A product-key parametric memory head with selective sparse updates mitigates catastrophic forgetting in generative retrieval models during sequential addition of new documents.
Mixed citations
ISBN 9798400715921
Mixed citation behavior. Most common role is background (60%).
11
Pith papers citing it
Background
60% of classified citations
citation-role summary
background 3
baseline 2
citation-polarity summary
verdicts
UNVERDICTED 11representative citing papers
PURE reduces preference-inconsistent explanations in LLM recommenders by selecting user-aligned evidence paths and injecting them into generation, while preserving accuracy.
GQR is a test-time optimization technique that refines primary retriever query embeddings using complementary retriever scores to achieve high performance with smaller representations in multimodal visual document retrieval.
APG4RecSim automatically generates realistic user profiles for LLM-based recommendation simulations, outperforming manual baselines by up to 7% in nDCG@10 and 8% in JSD on three benchmark datasets.
Test-time LLM feedback refines query embeddings to deliver up to 25% relative gains on zero-shot literature search, intent detection, and related benchmarks.
Trie-based experiment plans reduce the duration of comparative evaluations of IR pipelines by 26% versus linear plans in a BM25-MonoT5-DuoT5 demonstration on MSMARCO v2.
CAMI frames multi-index construction for semantic retrieval as a budgeted multi-objective portfolio problem and uses agent-guided search plus confidence-aware pruning to find high-recall configurations with reduced evaluation cost.
A gated hybrid contrastive collaborative filtering framework improves hit rate@10 and NDCG@10 on movie review datasets by layer-wise adaptive fusion of semantic and collaborative signals with contrastive objectives.
CroSearch-R1 applies search-augmented RL with cross-lingual integration and multilingual rollouts to improve RAG effectiveness on multilingual collections.
Taiji presents a LLM-as-Enhancer system with reverse-engineered CoT data generation and Pareto Optimal Policy Optimization (POPO) to trade off semantic and ID rewards, deployed at Kuaishou serving 400M daily users.
Multi-objective LTR combining clicks, VLM labels, and locale boosting improves relevance and local content visibility across five growth markets.
citing papers explorer
-
Beyond Factual Correctness: Mitigating Preference-Inconsistent Explanations in Explainable Recommendation
PURE reduces preference-inconsistent explanations in LLM recommenders by selecting user-aligned evidence paths and injecting them into generation, while preserving accuracy.