem is therefore a necessary step toward fair ML. By enforcing Bayesian consistency at the finest resolution the data supports, the our classifier demonstrates that exhaustive subgroup fairness with principled abstention is achievable in practice.

Owen O'Neill, Fintan Costello

University College Dublin, Ireland

Selective Prediction Bayesian Inference Algorithmic Fairness Group Fairness Intersectional Fairness

Jun 8, 2026

Density Ridge Selective Prediction for LLM and VLM Hallucination Detection under Calibration Label Scarcity

Hallucination detection in large language and vision-language models is increasingly framed as selective prediction, where a detector assigns a confidence score and abstains when confidence is low. Unsupervised sampling detectors (Semantic Entropy) avoid labels but plateau in quality, while supervised probes attain stronger in-distribution scores yet degrade sharply when calibration labels are scarce. We recover the response manifold of an LLM as the density ridge of a kernel density estimate built on a six-dimensional kinematic feature map of hidden state generation trajectories. A test generation is scored by the negated Euclidean distance from its projected feature point to the nearest ridge vertex, yielding a low-dimensional geometric skeleton of the stochastic output distribution. We evaluate against Semantic Entropy, topological methods, and log-probability on six QA benchmarks (HaluEval-QA, TriviaQA, GSM8K, POPE, ScienceQA, A-OKVQA) using eight text and vision LLMs in a deliberately label-scarce protocol (

n_{\text{cal}}{=}200

queries,

N{=}5

generations). Our ridge-based score beats on AUROC with 5-20 points gain, while demonstrating tempered degradation under calibration-label scarcity.

Nina I. Shamsi

Northeastern University Boston, United States

Hallucination Detection in VLMs Vision-Language Models Audio-Language Model Hallucination Detection Selective Prediction Large Vision-Language Models LLM Hallucination Detection

Jun 8, 2026

Evidence Acquisition and Stopping via Lattice Distillation

Sequential evidence acquisition requires deciding what to observe and when to stop from partial information. We introduce a complete-record view of policy supervision: each fully observed training instance defines a lattice of evidence subsets, with a stop/query decision at every node. For a modest number of evidence groups, this structure can be enumerated even when individual groups contain rich representations. Our method, Subset Lattice Distillation (SLD), scores subsets with a shared masked predictor, constructs multi-step decision targets by cost-sensitive backward planning, and distills them into an observed-history controller. Uniformly resampled masks train the student across the subset space, while combinatorial planning remains offline. Separating subset scores from acquisition prices allows the predictor to be reused when the policy is replanned for new costs. Our analysis identifies action-margin conditions under which privileged supervision preserves optimal online decisions. On retrospective influenza monitoring, SLD achieves higher phase F1 at lower acquisition cost than both the closest-cost adaptive baselines and the fixed full-evidence model. A geographic and seasonal holdout, price perturbations, and ablation studies provide further evaluation.

Yixuan Zhang, Yang Song, Jiayi Zhang +4

Section of Health Data Science and AI, Department of Public Health, University of Copenhagen, Copenhagen, Denmark · Section of Health Data Science & AI, Department of Public Health, University of Copenhagen, Copenhagen, Denmark · Rutgers University, New Brunswick, NJ, USA +1

Epidemic Forecasting Selective Prediction Bayesian Inference Cost-Aware Inference Bayesian Experimental Design

Jun 7, 2026

A Joint Finite-Sample Certificate for Adaptive Selective Conformal Risk Control

Selective predictors answer on confident inputs and abstain elsewhere; deploying one safely needs a single finite-sample certificate that simultaneously upper-bounds the selected risk, lower-bounds the acceptance probability

\pacc

above a floor

\pmin

, and lower-bounds the deployment utility. This certificate must be valid under adaptive threshold selection from a finite grid of

m

pairs on

\ncert

samples. We give such a certificate for bounded, possibly non-monotone losses by treating the selected risk directly as a ratio rather than through a Hoeffding-style range bound. The construction couples three confidence bounds: a variance-adaptive empirical-Bernstein bound on the ratio risk, a Clopper--Pearson bound on acceptance, and a two-sided closeness bound on utility. Together they lower-bound the certified policy's utility absolutely and to within

2\gammau

of the best over the certified set, both non-vacuous whenever feasible; a regime-scoped third leg matches an external oracle, informative only where the risk margin

\gammar < α

and vacuous at the headline operating points. Relative to the range-only Hoeffding-ratio construction this sharpens the acceptance-floor dependence from

1/\pmin

to

1/\sqrt{\pmin}

, and a closed-form corollary identifies a per-pair regime in which our risk bound dominates a Hoeffding conformal risk control (Hoeffding--CRC) selective bound. Empirically, on ImageNet (three ResNets) and COCO val 2017 panoptic, the certificate opens a

+22

pp certified-acceptance frontier over Hoeffding--CRC and is

{\approx}10{\times}

tighter than a non-vacuous matched-valid baseline; these gains are regime-scoped, not universal, and absent on ADE20K. The certifier runs in

O(\ncert m)

time.

Xiaoli Yu, Jiamiao Liu

School of Cyber Security and Information Law Chongqing University of Posts and Telecommunications Chongqing 400065, China · Department of Information, Xinqiao Hospital Army Medical University (Third Military Medical University) Chongqing 400037, China

Selective Prediction Conformal Risk Control Generalization Bounds