BICR uses blind-image contrastive ranking on frozen LVLM hidden states to train a lightweight probe that penalizes confidence on blacked-out inputs, yielding top calibration and discrimination across five models and multiple tasks at low parameter cost.
hub
Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
25 Pith papers cite this work. Polarity classification is still indexing.
25
Pith papers citing it
abstract
Empowering large language models to accurately express confidence in their answers is essential for trustworthy decision-making. Previous confidence elicitation methods, which primarily rely on white-box access to internal model information or model fine-tuning, have become less suitable for LLMs, especially closed-source commercial APIs. This leads to a growing need to explore the untapped area of black-box approaches for LLM uncertainty estimation. To better break down the problem, we define a systematic framework with three components: prompting strategies for eliciting verbalized confidence, sampling methods for generating multiple responses, and aggregation techniques for computing consistency. We then benchmark these methods on two key tasks-confidence calibration and failure prediction-across five types of datasets (e.g., commonsense and arithmetic reasoning) and five widely-used LLMs including GPT-4 and LLaMA 2 Chat. Our analysis uncovers several key insights: 1) LLMs, when verbalizing their confidence, tend to be overconfident, potentially imitating human patterns of expressing confidence. 2) As model capability scales up, both calibration and failure prediction performance improve. 3) Employing our proposed strategies, such as human-inspired prompts, consistency among multiple responses, and better aggregation strategies can help mitigate this overconfidence from various perspectives. 4) Comparisons with white-box methods indicate that while white-box methods perform better, the gap is narrow, e.g., 0.522 to 0.605 in AUROC. Despite these advancements, none of these techniques consistently outperform others, and all investigated methods struggle in challenging tasks, such as those requiring professional knowledge, indicating significant scope for improvement. We believe this study can serve as a strong baseline and provide insights for eliciting confidence in black-box LLMs.
hub tools
years
2026 25representative citing papers
EquiMem calibrates shared memory in multi-agent debate by computing a game-theoretic equilibrium from agent queries and paths, outperforming heuristics and LLM validators across benchmarks while remaining robust to adversarial agents.
MRI-Eval benchmark shows frontier LLMs scoring 93-97% on MRI MCQs but falling to 37-61% on stem-only questions, with GE scanner operations as the weakest category for all models.
First-token normalized entropy (phi_first) from one greedy decode reaches mean AUROC 0.820 for hallucination detection, matching or exceeding semantic self-consistency (0.793) and surface self-consistency (0.791) across three 7-8B models and two benchmarks.
LLM agents overcommit on non-complete tasks at 41.7% unless given explicit support-state categories, which raise typed deferral accuracy to 91.7%.
MIRROR benchmark shows LLMs universally fail at compositional self-prediction and cannot translate partial self-knowledge into better agentic actions, with external metacognitive control reducing confident failures by ~70-76%.
LLMs predict outcomes of real scientific experiments at 14-26% accuracy, comparable to human experts, but lack calibration on prediction reliability while humans demonstrate strong calibration.
A user study finds that LLM reasoning traces and post-hoc explanations create false trust by increasing acceptance of incorrect answers, whereas contrastive dual explanations improve users' ability to detect errors.
Trajectory geometry in embedding space fused with coverage and verbalization yields better black-box CoT confidence estimation than self-consistency at lower sample counts across six benchmark-reasoner pairs.
Temporal reasoning is not the core bottleneck for LLMs on time-based QA; the real issue is unstructured text-to-event mapping, addressed by a neuro-symbolic system with PIS that reaches 100% accuracy on benchmarks when representations are correct.
Multi-variant testing reveals that prompt design and evaluator choices can change apparent model reliability by large margins, with verbal confidence often overstated and robustness uncorrelated with size.
Large reasoning models show measurable hidden-state dynamics that a new statistic can use to distinguish correct reasoning trajectories without labels.
A hybrid confidence framework for LLM-based short answer grading combines model signals with aleatoric uncertainty from semantic clustering of responses and improves selective grading reliability over single-source methods.
