Research map / Large language models / Language, safety and interpretability
Semantic Uncertainty Quantification of Hallucinations in LLMs: A Quantum Tensor Network Based Method
pragatheeswaran vipulanandan, Kamal Premaratne, Dilip Sarkar
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace Shannon semantic entropy with uncertainty-adjusted Renyi entropy | semantic entropy · Worked example query (oil producer ally of US) | total entropy: 0.22471 -> 0.12951 | Improved |
| use semantic clustering instead of naive entropy | naive entropy · Worked example query (oil producer ally of US) | total entropy: 0.84557 -> 0.22471 | Improved |
| add TS-probability uncertainty adjustment to cluster probabilities | Saudi Arabia cluster · Worked example query (oil producer ally of US) | cluster probability: 0.88824 -> 0.85880 | Hurt |
| add TS-probability uncertainty adjustment to cluster probabilities | Qatar cluster · Worked example query (oil producer ally of US) | cluster probability: 0.00672 -> 0.01214 | Improved |
| add uncertainty-aware entropy maximization | SRE-UQ · 116 experiments (TriviaQA, SQuAD, NQ-Open, SVAMP) | AUROC and AURAC win rate | Improved |
| lower quantization precision from 16-bit to 4-bit | SRE-UQ · 116 experiments | AUROC | Mixed |
Closest papers by meaning
- INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection (ICLR 2024 · similarity 0.91)
- Sample Transform Cost-Based Training-Free Hallucination Detector for Large Language Models (NeurIPS 2026 · similarity 0.90)
- Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detection (AAAI 2025 · similarity 0.90)
- HaDeMiF: Hallucination Detection and Mitigation in Large Language Models (ICLR 2025 · similarity 0.90)
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024 · similarity 0.89)
- Steer LLM Latents for Hallucination Detection (ICML 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
