arXiv AI
Aug 21
Improved Confidence Estimates for Black-Box Large Language Models
arXiv:2608. 19323v1 Announce Type: cross Abstract: Uncertainty quantification (UQ) is essential for the safe deployment of large language models (LLMs).
The Score Granularity Gap in Black-Box LLM Classification: A Comparative Study of Confidence Constructions
The paper investigates the "score granularity gap" in black-box large language model (LLM) classifiers, asking how finely a confidence score can be thresholded for deployment. By comparing seven confidence construction methods across 25 model-dataset pairs, the authors find that single-shot verbalized confidence, when properly converted to a probability, ranks well but offers only a few distinct threshold values, limiting operational flexibility. The study also shows that multi-query aggregation can improve weak models but may harm strong ones, and provides concrete guidance for deployment trade-offs.
Related stories
arXiv Computation and Language
Sep 28
Large Language Model Selection with Limited Annotations
arXiv:2605.24981v2 Announce Type: replace Abstract: Choosing a Large Language Model (LLM) for a given task requires comparing many strong candidates, yet standard evaluation relies on costly annotati...
Hugging Face Trending Papers
Aug 5
Evaluation Pitfalls and Sparsity Limitations in LLM-based Confidence Estimates for Classification
Confidence estimation is essential when LLMs are used for classification, indicating when predictions can be trusted. However, common approaches such as verbalization produce extremely sparse outputs.
arXiv Computation and Language
Sep 10
ProbPlug: A Plugin Uncertainty Network for Reliable Confidence in LLM Binary Classification
arXiv:2609.10122v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance across a broad range of classification settings, yet the reliability of their predictions...
arXiv Computation and Language
Sep 11
Rethinking Verbalized Confidence for LLM-as-a-Judge: A Compatibility Shift on Post-2025 Proprietary Models
The paper argues that verbalized confidence—once viewed as overconfident and coarse—has become the preferred soft‑scoring method for LLM‑as‑a‑Judge on top‑tier proprietary models released after 2025. Experiments on SummEval, AggreFact, and HelpSteer2 across up to 18 LLMs show that log‑probabilities are no longer the best signal, and that adding an overconfidence advisory and self‑debate further improves calibration and robustness. The authors note that these enhancements incur little accuracy loss on post‑2025 models but do affect pre‑2025 ones, highlighting a compatibility shift in how confidence should be measured.
arXiv AI
Jul 29
Beyond Self-Knowledge: Propagating Uncertainty Across Reasoning and Retrieval in LLMs
arXiv:2607. 25600v1 Announce Type: cross Abstract: Retrieval-augmented generation improves knowledge-intensive question answering, but indiscriminate retrieval can introduce irrelevant evidence and unnecessary computation.
Hugging Face Trending Papers
Sep 29
Probability is Not Enough: Exploring and Counting Divergent Tokens for Reasoning Uncertainty Quantification in LLMs
As the chain-of-thought reasoning capabilities of large language models improve, evaluating and calibrating their reasoning confidence is becoming increasingly important for quantifying the uncertaint...
arXiv AI
Sep 30
Probability is Not Enough: Exploring and Counting Divergent Tokens for Reasoning Uncertainty Quantification in LLMs
The paper introduces Divergent Token Confidence (DTC), a method that estimates large language model confidence by counting tokens where two models strongly disagree during decoding. DTC uses Jensen-Shannon divergence between next-token distributions along the same reasoning trajectory and shows a near-negative correlation with answer accuracy. Experiments on multiple model families and six mathematical benchmarks demonstrate that DTC improves calibration over traditional probability-based and verbalized baselines, achieving lower expected calibration errors in both white-box and black-box settings.
arXiv Computation and Language
Sep 21
Do small language models know what they don't know?
arXiv:2609.20824v1 Announce Type: new Abstract: We explore whether entropy-based confidence signals can be leveraged to improve the accuracy of Small Language Models (SLMs) with fewer than 3 billion...
arXiv AI
Jul 7
Consistent but Miscalibrated: Evaluating LLM Limitations for Risk Communication in Natural Language
arXiv:2607. 03882v1 Announce Type: cross Abstract: LLMs are increasingly deployed as post-hoc explainers of AI-generated outputs, yet it remains unclear whether they can reliably communicate probabilistic information in natural language.
arXiv Computation and Language
Sep 22
Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning
arXiv:2604.08974v2 Announce Type: replace Abstract: Uncertainty quantification techniques measure confidence in language model outputs to support critical applications like hallucination detection an...
arXiv AI
Jun 10
RankLLM: Weighted Ranking of LLMs by Quantifying Question Difficulty
arXiv:2602. 12424v2 Announce Type: replace-cross Abstract: Benchmarks establish a standardized evaluation framework to systematically assess the performance of large language models (LLMs), facilitating objective comparisons and driving advancements in the field.