BEAR adds a beam-search-aware regularization to LLM fine-tuning for recommendations that forces positive-item tokens to rank in the top-B candidates at each decoding step to avoid premature pruning.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
years
2026 3representative citing papers
EvoRAG adds a feedback-driven backpropagation step that attributes response quality to individual knowledge-graph triplets and updates the graph to raise reasoning accuracy by 7.34 percent over prior KG-RAG methods.
LWGR applies personalized soft instructions for LLM knowledge extraction and Lagrangian primal-dual optimization to selectively fuse beneficial world knowledge into generative recommendation while bounding degradation.
citing papers explorer
-
BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models
BEAR adds a beam-search-aware regularization to LLM fine-tuning for recommendations that forces positive-item tokens to rank in the top-B candidates at each decoding step to avoid premature pruning.
-
EvoRAG: Making Knowledge Graph-based RAG Automatically Evolve through Feedback-driven Backpropagation
EvoRAG adds a feedback-driven backpropagation step that attributes response quality to individual knowledge-graph triplets and updates the graph to raise reasoning accuracy by 7.34 percent over prior KG-RAG methods.
-
LWGR: Lagrangian-Constrained Personalized World Knowledge for Generative Recommendation
LWGR applies personalized soft instructions for LLM knowledge extraction and Lagrangian primal-dual optimization to selectively fuse beneficial world knowledge into generative recommendation while bounding degradation.