PhantomBench is a new benchmark of 60K+ non-existent terms showing language models hallucinate at rates up to 86.7 percent even when inputs assume the concepts exist.
Do Large Language Models Know What They Don ' t Know?
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
years
2026 10verdicts
UNVERDICTED 10representative citing papers
LLMs struggle to associate epistemic markers with stable internal confidence levels across distributions, even under model-centric interpretations, while maintaining somewhat consistent marker rankings.
Model-adaptive tool necessity shows 26-54% mismatch with actual tool calls across LLMs, driven by nearly orthogonal hidden-state signals for cognition versus action.
Frontier LLMs struggle to discriminate data uncertainty from model uncertainty even when accurate, but a new benchmark and lightweight RL strategy improve attribution without sacrificing answer accuracy.
RLMF uses quality of model self-judgments to refine RL rankings and select training data, achieving SOTA faithful calibration while preserving accuracy and outperforming standard RL by up to 63%.
BLINKG is a benchmark for evaluating LLMs on mapping input data schemas to ontology concepts for knowledge graph construction, with experiments showing promising but limited performance in complex real-world scenarios.
LaaB improves LLM hallucination detection by mapping self-judgment labels back into neural feature space and using mutual learning under logical consistency constraints between responses and meta-judgments.
LLMs outperform humans in expressing illocutionary intents and sycophancy in successful persuasive counter-arguments from ChangeMyView, with crowd workers preferring LLM versions.
Introduces LLM-FACETS, a privacy-preserving open-source framework for LLM evaluation using deterministic metrics locally, LLM-judge metrics with user-controlled APIs, and mechanisms for uncertainty visualization and hallucination detection.
Hybrid entropy-uncertainty-geometric defence improves clean accuracy by up to 43% and adversarial robustness by up to 65% on NLU and security benchmarks.
citing papers explorer
-
PhantomBench: Benchmarking the Non-existential Threat of Language Models
PhantomBench is a new benchmark of 60K+ non-existent terms showing language models hallucinate at rates up to 86.7 percent even when inputs assume the concepts exist.
-
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.
-
Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use
Model-adaptive tool necessity shows 26-54% mismatch with actual tool calls across LLMs, driven by nearly orthogonal hidden-state signals for cognition versus action.
-
Beyond "I Don't Know": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty
Frontier LLMs struggle to discriminate data uncertainty from model uncertainty even when accurate, but a new benchmark and lightweight RL strategy improve attribution without sacrificing answer accuracy.
-
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs
RLMF uses quality of model self-judgments to refine RL rankings and select training data, achieving SOTA faithful calibration while preserving accuracy and outperforming standard RL by up to 63%.
-
BLINKG: A Benchmark for LLM-Integrated Knowledge Graph Generation
BLINKG is a benchmark for evaluating LLMs on mapping input data schemas to ontology concepts for knowledge graph construction, with experiments showing promising but limited performance in complex real-world scenarios.
-
Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments
LaaB improves LLM hallucination detection by mapping self-judgment labels back into neural feature space and using mutual learning under logical consistency constraints between responses and meta-judgments.
-
"I understand your perspective": LLM Persuasion and Sycophancy through the Lens of Communicative Action Theory
LLMs outperform humans in expressing illocutionary intents and sycophancy in successful persuasive counter-arguments from ChangeMyView, with crowd workers preferring LLM versions.
-
LLM-FACETS: A Privacy-Preserving Framework for Evaluating LLM Transparency and Accountability
Introduces LLM-FACETS, a privacy-preserving open-source framework for LLM evaluation using deterministic metrics locally, LLM-judge metrics with user-controlled APIs, and mechanisms for uncertainty visualization and hallucination detection.
-
Hybrid Adversarial Defence for Natural Language Understanding Tasks
Hybrid entropy-uncertainty-geometric defence improves clean accuracy by up to 43% and adversarial robustness by up to 65% on NLU and security benchmarks.