LLMs show poor calibration in predicting task success and token use on software engineering benchmarks, causing market auctions to underperform compared to perfect information scenarios, with limited improvement from added context.
LLMs implement a second-order confidence architecture where the PANL activation encodes both error likelihood and the ability to correct it, beyond verbal confidence or log-probabilities.
Seven 3-9B instruction-tuned LLMs produce verbal confidence that saturates at high values and fails psychometric validity criteria for Type-2 discrimination under minimal elicitation.
Twin-Pass Chain-of-Thought Ensembling cuts Expected Calibration Error by up to 88% in Gemma-3 models on TeleQnA, ORANBench, and srsRANBench.
CAPO improves LLM calibration by up to 15% while matching or exceeding GRPO accuracy through logistic AUC loss and noise masking, enabling better abstention and scaling performance.
CLSGen is a dual-head LLM fine-tuning framework that enables joint probabilistic classification and verbalized explanation generation without catastrophic forgetting of generative capabilities.
LLM confidence for social science text measurements is poorly calibrated across models, and a soft-label distillation pipeline reduces expected calibration error by 43% and Brier score by 34%.
Overthinking in medical QA is linearly decodable at 71.6% accuracy yet fixed residual-stream steering yields no correction across 29 configurations, while enabling selective abstention with AUROC 0.610.
Meta-d' and signal detection theory provide quantitative tools to assess metacognitive sensitivity and risk-based regulation in large language models.
CERTA adds relevance-based certainty estimation to RAG so LLMs can better signal uncertainty on non-objective questions, reducing overconfidence.
A deep research agent incorporates progressive confidence estimation and calibration to produce trustworthy reports with transparent confidence scores on claims.
citing papers explorer
-
Grounded or Guessing? LVLM Confidence Estimation via Blind-Image Contrastive Ranking
BICR uses blind-image contrastive ranking on frozen LVLM hidden states to train a lightweight probe that penalizes confidence on blacked-out inputs, yielding top calibration and discrimination across five models and multiple tasks at low parameter cost.
-
EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium
EquiMem calibrates shared memory in multi-agent debate by computing a game-theoretic equilibrium from agent queries and paths, outperforming heuristics and LLM validators across benchmarks while remaining robust to adversarial agents.
-
MRI-Eval: A Tiered Benchmark for Evaluating LLM Performance on MRI Physics and GE Scanner Operations Knowledge
MRI-Eval benchmark shows frontier LLMs scoring 93-97% on MRI MCQs but falling to 37-61% on stem-only questions, with GE scanner operations as the weakest category for all models.
-
The First Token Knows: Single-Decode Confidence for Hallucination Detection
First-token normalized entropy (phi_first) from one greedy decode reaches mean AUROC 0.820 for hallucination detection, matching or exceeding semantic self-consistency (0.793) and surface self-consistency (0.791) across three 7-8B models and two benchmarks.
-
Don't Start What You Can't Finish: A Counterfactual Audit of Support-State Triage in LLM Agents
LLM agents overcommit on non-complete tasks at 41.7% unless given explicit support-state categories, which raise typed deferral accuracy to 91.7%.
-
MIRROR: A Hierarchical Benchmark for Metacognitive Calibration in Large Language Models
MIRROR benchmark shows LLMs universally fail at compositional self-prediction and cannot translate partial self-knowledge into better agentic actions, with external metacognitive control reducing confident failures by ~70-76%.
-
SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?
LLMs predict outcomes of real scientific experiments at 14-26% accuracy, comparable to human experts, but lack calibration on prediction reliability while humans demonstrate strong calibration.
-
Evaluating the False Trust engendered by LLM Explanations
A user study finds that LLM reasoning traces and post-hoc explanations create false trust by increasing acceptance of incorrect answers, whereas contrastive dual explanations improve users' ability to detect errors.
