Metraipolis › archive › dc_04e451ff4ddc

Should I Be Polite to My LLM Relevance Judge? Tone as a Severity Operating-Point Shift — arXiv:2609.09703

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.09703
License (as archived): CC0-1.0
Archived: 2026-10-16T10:56:50.805Z
SHA-256 of the archived text: 2627b231b5996484b2e2e9804e16b5dedc15b876201cac6ac7d45f73c1281358
Stable URL of this page: https://metraipolis.com/documento/dc_04e451ff4ddc

How to cite

Should I Be Polite to My LLM Relevance Judge? Tone as a Severity Operating-Point Shift — arXiv:2609.09703 — arXiv (en), https://arxiv.org/abs/2609.09703 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_04e451ff4ddc (Metraipolis archive dc_04e451ff4ddc, sha256 2627b231b5996484b2e2e9804e16b5dedc15b876201cac6ac7d45f73c1281358)

BibTeX

@misc{dc04e451ff4ddc,
  title = {Should I Be Polite to My LLM Relevance Judge? Tone as a Severity Operating-Point Shift — arXiv:2609.09703},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09703},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_04e451ff4ddc; sha256 2627b231b5996484b2e2e9804e16b5dedc15b876201cac6ac7d45f73c1281358},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09703. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models are increasingly used as relevance judges, yet their labels can shift with prompt surface form. We study one such feature -- tone -- on 3,498 TREC DL19/DL20 query-passage pairs, across eight judge models, five classifier-calibrated politeness levels, and three paraphrases per level. Effects are strongly model-dependent: one judge shows a structured U-shaped response, whereas most show only small changes. Where tone changes agreement, the results are more consistent with a shift in the judge's severity operating point -- its overall scoring leniency -- than with improved judgment. Agreement rises or falls as this shift moves the judge toward or away from human annotators' strictness. A query-disjoint cross-fit retains the expected association (Spearman $\rho = -0.683$; exact model-block permutation $p = 0.019$). Tone affects calibration-based agreement more than ranking outcomes: across 32 model-tone contrasts, the largest absolute mean change in NDCG@10 is 0.011, although Kendall's $\tau$ as low as 0.743 shows that reordering is reduced, not absent. The account reconciles prior contradictory findings and identifies prompt tone as a potential validity threat when absolute relevance labels matter.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-10 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.09703 — 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 2026-10-16T10:02:15.204Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).