The DECK taxonomy partitions LLM hallucinations into four detectability regimes using consistency and confidence axes, mapping each to scorer families and identifying a universal blind spot for output-level uncertainty quantification on knowledge-gap inputs.
A survey on uncertainty quantification of large language models: Taxonomy, open research challenges, and future directions
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
SemGrad measures LLM uncertainty via gradients in semantic space using a Semantic Preservation Score to select embeddings, with HybridGrad combining it with parameter gradients to outperform sampling-based baselines especially when multiple responses are valid.
Introduces functional equivalence methods and functional entropy to predict functional correctness of LLM-generated code via uncertainty quantification, outperforming NLI-based baselines in most tested settings.
Average token log-probability provides a zero-shot confidence signal for small LLMs that matches supervised baselines in-distribution and outperforms them out-of-distribution, with a new retrieval-conditional variant improving further at lower latency.
LLM OOD detectors are length-confounded; a two-pathway embedding-plus-trajectory framework detects covert OOD inputs at 0.721 average AUROC and 0.850 on jailbreaks.
Cross-model semantic disagreement adds an epistemic uncertainty term that improves total uncertainty estimation over self-consistency alone, helping flag confident errors in LLMs.
The paper consolidates risks of overreliance on LLMs, identifies gaps in current measurement approaches, and proposes mitigation strategies to keep AI as a human-compatible thought partner.
Empirical tests on four GPT models across five uncertainty types found hyper-truth states (T+I+F>1) in 35% of cases, mostly under ethical contradictions and paradoxes.
A survey categorizing LLM-powered agent systems into software-based, physical, and hybrid types, covering industrial applications and challenges such as latency and security.
citing papers explorer
-
Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training
Average token log-probability provides a zero-shot confidence signal for small LLMs that matches supervised baselines in-distribution and outperforms them out-of-distribution, with a new retrieval-conditional variant improving further at lower latency.
-
Measuring and mitigating overreliance to build human-compatible AI
The paper consolidates risks of overreliance on LLMs, identifies gaps in current measurement approaches, and proposes mitigation strategies to keep AI as a human-compatible thought partner.