-
Measuring Black-Box Confidence via Reasoning Trajectories: Geometry, Coverage, and Verbalization
Trajectory geometry in embedding space fused with coverage and verbalization yields better black-box CoT confidence estimation than self-consistency at lower sample counts across six benchmark-reasoner pairs.
-
Temporal Reasoning Is Not the Bottleneck: A Probabilistic Inconsistency Framework for Neuro-Symbolic QA
Temporal reasoning is not the core bottleneck for LLMs on time-based QA; the real issue is unstructured text-to-event mapping, addressed by a neuro-symbolic system with PIS that reaches 100% accuracy on benchmarks when representations are correct.
-
What Single-Prompt Accuracy Misses: A Multi-Variant Reliability Audit of Language Models
Multi-variant testing reveals that prompt design and evaluator choices can change apparent model reliability by large margins, with verbal confidence often overstated and robustness uncorrelated with size.
-
Spatiotemporal Hidden-State Dynamics as a Signature of Internal Reasoning in Large Language Models
Large reasoning models show measurable hidden-state dynamics that a new statistic can use to distinguish correct reasoning trajectories without labels.
-
Confidence Estimation in Automatic Short Answer Grading with LLMs
A hybrid confidence framework for LLM-based short answer grading combines model signals with aleatoric uncertainty from semantic clustering of responses and improves selective grading reliability over single-source methods.
-
MarketBench: Evaluating AI Agents as Market Participants
LLMs show poor calibration in predicting task success and token use on software engineering benchmarks, causing market auctions to underperform compared to perfect information scenarios, with limited improvement from added context.
-
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals
LLMs implement a second-order confidence architecture where the PANL activation encodes both error likelihood and the ability to correct it, beyond verbal confidence or log-probabilities.
-
Verbal Confidence Saturation in 3-9B Open-Weight Instruction-Tuned LLMs: A Pre-Registered Psychometric Validity Screen
Seven 3-9B instruction-tuned LLMs produce verbal confidence that saturates at high values and fails psychometric validity criteria for Type-2 discrimination under minimal elicitation.
-
Enhancing Confidence Estimation in Telco LLMs via Twin-Pass CoT-Ensembling
Twin-Pass Chain-of-Thought Ensembling cuts Expected Calibration Error by up to 88% in Gemma-3 models on TeleQnA, ORANBench, and srsRANBench.
-
Calibration-Aware Policy Optimization for Reasoning LLMs
CAPO improves LLM calibration by up to 15% while matching or exceeding GRPO accuracy through logistic AUC loss and noise masking, enabling better abstention and scaling performance.
-
CLSGen: A Dual-Head Fine-Tuning Framework for Joint Probabilistic Classification and Verbalized Explanation
CLSGen is a dual-head LLM fine-tuning framework that enables joint probabilistic classification and verbalized explanation generation without catastrophic forgetting of generative capabilities.
-
Assessing and Mitigating Miscalibration in LLM-Based Social Science Measurement
LLM confidence for social science text measurements is poorly calibrated across models, and a soft-label distillation pipeline reduces expected calibration error by 43% and Brier score by 34%.
-
Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes
Overthinking in medical QA is linearly decodable at 71.6% accuracy yet fixed residual-stream steering yields no correction across 29 configurations, while enabling selective abstention with AUROC 0.610.
-
Measuring the metacognition of AI
Meta-d' and signal detection theory provide quantitative tools to assess metacognitive sensitivity and risk-based regulation in large language models.
-
"I Don't Know" -- Towards Appropriate Trust with Certainty-Aware Retrieval Augmented Generation
CERTA adds relevance-based certainty estimation to RAG so LLMs can better signal uncertainty on non-objective questions, reducing overconfidence.
-
Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration
A deep research agent incorporates progressive confidence estimation and calibration to produce trustworthy reports with transparent confidence scores on claims.
-
Do Small Language Models Know When They're Wrong? Confidence-Based Cascade Scoring for Educational Assessment
Verbalized confidence from small LMs enables cost-effective cascade routing for automated educational scoring, matching large-model accuracy at 76% lower cost when discrimination is strong.