Research map / Large language models / Language, safety and interpretability
GAUSS: Graph-Assisted Uncertainty Quantification using Structure and Semantics for Long-Form Generation in LLMs
Karthik Somayaji NS, Yuxuan Yin, Peng Li
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 |
|---|---|---|---|
| use GAUSS graph alignment instead of Gen-Binary | falcon-7b-instruct · Bios | SC: -0.1535 -> -0.4118 | Improved |
| use GAUSS graph alignment instead of Gen-Binary | llama3-8b-instruct · Bios | SC: -0.5986 -> -0.7066 | Improved |
| use GAUSS graph alignment instead of Gen-Binary | qwen2-57b-instruct · LongFact | SC: -0.3328 -> -0.4226 | Improved |
| use GAUSS graph alignment instead of Gen-Binary | falcon-7b-instruct · WildHallu | SC: -0.7628 -> -0.7565 | No clear effect |
| use GAUSS graph alignment instead of Gen-Binary | falcon-7b-instruct · LongFact | SC: -0.6443 -> -0.6555 | No clear effect |
| use GAUSS graph alignment instead of Centrality | qwen2-57b-instruct · WildHallu | SC: -0.3728 -> -0.6852 | Improved |
| use GAUSS instead of LUQ | mistral-7b-instruct · Bios | SC: 0.0541 -> -0.6643 | Improved |
| add structural cost (alpha above 0) to semantic-only alignment (ablation) | GAUSS · Bios, LongFact, WildHallu (5 LLMs) | SC, PC | Improved |
| add semantic cost (alpha below 1) to structural-only alignment (ablation) | GAUSS · Bios, LongFact, WildHallu (5 LLMs) | SC, PC | Improved |
Closest papers by meaning
- Graph-based Uncertainty Metrics for Long-form Language Model Generations (NeurIPS 2024 · similarity 0.90)
- Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities (NeurIPS 2024 · similarity 0.88)
- Benchmarking LLMs via Uncertainty Quantification (NeurIPS 2024 · similarity 0.88)
- Improving Uncertainty Estimation through Semantically Diverse Language Generation (ICLR 2025 · similarity 0.88)
- Distinguishing the Knowable from the Unknowable with Language Models (ICML 2024 · similarity 0.88)
- To Believe or Not to Believe Your LLM: Iterative Prompting for Estimating Epistemic Uncertainty (NeurIPS 2024 · similarity 0.87)
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.
