InfluMatch: Frontier-Quality KOL Search at 4B-Model Cost
Matching influencers (KOLs) to free-form, multi-part Thai marketing criteria is today served either by keyword search over structured profiles, which misses semantic fit, or by prompting frontier LLMs over every candidate, which is accurate but slow and expensive. We present InfluMatch, a low-cost three-stage cascade -- retrieval $\rightarrow$ rerank $\rightarrow$ reason -- built entirely from small open-weight models: dense retrieval returns 50 candidates, a 4B pointwise reranker scores each by the log-probability of a single Yes token and keeps 10, and a 4B reasoner grades the shortlist per
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 46%RAGless: Q-Q retrieval with score aggregation for closed-domain FAQ [P] →
- LinkedLinked via arxiv author · 85%Krittanon Kaewtawee →
“InfluMatch: Frontier-Quality KOL Search at 4B-Model Cost”
- LinkedLinked via arxiv author · 85%Petmongkon Pornpichitsuwan →
“InfluMatch: Frontier-Quality KOL Search at 4B-Model Cost”
- LinkedLinked via arxiv author · 85%Natchaya Temyingyong →
“InfluMatch: Frontier-Quality KOL Search at 4B-Model Cost”
- LinkedLinked via arxiv author · 85%Nutnicha Laplamoon →
“InfluMatch: Frontier-Quality KOL Search at 4B-Model Cost”
- LinkedLinked via arxiv author · 85%Wachiravit Modecrua →
“InfluMatch: Frontier-Quality KOL Search at 4B-Model Cost”
- LinkedLinked via arxiv author · 85%Krittin Pachtrachai →
“InfluMatch: Frontier-Quality KOL Search at 4B-Model Cost”
- LinkedLinked via arxiv author · 85%Touchapon Kraisingkorn →
“InfluMatch: Frontier-Quality KOL Search at 4B-Model Cost”