Models delayed verification in multi-agent LLMs as graph consensus, derives stability thresholds (inverse golden ratio for delay two) via grounded Laplacian, and gives a supermodular greedy rule for corrector placement; experiments on five models confirm dose-delay oscillations.
hub Canonical reference
SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models
Canonical reference. 100% of citing Pith papers cite this work as background.
51
Pith papers citing it
Background
100% of classified citations
abstract
Generative Large Language Models (LLMs) such as GPT-3 are capable of generating highly fluent responses to a wide variety of user prompts. However, LLMs are known to hallucinate facts and make non-factual statements which can undermine trust in their output. Existing fact-checking approaches either require access to the output probability distribution (which may not be available for systems such as ChatGPT) or external databases that are interfaced via separate, often complex, modules. In this work, we propose "SelfCheckGPT", a simple sampling-based approach that can be used to fact-check the responses of black-box models in a zero-resource fashion, i.e. without an external database. SelfCheckGPT leverages the simple idea that if an LLM has knowledge of a given concept, sampled responses are likely to be similar and contain consistent facts. However, for hallucinated facts, stochastically sampled responses are likely to diverge and contradict one another. We investigate this approach by using GPT-3 to generate passages about individuals from the WikiBio dataset, and manually annotate the factuality of the generated passages. We demonstrate that SelfCheckGPT can: i) detect non-factual and factual sentences; and ii) rank passages in terms of factuality. We compare our approach to several baselines and show that our approach has considerably higher AUC-PR scores in sentence-level hallucination detection and higher correlation scores in passage-level factuality assessment compared to grey-box methods.
hub tools
citation-role summary
background 9
citation-polarity summary
roles
background 8polarities
background 8representative citing papers
Operadic consistency is a new per-question signal that correlates strongly with accuracy (r 0.86-0.94) across four multi-hop QA datasets and improves selective prediction over CoT-SC baselines.
A per-token feature from temperature-induced changes in LLM token distributions predicts within-prompt creativity rank at Spearman rho 0.918 vs LLM judges and 0.870 vs humans, outperforming perplexity, entropy, top-1 margin, and compression baselines.
Compositional selective specificity (CSS) decomposes generated answers into claims and emits each at the most specific level supported by evidence, raising overcommitment-aware utility from 0.846 to 0.913 on LongFact while retaining 0.938 specificity.
AgentProp-Bench shows substring judging agrees with humans at kappa=0.049, LLM ensemble at 0.432, bad-parameter injection propagates with ~0.62 probability, rejection and recovery are independent, and a runtime fix cuts hallucinations 23pp on GPT-4o-mini but not Gemini-2.0-Flash.
RAGognizer adds a detection head to LLMs for joint training on generation and token-level hallucination detection, yielding SOTA detection and fewer hallucinations in RAG while preserving output quality.
ScrapeGraphAI-100k releases 93,695 real telemetry examples pairing web page content with prompts, schemas, and LLM responses to support training and benchmarking of schema-constrained generation.
LatentRefusal predicts answerability of text-to-SQL queries from LLM hidden states using a Tri-Residual Gated Encoder, reaching 88.5% average F1 across four benchmarks with about 2ms overhead.
TARG uses uncertainty scores from a short no-context draft to gate retrieval in RAG, matching Always-RAG accuracy while cutting retrievals by 70-90% on QA benchmarks.
WizardLM uses LLM-driven iterative rewriting to generate complex instruction data and fine-tunes LLaMA to reach over 90% of ChatGPT capacity on 17 of 29 evaluated skills.
Global calibration metrics like ECE are confounded by accuracy; the proposed ACE framework with three accuracy-controlled views shows many prior calibration advantages weaken or reverse.
Grad Detect uses internal gradient patterns from one inference pass to predict LLM hallucinations and abstention, outperforming confidence and sampling baselines on Q&A benchmarks with most signal in the final five layers.
DeepSurvey introduces an agentic system for automated survey generation that improves depth through full-text keynotes, cross-paper clustering, and code analysis, while boosting citation reliability via graph expansion, hybrid filtering, and evidence-constrained assignment, with reported gains over
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.
EEG study reveals distinct ERP patterns for AI hallucinations, with misjudged ones failing to trigger standard neurocognitive verification pathways.
