Metraipolis › archive › dc_7b2e9d75a644

Embedding Semantic Entropy: NLI-Free Semantic Uncertainty Estimation with Geometry-Aware Clustering — arXiv:2611.03876

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03876
License (as archived)
CC0-1.0
Archived
2026-11-04T18:53:50.034Z
SHA-256 of the archived text
b7851362e34b494e64dc5409f526bd481bef33d6224185a4b36f298603fd310b
Stable URL of this page
https://metraipolis.com/documento/dc_7b2e9d75a644

How to cite

Embedding Semantic Entropy: NLI-Free Semantic Uncertainty Estimation with Geometry-Aware Clustering — arXiv:2611.03876 — arXiv (en), https://arxiv.org/abs/2611.03876 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7b2e9d75a644 (Metraipolis archive dc_7b2e9d75a644, sha256 b7851362e34b494e64dc5409f526bd481bef33d6224185a4b36f298603fd310b)
BibTeX
@misc{dc7b2e9d75a644,
  title = {Embedding Semantic Entropy: NLI-Free Semantic Uncertainty Estimation with Geometry-Aware Clustering — arXiv:2611.03876},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03876},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7b2e9d75a644; sha256 b7851362e34b494e64dc5409f526bd481bef33d6224185a4b36f298603fd310b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03876. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) often generate fluent yet incorrect responses, making un- certainty estimation important for reliable deployment. Semantic Entropy (SE) estimates uncertainty by clustering responses based on semantic equivalence, but it relies on hard entailment-based clustering. We propose Embedding Semantic Entropy, which replaces entailment-based clustering with K-Medoids in semantic embedding space and uses dynamic cluster selection to account for intra-cluster compactness and inter-cluster separation. We evaluate the method on TriviaQA, SQuAD, NQ-Open, SVAMP, and BioASQ using Falcon- 7B-Instruct, LLaMA-2-7B, LLaMA-2-7B-Chat, and Gemma-7B. Results show competitive AUROC and AUARC performance, suggesting that NLI-based entailment clustering can be replaced with embedding-space clustering with limited degradation while improving the inspectability of semantic grouping. This matters because semantic uncertainty scores depend on underlying semantic groups; by making these groups explicit, compact, and separable in embedding space, Emb-SE turns uncertainty estimation from a black-box en- tailment decision into an inspectable clustering problem.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.03876 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T18:35:37.402Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).