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.
citation dossier
Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models
17Pith papers citing it
17reference links
cs.CLtop field · 8 papers
UNVERDICTEDtop verdict bucket · 14 papers
why this work matters in Pith
Pith has found this work in 17 reviewed papers. Its strongest current cluster is cs.CL (8 papers). The largest review-status bucket among citing papers is UNVERDICTED (14 papers). For highly cited works, this page shows a dossier first and a bounded explorer second; it never tries to render every citing paper at once.
representative citing papers
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.
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.
A user study finds that LLM reasoning traces and post-hoc explanations create false trust by increasing acceptance of incorrect answers, whereas contrastive dual explanations improve users' ability to detect errors.
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.
Compositional selective specificity (CSS) improves overcommitment-aware utility from 0.846 to 0.913 on LongFact while retaining 0.938 specificity by calibrating claim-level backoffs in agentic AI responses.
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.
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.
A reference-free proxy scoring framework combined with GIRB calibration produces better-aligned evaluation metrics for summarization and outperforms baselines across seven datasets.
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.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
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.
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.
The paper surveys the origins, frameworks, applications, and open challenges of AI agents built on large language models.
citing papers explorer
-
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.
-
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.
-
Evaluating the False Trust engendered by LLM Explanations
A user study finds that LLM reasoning traces and post-hoc explanations create false trust by increasing acceptance of incorrect answers, whereas contrastive dual explanations improve users' ability to detect errors.
-
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.
-
Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems
Compositional selective specificity (CSS) improves overcommitment-aware utility from 0.846 to 0.913 on LongFact while retaining 0.938 specificity by calibrating claim-level backoffs in agentic AI responses.
-
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.
-
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.
-
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.
-
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.
-
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.
-
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.