Count Evidence, Not Sentences: Tempered Evidence Fusion of LLM Judgments for Long-Text Value Measurement
arXiv:2609.27165v1 Announce Type: new Abstract: 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…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-09-24 04:00 · arXiv cs.CL
Count Evidence, Not Sentences: Tempered Evidence Fusion of LLM Judgments for Long-Text Value Measurement