Metraipolis › archive › dc_371cd9b67478
Count Evidence, Not Sentences: Tempered Evidence Fusion of LLM Judgments for Long-Text Value Measurement — arXiv:2609.27165
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.27165
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T09:12:15.432Z
- SHA-256 of the archived text
dc4f02725b691589c6018d40a3bd0fed34bb434b996c3b7ee6eea5922e70f96f- Stable URL of this page
https://metraipolis.com/documento/dc_371cd9b67478
How to cite
Count Evidence, Not Sentences: Tempered Evidence Fusion of LLM Judgments for Long-Text Value Measurement — arXiv:2609.27165 — arXiv (en), https://arxiv.org/abs/2609.27165 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_371cd9b67478 (Metraipolis archive dc_371cd9b67478, sha256 dc4f02725b691589c6018d40a3bd0fed34bb434b996c3b7ee6eea5922e70f96f)
BibTeX
@misc{dc371cd9b67478,
title = {Count Evidence, Not Sentences: Tempered Evidence Fusion of LLM Judgments for Long-Text Value Measurement — arXiv:2609.27165},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.27165},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_371cd9b67478; sha256 dc4f02725b691589c6018d40a3bd0fed34bb434b996c3b7ee6eea5922e70f96f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27165. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) are increasingly used to measure public value orientations from long social media posts, yet such posts often mix background, quotations, concessions, and only a few stance-bearing sentences. Existing approaches either ask the model to predict a document-level label directly, which can be overconfident, or aggregate sentence-level predictions by majority or soft voting, which treat uncertain and decisive sentences as equally informative. We formulate long-text value measurement as a decision-fusion problem and propose Tempered Evidence Fusion (TEF), a training-free rule that weights each sentence's log-odds by its normalized information gain, as derived from a generalized Bayesian posterior. This makes the fused score nearly vanish for uncertain sentences while preserving the Bayes-optimal weight of decisive evidence. We further introduce Multi-event Insight Network Dimensions (MIND), a benchmark of 8,358 Chinese and English posts spanning five years of public events and six value dimensions. On MIND, TEF outperforms the strongest baseline among Direct, Majority Vote, and Soft Vote by an average of 4.5 accuracy points and 4.6 macro-F1 points across five LLMs and two languages. MIND dataset and code are available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.27165 — 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 2026-10-08T08:13:26.627Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).