Pith. sign in

Integrating the Probabilistic Models BM25/BM25F into Lucene

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

This document describes the BM25 and BM25F implementation using the Lucene Java Framework. Both models have stood out at TREC by their performance and are considered as state-of-the-art in the IR community. BM25 is applied to retrieval on plain text documents, that is for documents that do not contain fields, while BM25F is applied to documents with structure.

fields

cs.IR 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Field Aware Agent Skill Retrieval

cs.IR · 2026-08-03 · conditional · novelty 5.0

Splitting an agent skill into its name, description, and body during retrieval, then learning how to weight per-field similarity scores, outperforms flat concatenation on SkillRet and SRA-Bench and gains more as the skill bank grows.

citing papers explorer

Showing 1 of 1 citing paper.

  • Field Aware Agent Skill Retrieval cs.IR · 2026-08-03 · conditional · none · ref 5 · internal anchor

    Splitting an agent skill into its name, description, and body during retrieval, then learning how to weight per-field similarity scores, outperforms flat concatenation on SkillRet and SRA-Bench and gains more as the skill bank grows.