Semantic distance on program execution behaviors improves uncertainty estimation for LLM code generation and outperforms prior sample-based methods across benchmarks and models.
LLM token rank-frequency distributions converge to a shared Mandelbrot distribution across models and domains, enabling a microsecond-scale statistical primitive for provenance verification and black-box anomaly triage.
A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
Cross-model semantic disagreement adds an epistemic uncertainty term that improves total uncertainty estimation over self-consistency alone, helping flag confident errors in LLMs.
PBRC is a contract protocol that enforces evidential belief updates in deliberative multi-agent systems and proves it prevents conformity-driven false cascades under conservative fallbacks.
RUDDER creates a persistent visual anchor by extracting CARD from prefill residuals and modulating its injection via an adaptive Beta Gate, cutting CHAIR_S by 24.4% and CHAIR_i by 23.6% on average across LLaVA, Idefics2, InstructBLIP and Qwen2.5-VL with >96% throughput.
ReFACT benchmark reveals LLMs show a persistent salient distractor failure mode where 61% of incorrect error span predictions are semantically unrelated to actual errors, persisting across model sizes, and comparative judgment yields lower F1 than independent detection.
The method aggregates multiple hallucination evaluation scores via conformal p-values to enable calibrated detection with controlled false alarm rates across LLMs and datasets.
Adapts multi-layer token-level Mahalanobis distance with supervised linear regression to yield improved uncertainty scores for LLM truthfulness tasks.
citing papers explorer
-
Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement
Models delayed verification in multi-agent LLMs as graph consensus, derives stability thresholds (inverse golden ratio for delay two) via grounded Laplacian, and gives a supermodular greedy rule for corrector placement; experiments on five models confirm dose-delay oscillations.
-
Operadic consistency: a label-free signal for compositional reasoning failures in LLMs
Operadic consistency is a new per-question signal that correlates strongly with accuracy (r 0.86-0.94) across four multi-hop QA datasets and improves selective prediction over CoT-SC baselines.
-
Before and After Temperature: A Distributional View of Creative LLM Generation
A per-token feature from temperature-induced changes in LLM token distributions predicts within-prompt creativity rank at Spearman rho 0.918 vs LLM judges and 0.870 vs humans, outperforming perplexity, entropy, top-1 margin, and compression baselines.
-
Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems
Compositional selective specificity (CSS) decomposes generated answers into claims and emits each at the most specific level supported by evidence, raising overcommitment-aware utility from 0.846 to 0.913 on LongFact while retaining 0.938 specificity.
-
Evaluating Tool-Using Language Agents: Judge Reliability, Propagation Cascades, and Runtime Mitigation in AgentProp-Bench
AgentProp-Bench shows substring judging agrees with humans at kappa=0.049, LLM ensemble at 0.432, bad-parameter injection propagates with ~0.62 probability, rejection and recovery are independent, and a runtime fix cuts hallucinations 23pp on GPT-4o-mini but not Gemini-2.0-Flash.
-
RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration
RAGognizer adds a detection head to LLMs for joint training on generation and token-level hallucination detection, yielding SOTA detection and fewer hallucinations in RAG while preserving output quality.
-
ScrapeGraphAI-100k: Dataset for Schema-Constrained LLM Generation
ScrapeGraphAI-100k releases 93,695 real telemetry examples pairing web page content with prompts, schemas, and LLM responses to support training and benchmarking of schema-constrained generation.
-
LatentRefusal: Latent-Signal Refusal for Unanswerable Text-to-SQL Queries
LatentRefusal predicts answerability of text-to-SQL queries from LLM hidden states using a Tri-Residual Gated Encoder, reaching 88.5% average F1 across four benchmarks with about 2ms overhead.
-
Retrieval as a Decision: Training-Free Adaptive Gating for Efficient RAG
TARG uses uncertainty scores from a short no-context draft to gate retrieval in RAG, matching Always-RAG accuracy while cutting retrievals by 70-90% on QA benchmarks.
-
WizardLM: Empowering large pre-trained language models to follow complex instructions
WizardLM uses LLM-driven iterative rewriting to generate complex instruction data and fine-tunes LLaMA to reach over 90% of ChatGPT capacity on 17 of 29 evaluated skills.
