OSA improves LLM-based recommenders by anchoring ordinal preference levels as numeric tokens in the model's latent space to retain fine-grained strength information when fusing collaborative signals.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Introduces the LLM ORDER BY semantic operator with algorithmic improvements, a semantic-aware external merge sort, and a budget-aware optimizer that selects near-optimal access paths for LLM-based ordering.
A re-ranking system for rich-media search that plans query intents from sessions, adds visual signals from VLMs, and uses an LLM to score results on multiple facets before multi-task RL adaptation, with reported gains in engagement after industrial deployment.
Argues for a denoising-first paradigm in LLM-oriented information retrieval, framing challenges via a four-stage progression and providing a taxonomy of signal-to-noise optimization techniques across the pipeline.
citing papers explorer
-
Every Preference Has Its Strength: Injecting Ordinal Semantics into LLM-Based Recommenders
OSA improves LLM-based recommenders by anchoring ordinal preference levels as numeric tokens in the model's latent space to retain fine-grained strength information when fusing collaborative signals.
-
Access Paths for Efficient Ordering with Large Language Models
Introduces the LLM ORDER BY semantic operator with algorithmic improvements, a semantic-aware external merge sort, and a budget-aware optimizer that selects near-optimal access paths for LLM-based ordering.
-
Rich-Media Re-Ranker: A User Satisfaction-Driven LLM Re-ranking Framework for Rich-Media Search
A re-ranking system for rich-media search that plans query intents from sessions, adds visual signals from VLMs, and uses an LLM to score results on multiple facets before multi-task RL adaptation, with reported gains in engagement after industrial deployment.
-
LLM-Oriented Information Retrieval: A Denoising-First Perspective
Argues for a denoising-first paradigm in LLM-oriented information retrieval, framing challenges via a four-stage progression and providing a taxonomy of signal-to-noise optimization techniques across the pipeline.