A unified benchmark of 24 black-box UE methods for LLMs finds no universal winner but favors methods that reason over answer candidates and hybrid combinations of signals.
hub
Large language models hallucination: A comprehen- sive survey
18 Pith papers cite this work, alongside 6 external citations. Polarity classification is still indexing.
18
Pith papers citing it
6
external citations · external index
hub tools
citation-role summary
background 2
citation-polarity summary
years
2026 18roles
background 2representative citing papers
Autoregressive transformers exhibit measurable cognitive fatigue during extended generation, quantified by the Fatigue Index that predicts degradation (AUROC 0.95) and repetition (rho 0.94).
HalluScore is a curated Arabic QA dataset with 827 questions, ground-truth evidence, and human annotations used to measure hallucination rates across 17 LLMs.
A large-scale multilingual evaluation of LLM uncertainty estimation methods across 22 languages and 9 models finds that English reasoning closes the UE gap for low-resource languages and that optimal UE method choice depends on model scale.
PseudoBench shows current LLM agents produce persuasive pseudoscientific reports with near-zero refusal rates and at most 27.4% resistance.
SANE is a new schema-aware benchmark paradigm for text-to-SQL evaluation that demonstrates few-shot LLMs with structured prompting can generate accurate queries on constrained biological data schemas without fine-tuning.
HEAR uses a stratified hypergraph ontology to orchestrate evidence-driven multi-hop reasoning over heterogeneous business systems, reaching 94.7% accuracy on supply-chain root-cause tasks with open-weight models.
LLM reliability techniques are unified as communication channel operators, with a new cost-aware router achieving superior quality-cost tradeoffs on hard tasks.
SensingAgents is a multi-agent LLM framework that reaches 79.5% zero-shot accuracy on IMU activity recognition by using position-specific analysts, debating advocates, and a final decision agent, beating prior agent and deep-learning baselines.
Case study of CMBAgent on 18 astrophysical tasks finds strong performance on well-specified problems but frequent silent failures yielding physically inconsistent outputs.
SmartVector augments embeddings with time, confidence, and relation signals plus a consolidation process, raising top-1 accuracy on versioned queries from 31% to 62% on a synthetic benchmark while cutting stale answers and calibration error.
Hybrid human-AI prediction markets match or slightly outperform AI-only markets at forecasting scientific replication outcomes across six social science disciplines.
LLM hallucinations arise from task-dependent basins in latent space, with separability varying by task and geometry-aware steering reducing their probability.
Meta-d′ and signal detection theory give comparable measures of AI metacognitive sensitivity and risk-sensitive decision regulation, demonstrated on three LLMs.
Per-Entity Bias Mapping claims aggregate visibility metrics fail because large brands exhibit higher fabricated citation rates than smaller ones in AI responses, attributed to the Brand Hallucination Paradox.
AI tools deliver useful overviews for research exploration but prove unreliable for precise information extraction and systematic reviews due to low explainability, reproducibility, and transparency.
Authors derive three principles for resilient LLM-assisted digital twin workflows: orthogonalize structure from parameters, restrict to library component interconnections, and use density-preserving Python IR to limit hallucination accumulation.
Hallucinations are mapped as outputs of self-attention entity confusion, MLE lack of factual constraint, and autoregressive error cascade, using an existing taxonomy.
citing papers explorer
-
A Systematic Evaluation of Black-Box Uncertainty Estimation Methods for Large Language Models
A unified benchmark of 24 black-box UE methods for LLMs finds no universal winner but favors methods that reason over answer candidates and hybrid combinations of signals.
-
Cognitive Fatigue in Autoregressive Transformers: Formalization and Measurement
Autoregressive transformers exhibit measurable cognitive fatigue during extended generation, quantified by the Fatigue Index that predicts degradation (AUROC 0.95) and repetition (rho 0.94).
-
HalluScore: Large Language Model Hallucination Question Answering Benchmark
HalluScore is a curated Arabic QA dataset with 827 questions, ground-truth evidence, and human annotations used to measure hallucination rates across 17 LLMs.
-
Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs
A large-scale multilingual evaluation of LLM uncertainty estimation methods across 22 languages and 9 models finds that English reasoning closes the UE gap for low-resource languages and that optimal UE method choice depends on model scale.
-
PseudoBench: Measuring How Agentic Auto-Research Fuels Pseudoscience
PseudoBench shows current LLM agents produce persuasive pseudoscientific reports with near-zero refusal rates and at most 27.4% resistance.
-
SANE Schema-aware Natural-language Evaluation of Biological Data
SANE is a new schema-aware benchmark paradigm for text-to-SQL evaluation that demonstrates few-shot LLMs with structured prompting can generate accurate queries on constrained biological data schemas without fine-tuning.
-
Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems
HEAR uses a stratified hypergraph ontology to orchestrate evidence-driven multi-hop reasoning over heterogeneous business systems, reaching 94.7% accuracy on supply-chain root-cause tasks with open-weight models.
-
A Communication-Theoretic Framework for LLM Agents: Cost-Aware Adaptive Reliability
LLM reliability techniques are unified as communication channel operators, with a new cost-aware router achieving superior quality-cost tradeoffs on hard tasks.
-
SensingAgents: A Multi-Agent Collaborative Framework for Robust IMU Activity Recognition
SensingAgents is a multi-agent LLM framework that reaches 79.5% zero-shot accuracy on IMU activity recognition by using position-specific analysts, debating advocates, and a final decision agent, beating prior agent and deep-learning baselines.
-
Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflows
Case study of CMBAgent on 18 astrophysical tasks finds strong performance on well-specified problems but frequent silent failures yielding physically inconsistent outputs.
-
Self-Aware Vector Embeddings for Retrieval-Augmented Generation: A Neuroscience-Inspired Framework for Temporal, Confidence-Weighted, and Relational Knowledge
SmartVector augments embeddings with time, confidence, and relation signals plus a consolidation process, raising top-1 accuracy on versioned queries from 31% to 62% on a synthetic benchmark while cutting stale answers and calibration error.
-
Human-AI Collaboration for Estimating Scientific Replicability
Hybrid human-AI prediction markets match or slightly outperform AI-only markets at forecasting scientific replication outcomes across six social science disciplines.
-
Hallucination Basins: A Dynamic Framework for Understanding and Controlling LLM Hallucinations
LLM hallucinations arise from task-dependent basins in latent space, with separability varying by task and geometry-aware steering reducing their probability.
-
Measuring the metacognition of AI
Meta-d′ and signal detection theory give comparable measures of AI metacognitive sensitivity and risk-sensitive decision regulation, demonstrated on three LLMs.
-
Per-Entity Bias Mapping for AI Visibility: Why Brand Mentions Require Entity-Specific Calibration
Per-Entity Bias Mapping claims aggregate visibility metrics fail because large brands exhibit higher fabricated citation rates than smaller ones in AI responses, attributed to the Brand Hallucination Paradox.
-
Useful for Exploration, Risky for Precision: Evaluating AI Tools in Academic Research
AI tools deliver useful overviews for research exploration but prove unreliable for precise information extraction and systematic reviews due to low explainability, reproducibility, and transparency.
-
On Integrating Resilience and Human Oversight into LLM-Assisted Modeling Workflows for Digital Twins
Authors derive three principles for resilient LLM-assisted digital twin workflows: orthogonalize structure from parameters, restrict to library component interconnections, and use density-preserving Python IR to limit hallucination accumulation.
-
From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data
Hallucinations are mapped as outputs of self-attention entity confusion, MLE lack of factual constraint, and autoregressive error cascade, using an existing taxonomy.