-
When Calibration Rankings Reverse: Accuracy-Controlled Evaluation for Fair Comparison of LLMs
Global calibration metrics like ECE are confounded by accuracy; the proposed ACE framework with three accuracy-controlled views shows many prior calibration advantages weaken or reverse.
-
Grad Detect: Gradient-Based Hallucination Detection in LLMs
Grad Detect uses internal gradient patterns from one inference pass to predict LLM hallucinations and abstention, outperforming confidence and sampling baselines on Q&A benchmarks with most signal in the final five layers.
-
DeepSurvey: Enhancing Analytical Depth and Citation Reliability in Automated Survey Generation
DeepSurvey introduces an agentic system for automated survey generation that improves depth through full-text keynotes, cross-paper clustering, and code analysis, while boosting citation reliability via graph expansion, hybrid filtering, and evidence-constrained assignment, with reported gains over
-
Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification
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.
-
How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study
EEG study reveals distinct ERP patterns for AI hallucinations, with misjudged ones failing to trigger standard neurocognitive verification pathways.
-
Using Semantic Distance to Estimate Uncertainty in LLM-Based Code Generation
Semantic distance on program execution behaviors improves uncertainty estimation for LLM code generation and outperforms prior sample-based methods across benchmarks and models.
-
The Surprising Universality of LLM Outputs: A Real-Time Verification Primitive
LLM token rank-frequency distributions converge to a shared Mandelbrot distribution across models and domains, enabling a microsecond-scale statistical primitive for provenance verification and black-box anomaly triage.
-
Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives
A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
-
Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification
Cross-model semantic disagreement adds an epistemic uncertainty term that improves total uncertainty estimation over self-consistency alone, helping flag confident errors in LLMs.
-
Preregistered Belief Revision Contracts
PBRC is a contract protocol that enforces evidential belief updates in deliberative multi-agent systems and proves it prevents conformity-driven false cascades under conservative fallbacks.
-
Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models
RUDDER creates a persistent visual anchor by extracting CARD from prefill residuals and modulating its injection via an adaptive Beta Gate, cutting CHAIR_S by 24.4% and CHAIR_i by 23.6% on average across LLaVA, Idefics2, InstructBLIP and Qwen2.5-VL with >96% throughput.
-
ReFACT: A Benchmark for Scientific Confabulation Detection with Positional Error Annotations
ReFACT benchmark reveals LLMs show a persistent salient distractor failure mode where 61% of incorrect error span predictions are semantically unrelated to actual errors, persisting across model sizes, and comparative judgment yields lower F1 than independent detection.
-
Principled Detection of Hallucinations in Large Language Models via Multiple Testing
The method aggregates multiple hallucination evaluation scores via conformal p-values to enable calibrated detection with controlled false alarm rates across LLMs and datasets.
-
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.
-
From Local to Global: A Graph RAG Approach to Query-Focused Summarization
GraphRAG improves comprehensiveness and diversity of answers to global questions over million-token document sets by constructing entity graphs and hierarchical community summaries before combining partial responses.
-
Ragas: Automated Evaluation of Retrieval Augmented Generation
Ragas supplies reference-free metrics for measuring context relevance, faithfulness to retrieved passages, and answer quality in RAG pipelines.
-
Chain-of-Verification Reduces Hallucination in Large Language Models
Chain-of-Verification reduces hallucinations in large language models by drafting responses, planning independent verification questions, answering them separately, and generating a final verified output.
-
DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
DoLa reduces hallucinations in LLMs by contrasting logits from later versus earlier layers during decoding, improving truthfulness on TruthfulQA by 12-17 absolute points without fine-tuning or retrieval.
-
TRACE: A taxonomy-grounded synthetic dataset for teaching-program generation and session interpretation in Applied Behavior Analysis
TRACE is a taxonomy-grounded synthetic instruction-tuning dataset with 2,999 examples for ABA teaching-program generation and multi-session behavioral interpretation, released with code, provenance, and stratified splits.
-
StepGap: A Hybrid NLI-LLM Checker for Step-Level Evidence-Gap Detectionin Multi-Hop Question Answering
StepGap hybrid checker detects typed evidence gaps in multi-hop QA steps with sF1 72.0 and boosts downstream model EM by 3.3 points when used as GRPO reward.
