Metraipolis › archive › dc_c76ed52f4f8d

From Noisy Retrieval to Decision Evidence: Silver Evidence Demonstrations for In-Context Learning — arXiv:2610.32128

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.32128
License (as archived)
CC0-1.0
Archived
2026-10-26T19:53:27.049Z
SHA-256 of the archived text
a950e8a0761956eab6b3bdfc876c54fb543ee452203283483942c036b9fe6a13
Stable URL of this page
https://metraipolis.com/documento/dc_c76ed52f4f8d

How to cite

From Noisy Retrieval to Decision Evidence: Silver Evidence Demonstrations for In-Context Learning — arXiv:2610.32128 — arXiv (en), https://arxiv.org/abs/2610.32128 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c76ed52f4f8d (Metraipolis archive dc_c76ed52f4f8d, sha256 a950e8a0761956eab6b3bdfc876c54fb543ee452203283483942c036b9fe6a13)
BibTeX
@misc{dcc76ed52f4f8d,
  title = {From Noisy Retrieval to Decision Evidence: Silver Evidence Demonstrations for In-Context Learning — arXiv:2610.32128},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32128},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c76ed52f4f8d; sha256 a950e8a0761956eab6b3bdfc876c54fb543ee452203283483942c036b9fe6a13},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32128. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

RAG and retrieval-augmented few-shot ICL can struggle when decision-relevant evidence is buried in long, noisy context. Retrieved passages and demonstrations may contain redundant or distracting information. Although expert-labeled development examples may identify the text supporting each decision, these annotations are typically used only as answer-side rationales rather than as supervision for filtering noisy retrieval. We propose silver-evidence demonstrations, which replace raw retrieved passages in ICL examples with generated, target-conditioned evidence summaries. For each labeled development example, an LLM generates silver evidence without access to the expert label or gold evidence; this evidence is then paired with the expert label and gold evidence where available. At test time, a single structured call generates silver evidence from retrieved passages and then predicts the final label and decision evidence. Across EI 2.0, SciFact, synthetic policy retrieval, and HICRIC/IMR data, our full method improves over equally sized gold-only ICL (label-only for policy) on three of four datasets and improves evidence F1 on all annotated datasets. It also achieves higher mean label accuracy than InstructRAG-style ICL on all four datasets. These results suggest that replacing demonstration-side retrieved passages with compact, target-conditioned silver evidence is particularly useful for decisions based on long and noisy text, where it reduces distracting context while preserving decision-relevant signals and expert supervision.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.32128 — 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 2026-10-26T19:45:48.347Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).