用 silver evidence 演示替代噪声检索：面向上下文学习的决策证据方法

View PDF HTML (experimental)

Abstract: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.

Subjects:	Computation and Language (cs.CL)
Cite as:	arXiv:2610.32128 [cs.CL]
	(or arXiv:2610.32128v1 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2610.32128 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Masoud Monajatipoor [view email]
[v1] Fri, 23 Oct 2026 03:56:06 UTC (790 KB)