Semantic distance on program execution behaviors improves uncertainty estimation for LLM code generation and outperforms prior sample-based methods across benchmarks and models.
Chainpoll: A high efficacy method for llm hallucination detection
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
verdicts
UNVERDICTED 3representative citing papers
Probabilistic circuits detect LLM hallucinations as residual-stream anomalies with up to 99% AUROC and enable dynamic correction that raises truthfulness scores while cutting unnecessary output corruption.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
citing papers explorer
-
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.
-
Hallucination as an Anomaly: Dynamic Intervention via Probabilistic Circuits
Probabilistic circuits detect LLM hallucinations as residual-stream anomalies with up to 99% AUROC and enable dynamic correction that raises truthfulness scores while cutting unnecessary output corruption.
-
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.