RouteRec
LLM reranker research, joint-1st by reviewer score at a SIGIR 2026 workshop
Results
- Accepted at the SIGIR 2026 AgentSearch workshop
- Ranked joint-1st by reviewer score
Context
Can an off-the-shelf LLM rerank recommendations reliably? RouteRec is a research paper I co-authored that put open-weight LLMs, including OpenAI's gpt-oss, under stress as recommender-system rerankers.
What I did
- 01Co-authored the paper
- 02Stress-tested open-weight LLMs as rerankers
- 03Mapped where and how LLM reranking fails
Stack
Python / Open-weight LLMs / OpenAI gpt-oss
Related service
More work
04 / Contact
Have something to build? Book a call.
20 minutes, free. Tell me what you need; you leave with a scope, a timeline and a straight answer on whether I'm the right fit.