LLMs struggle to associate epistemic markers with stable internal confidence levels across distributions, even under model-centric interpretations, while maintaining somewhat consistent marker rankings.
On hallucination and predictive uncertainty in conditional language generation
7 Pith papers cite this work, alongside 75 external citations. Polarity classification is still indexing.
7
Pith papers citing it
75
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
CyberCertBench shows frontier LLMs reach human-expert performance on general IT and networking security but drop on vendor-specific and formal standards questions such as IEC 62443, with a new framework for producing interpretable explanations.
Data-similarity and data-influence produce significantly overlapping rankings of training documents for LLM outputs, with asymmetry allowing a favorable cost-accuracy trade-off.
A new framework quantifies faithful confidence expression in large reasoning models by comparing linguistic decisiveness to token probabilities, hidden states, and response consistency, revealing it as a persistent challenge.
Adapts multi-layer token-level Mahalanobis distance with supervised linear regression to yield improved uncertainty scores for LLM truthfulness tasks.
SelfCheckGPT detects hallucinations by checking consistency across multiple sampled responses from black-box LLMs on WikiBio biography generation tasks.
A conformal prediction filter for retrieval chunks plus an attention-based factuality classifier can raise RAG answer quality by up to 6% and detect inconsistent generations up to 77% of the time.
citing papers explorer
-
Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?
LLMs struggle to associate epistemic markers with stable internal confidence levels across distributions, even under model-centric interpretations, while maintaining somewhat consistent marker rankings.
-
CyberCertBench: Evaluating LLMs in Cybersecurity Certification Knowledge
CyberCertBench shows frontier LLMs reach human-expert performance on general IT and networking security but drop on vendor-specific and formal standards questions such as IEC 62443, with a new framework for producing interpretable explanations.
-
Quantifying the Agreement Between Data-Influence and Data-Similarity to Understand LLM Behavior
Data-similarity and data-influence produce significantly overlapping rankings of training documents for LLM outputs, with asymmetry allowing a favorable cost-accuracy trade-off.
-
Quantifying Faithful Confidence Expression in Large Reasoning Models
A new framework quantifies faithful confidence expression in large reasoning models by comparing linguistic decisiveness to token probabilities, hidden states, and response consistency, revealing it as a persistent challenge.
-
Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models
Adapts multi-layer token-level Mahalanobis distance with supervised linear regression to yield improved uncertainty scores for LLM truthfulness tasks.
-
SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models
SelfCheckGPT detects hallucinations by checking consistency across multiple sampled responses from black-box LLMs on WikiBio biography generation tasks.
-
Towards Dependable Retrieval-Augmented Generation Using Factual Confidence Prediction
A conformal prediction filter for retrieval chunks plus an attention-based factuality classifier can raise RAG answer quality by up to 6% and detect inconsistent generations up to 77% of the time.