-
Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization
Identifies two gaps in entropy-based uncertainty for LLM post-training and proposes GCPO to align geometry-aware disagreement measures with reward-based calibration for better gradient regulation.
-
Pramana: A Protocol-Layer Treatment of Claim Verification in Autonomous Agent Networks
Pramana defines a typed ClaimAttestation protocol with four variants and verify operations, specifies its lifecycle in TLA+, model-checks it with TLC, and provides a tested Python implementation for auditable agent claims.
-
Evaluating the False Trust Engendered by LLM Explanations
LLM reasoning traces and post-hoc explanations increase false trust in incorrect predictions, whereas contrastive dual explanations enhance users' ability to distinguish correct from incorrect AI outputs.
-
Mask-to-Correct$^+$: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction
Mask-to-Correct and M2C+ use diversity-aware masking in RAG to identify erroneous claim spans and produce faithful corrections, outperforming baselines by up to 14% SARI without gold evidence.
-
Calibrating Model-Based Evaluation Metrics for Summarization
A reference-free proxy scoring framework combined with GIRB calibration produces better-aligned evaluation metrics for summarization and outperforms baselines across seven datasets.
-
Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs
HETA is a new attribution framework for decoder-only LLMs that combines semantic transition vectors, Hessian-based sensitivity scores, and KL divergence to produce more faithful and human-aligned token attributions than prior methods.
-
KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality
KnowRL integrates a knowledge-verification factuality reward into RL training to enforce fact-based reasoning steps and lower hallucination rates in LLMs.
-
TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
TokUR estimates token-level uncertainty via low-rank weight perturbations in LLMs, aggregates signals to correlate with correctness, and uses them to improve reasoning performance on math tasks.
-
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
-
Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Survey organizes LLM trustworthiness into seven categories and 29 sub-categories, measures eight sub-categories on popular models, and finds that more aligned models generally score higher but with varying effectiveness.
-
Peeking Inside LLMs: Leveraging Internal Artifacts of LLMs for Enhancing Reliability in Legal Classification
Internal LLM artifacts can be used to build classifiers that identify incorrect predictions on legal classification tasks.
-
Intelligence as Managed Autonomy: Failure, Escalation, and Governance for Agentic AI Systems
Introduces the SMARt four-layer model with timed guarded Petri nets to formalize detection of epistemic drift, recovery, and controlled surrender of autonomy in AI agents.
-
Bidirectional Empowerment of Metamorphic Testing and Large Language Models: A Systematic Survey
A systematic survey of 93 studies that maps the bidirectional relationship between metamorphic testing and LLMs, proposing a taxonomy for MT applied to LLMs and LLMs applied to MT.
-
HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMs
HalluScan benchmark evaluates hallucination detection in LLMs, reporting NLI Verification at AUROC 0.88 and introducing HalluScore (r=0.41 with humans) plus Adaptive Detection Routing for 2x cost savings.
-
Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)
HUMBR reduces LLM hallucinations in enterprise workflows by using a hybrid semantic-lexical utility within minimum Bayes risk decoding to identify consensus outputs, with derived error bounds and reported outperformance over self-consistency on benchmarks and production data.
-
Conversations Risk Detection LLMs in Financial Agents via Multi-Stage Generative Rollout
FinSec is a multi-stage detection system for financial LLM dialogues that reaches 90.13% F1 score, cuts attack success rate to 9.09%, and raises AUPRC to 0.9189.
-
LLM4Log: A Systematic Review of Large Language Model-based Log Analysis
Systematic review of 145 papers on LLM-based log analysis, providing a unified taxonomy, common design patterns, evaluation practices, and challenges for deployment under drift and limited labels.
-
Self-Reported Confidence of Large Language Models in Gastroenterology: Analysis of Commercial, Open-Source, and Quantized Models
LLMs show improved accuracy on gastroenterology questions but remain overconfident in self-reported certainty across commercial, open-source, and quantized variants.
-
The Rise and Potential of Large Language Model Based Agents: A Survey
The paper surveys the origins, frameworks, applications, and open challenges of AI agents built on large language models.
-
A Survey of Hallucination in Large Foundation Models
A survey classifying hallucination phenomena specific to large foundation models, establishing evaluation criteria, examining mitigation strategies, and discussing future directions.