RPTune is an end-to-end framework that learns to curate product catalogs for LLMs. It uses an encoder-reorganizer to order and prune items based on LLM feedback, and then post-trains the LLM with a context-relative reward. On 7 real merchants with 100 complex queries each, context curation improved accuracy by up to 31.4 percentage points, and post-training added another 10.3 points on average. The method allows small merchants to achieve accuracy comparable to larger models with up to 21x speedup.
Learned context curation boosts LLM catalog search accuracy
RPTune combines product pruning/reordering with LLM post-training to improve search results for small merchants.
Big Tech
Chuxuan Hu · Hejie Cui · Norman Huang · Shubham Kumar Bharti · Wang-Chiew Tan · Sercan Ö. Arık
Google · University of Illinois Urbana-Champaign
Research Digest··2 min read
In one line
Context curation and post-training with RPTune improves LLM catalog search accuracy by up to 31.4 percentage points.
Before you read this
Three ideas this paper builds oncontext compactionCompressing or summarizing an LLM's past context into a smaller representation to extend memory and improve reasoning within limited token budgets.81 papers →large language modelA neural network trained on massive text corpora to generate coherent text and perform diverse language tasks.329 papers →reinforcement learningA machine learning method where an agent learns to make sequences of decisions by receiving rewards or penalties for its actions.296 papers →
Read it as
The authors propose RPTune, a framework that learns how to curate product catalogs for long-context LLMs and fine-tunes the LLM to better use the curated input.
Kaplan et al. studied in-context catalog search for small merchants with catalogs small enough to fit in an LLM context window.
How it works
before and afterThe Daily Edition
The front page in your inbox each weekday morning: the lead, the picks, and why each one earned its place.